Papers by Yang Wang

Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language Models (2025.emnlp-main)

Challenge:	ProUIE improves universal information extraction (UIE) without external information . many LLM-based methods rely on extra schema cues, external resources or complex alignment and verification pipelines .
Approach:	They propose a Macro-to-Micro progressive learning approach that improves UIE without external information.
Outcome:	ProUIE outperforms instruction-tuned baselines on average for NER and RE while using a smaller backbone.

Copied to clipboard

Zihao Li, Xu Wang, Yuzhe Yang, Ziyu Yao, Haoyi Xiong, Mengnan Du

Progra: Progress-Aware Reinforcement Learning for Multi-Turn Function Calling (2026.findings-acl)

Challenge:	Large Language Models (LLMs) can solve reasoning and mathematical problems using the Chain-of-Thought technique, but require costly and long CoT data and fine-tuning.
Approach:	They propose a method that uses Sparse Autoencoders to extract interpretable features from vanilla CoT and use them to steer the LLM's internal states.
Outcome:	The proposed method uses Sparse Autoencoders (SAEs) to extract interpretable features from vanilla CoT and steer the LLM's internal states during generation.

Copied to clipboard

Huacan Chai, Zijie Cao, Maolin Ran, Yingxuan Yang, Jianghao Lin, Xin Peng, Hairui Wang, Renjie Ding, Ziyu Wan, Muning Wen, Weiwen Liu, Weinan Zhang, Fei Huang, Ying Wen

Challenge:	Existing methods for multi-turn function calling are limited by redundancy and lack explicit integration of progress awareness into training.
Approach:	They propose a framework that explicitly integrates progress awareness into LLM training for multi-turn function calling.
Outcome:	Empirical results show that Progra outperforms existing methods on two public benchmarks.

ReCode: Robustness Evaluation of Code Generation Models (2023.acl-long)

Copied to clipboard

Shiqi Wang, Zheng Li, Haifeng Qian, Chenghao Yang, Zijian Wang, Mingyue Shang, Varun Kumar, Samson Tan, Baishakhi Ray, Parminder Bhatia, Ramesh Nallapati, Murali Krishna Ramanathan, Dan Roth, Bing Xiang

Regret-Now: A Physics-Inspired Regret Framework for Temporal Knowledge Graph Question Answering with LLMs (2026.findings-acl)

Challenge:	Existing work on robustness in text or code tasks has focused on classification, while robustness for code generation tasks is an uncharted area.
Approach:	They propose a robustness evaluation benchmark for code generation models that customizes over 30 transformations specifically for code on docstrings, function and variable names, code syntax, and code format.
Outcome:	The proposed model performs better on human annotators and on SOTA models with human annnotators.

Copied to clipboard

Danyu Huang, Yao Zhang, Jun Wang, Zhenglu Yang

We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning? (2025.acl-long)

Challenge:	Large Language Models have impressive results in general reasoning tasks, but they still exhibit a lack of dynamic error-correction.
Approach:	They propose a temporal reasoning framework that uses the principle of minimum potential energy to model the reasoning process as a dynamic trajectory moving toward a more stable state.
Outcome:	The proposed framework shows consistent gains over strong baselines on two standard TKGQA benchmarks.

Copied to clipboard

Runqi Qiao, Qiuna Tan, Guanting Dong, MinhuiWu MinhuiWu, Chong Sun, Xiaoshuai Song, Jiapeng Wang, Zhuoma GongQue, Shanglin Lei, YiFan Zhang, Zhe Wei, Miaoxuan Zhang, Runfeng Qiao, Xiao Zong, Yida Xu, Peiqing Yang, Zhimin Bao, Muxi Diao, Chen Li, Honggang Zhang

L2Dir: Integrating L_2-Norm and Directional Alignment for Unsupervised Contrastive Representation Learning in Multimodal Retrieval (2026.acl-long)

Challenge:	Existing benchmarks focus more on end-to-end performance, but neglect the underlying principles of knowledge acquisition and generalization.
Approach:	They propose a benchmark specifically designed to explore the problem-solving principles by decomposing 6.5K visual math problems into 10.9K step-level questions for evaluation.
Outcome:	The proposed benchmark covers 6.5K visual math problems and 10.9K step-level questions spanning 5 layers of knowledge granularity and 67 hierarchical knowledge concepts.

Copied to clipboard

Tianyu Zong, Rui Dai, Hongzhu Yi, Yuanxiang Wang, Zhenghao Zhang, Zhenyu Guan, Yujia Yang, Bingkang Shi, Yueyang Ding, Xiangxiang Chu, Kaikui Liu, Jungang Xu

Knowledge Graph Alignment with Entity-Pair Embedding (2020.emnlp-main)

Challenge:	Existing approaches to multimodal representation learning focus on directional alignment and embedding magnitudes (L2-norm) however, these methods often fail to account for the intrinsic role of L2-norm in the contrastive process.
Approach:	They propose a plug-and-play framework that optimizes L2-norm alignment and Directional consistency jointly.
Outcome:	The proposed framework achieves consistent and significant performance gains over established baselines across 95 tasks using UniIR and VLM2Vec-V2 frameworks.

Copied to clipboard

Zhichun Wang, Jinjian Yang, Xiaoju Ye

Enhancing Reinforcement Learning for Radiology Report Generation with Evidence-aware Rewards and Self-correcting Preference Learning (2026.acl-long)

Challenge:	Existing methods for Knowledge Graph (KG) alignment are not satisfactory.
Approach:	They propose a method that directly learns embeddings of entity-pairs for KG alignment.
Outcome:	The proposed approach can achieve state-of-the-art on five real-world datasets.

Copied to clipboard

Qin Zhou, Guoyan Liang, Qianyi Yang, Jingyuan Chen, Sai Wu, Chang Yao, Zhe Wang

RoleCDE: Benchmarking and Mitigating Role–Alignment Trade-offs in Role-Playing Agents (2026.findings-acl)

Challenge:	Recent reinforcement learning approaches have advanced radiology report generation (RRG) however, there are two limitations: report-level rewards offer limited evidence-grounded guidance for clinical faithfulness .
Approach:	They propose a method that uses group-wise evidence-aware alignment rewards and self-correcting preference learning to build a reliable, disease-agnostic preference dataset without human supervision.
Outcome:	ESC-RL promotes clinically faithful, disease-aligned reward and supports continual self-improvement during training.

Copied to clipboard

Huayi Lai, Shichao Song, Simin Niu, Hanyu Wang, Jiawei Yang, Zhouxing Wang, Zhiqiang Yin, Xun Liang

UniVocal: Unified Speech-Singing Code-Switching Synthesis (2026.acl-long)

Challenge:	Existing benchmarks for role-playing agents only evaluate surface-level fidelity and provide limited insight into decision making under role–alignment value conflicts.
Approach:	They propose a benchmark to evaluate RPAs under role–alignment value conflicts . they use 8k diverse role profiles and 240k dilemma instances to evaluate role-aware decision making .
Outcome:	The proposed benchmark covers 8k diverse role profiles and scenarios and nearly 240k dilemma instances across three difficulty levels and eight role categories.

Copied to clipboard

YuFei Shi, Qian Chen, Wen Wang, Xiangang Li, Zhen-Hua Ling, Yang Ai

Speech & Audio in NLP

Challenge:	Existing systems cannot automatically determine when to switch between modes based on text content.
Approach:	They propose a unified framework that implicitly infers vocal modes from text context to pioneer SCS Synthesis.
Outcome:	The proposed framework infers vocal modes solely from text context to pioneer SCS Synthesis.

ASPO: Adaptive Sentence-Level Preference Optimization for Fine-Grained Multimodal Reasoning (2025.findings-acl)

Copied to clipboard

Yeyuan Wang, Dehong Gao, Rujiao Long, Lei Yi, Linbo Jin, Libin Yang, Xiaoyan Cai

Reinforcement Tuning for Detecting Stances and Debunking Rumors Jointly with Large Language Models (2024.findings-acl)

Challenge:	Recent advances have extended DPO to multimodal scenarios, achieving strong performance.
Approach:	They propose to use a sentence-level preference optimization technique to optimize individual sentences for more precise preference optimization without additional models or parameters.
Outcome:	Experiments show that Adaptive Sentence-level Preference Optimization significantly improves the alignment of multimodal models.

Copied to clipboard

Ruichao Yang, Wei Gao, Jing Ma, Hongzhan Lin, Bo Wang

Want To Reduce Labeling Cost? GPT-3 Can Help (2021.findings-emnlp)

Challenge:	Social media has become a fertile ground for nurturing rumors and misinformation due to its lack of systematic moderation.
Approach:	They propose a framework to enhance the joint predictive capabilities of LLMs for stance detection and rumor verification tasks.
Outcome:	The proposed framework outperforms state-of-the-art methods and generalizes to non-LLMs accommodated as task models.

Copied to clipboard

Shuohang Wang, Yang Liu, Yichong Xu, Chenguang Zhu, Michael Zeng

HSDreport: Heart Sound Diagnosis with Echocardiography Reports (2024.findings-emnlp)

Challenge:	Data annotation is labor-intensive and time-consuming for many NLP tasks.
Approach:	They propose to use GPT-3 to train models which are deployed for inference . they propose to combine pseudo labels from GPT3 with human labels .
Outcome:	The proposed method can be generalizable to many practical applications.

Copied to clipboard

Zihan Zhao, Pingjie Wang, Liudan Zhao, Yuchen Yang, Ya Zhang, Kun Sun, Xin Sun, Xin Zhou, Yu Wang, Yanfeng Wang

Challenge:	Existing methods for heart sound diagnosis are limited to a few fixed categories and do not utilize echocardiography reports, the gold standard in the diagnosis of related diseases.
Approach:	They propose a benchmark that mandates the direct utilization of heart sounds obtained from auscultation to predict echocardiography reports.
Outcome:	The proposed method outperforms existing methods and existing multimodal LLMs in detecting key abnormalities in heart sounds.

Improving In-Context Learning with Prediction Feedback for Sentiment Analysis (2024.findings-acl)

Copied to clipboard

Hongling Xu, Qianlong Wang, Yice Zhang, Min Yang, Xi Zeng, Bing Qin, Ruifeng Xu

Exploiting Global and Local Hierarchies for Hierarchical Text Classification (2022.emnlp-main)

Challenge:	Large language models (LLMs) have achieved promising results in sentiment analysis through the in-context learning paradigm.
Approach:	They propose a framework that incorporates prior predictions and feedback to improve sentiment understanding by incorporating prior feedback and leveraging a feedback-driven prompt.
Outcome:	The proposed framework improves on nine sentiment analysis datasets with an average improvement of 5.95% over conventional methods.

Copied to clipboard

Ting Jiang, Deqing Wang, Leilei Sun, Zhongzhi Chen, Fuzhen Zhuang, Qinghong Yang

ParaTag: A Dataset of Paraphrase Tagging for Fine-Grained Labels, NLG Evaluation, and Data Augmentation (2022.emnlp-main)

Challenge:	Existing methods encode label hierarchy in a global view, which makes them hard to exploit hierarchical information.
Approach:	They propose to leverage label hierarchy in multi-label text classification by encoding label hierarchy as a static hierarchical structure containing all labels.
Outcome:	The proposed method achieves significant improvement on three benchmark datasets compared with the state-of-the-art method HGCLR.

Copied to clipboard

Shuohang Wang, Ruochen Xu, Yang Liu, Chenguang Zhu, Michael Zeng

Thread: A Logic-Based Data Organization Paradigm for How-To Question Answering with Retrieval Augmented Generation (2025.emnlp-main)

Challenge:	Existing datasets only annotate a binary label for each sentence pair. Existing models only annnotate binary labels for each phrase pair.
Approach:	They propose a novel binary paraphrase classification task that annotates the degree of paraphrase between sentences and a new annotation schema that labels the minimum spans of tokens in a sentence that don't have the corresponding paraphrases in the other sentence.
Outcome:	The proposed dataset can be used to train an automatic scorer for language generation evaluation.

Copied to clipboard

Kaikai An, Fangkai Yang, Liqun Li, Junting Lu, Sitao Cheng, Shuzheng Si, Lu Wang, Pu Zhao, Lele Cao, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang, Baobao Chang

Muse: Towards Reproducible Long-Form Song Generation with Fine-Grained Style Control (2026.findings-acl)

Challenge:	Recent advances in retrieval-augmented generation (RAG) have substantially improved question-answering systems, particularly for factoid ‘5Ws’ questions.
Approach:	They propose a data organization paradigm where large language models transform documents into more structured and loosely interconnected LUs.
Outcome:	Experiments in open-domain and industrial settings show that the proposed paradigm outperforms existing paradigms and shows high adaptability across diverse document formats.

Copied to clipboard

Changhao Jiang, Jiahao Chen, Zhenghao Xiang, Zhixiong Yang, Hanchen Wang, Jiabao Zhuang, Xinmeng Che, Jiajun Sun, Hui Li, Yifei Cao, Shihan Dou, Ming Zhang, Junjie Ye, Tao Ji, Tao Gui, Qi Zhang, Xuanjing Huang

Speech & Audio in NLP

Challenge:	Recent commercial systems such as Suno demonstrate strong capabilities in long-form song generation, but academic research remains non-reproducible due to the lack of publicly available training data.
Approach:	They propose a system for long-form song generation with fine-grained style conditioning that includes a licensed synthetic dataset and a song generation model, Muse.
Outcome:	The proposed system achieves competitive performance on phoneme error rate, text–music style similarity, and audio aesthetic quality while enabling controllable segment-level generation across different musical structures.

GLoCIM: Global-view Long Chain Interest Modeling for news recommendation (2025.coling-main)

Copied to clipboard

Zhen Yang, Wenhui Wang, Tao Qi, Peng Zhang, TianYun Zhang, Ru Zhang, Jianyi Liu, Yongfeng Huang

K-order Ranking Preference Optimization for Large Language Models (2025.findings-acl)

Challenge:	Recent efforts to extract local subgraph information from click graphs have hindered collaboratively utilizing global click graph information.
Approach:	They propose a global-view long chain interests model that models a click graph with neighbor interest to enhance news recommendation.
Outcome:	The proposed method surpasses baseline methods on two real-world datasets.

Copied to clipboard

Shihao Cai, Chongming Gao, Yang Zhang, Wentao Shi, Jizhi Zhang, Keqin Bao, Qifan Wang, Fuli Feng

PEARL: Prompting Large Language Models to Plan and Execute Actions Over Long Documents (2024.eacl-long)

Challenge:	Existing list-wise methods focus on optimizing list ranking consistency for LLMs to improve ranking abilities.
Approach:	They propose to extend the Plackett-Luce model to accommodate top-K ranking by extending the DPO’s Plact-Lucer model to dynamically determine appropriate K for different samples.
Outcome:	The proposed model can be extended to accommodate top-K ranking and improve training efficiency.

Copied to clipboard

Simeng Sun, Yang Liu, Shuohang Wang, Dan Iter, Chenguang Zhu, Mohit Iyyer

Assessing Multilingual Fairness in Pre-trained Multimodal Representations (2022.findings-acl)

Challenge:	Using chain-of-thought prompting, large language models perform better on complex reasoning tasks.
Approach:	They propose a prompting framework that decomposes a question into a sequence of actions and executes them over the document to obtain the answer.
Outcome:	The proposed framework outperforms zero-shot and chain-of-thought prompting on a QuALITY dataset . it proposes a plan based on actions mined from a training set and executes it step by step .

Copied to clipboard

Jialu Wang, Yang Liu, Xin Wang

Unsupervised Neural Machine Translation with Weight Sharing (P18-1)

Challenge:	Recent pre-trained multimodal models have shown exceptional capabilities towards connecting images and natural language.
Approach:	They propose two new fairness notions for pre-trained multimodal models that consider language as the fairness recipient.
Outcome:	The proposed models can be generalized to multilingualism by cross-lingual alignment . the results show that the models are individually fair across languages .

Copied to clipboard

Zhen Yang, Wei Chen, Feng Wang, Bo Xu

OpenForecast: A Large-Scale Open-Ended Event Forecasting Dataset (2025.coling-main)

Challenge:	Unsupervised neural machine translation (NMT) is a new approach for machine translation . the model uses only one shared encoder to map pairs of sentences from different languages to a shared-latent space .
Approach:	They propose an unsupervised approach which trains the model without labeling data . they propose two independent encoders but share some partial weights to extract high-level representations of input sentences.
Outcome:	The proposed approach achieves significant improvements on English-German, English-French and Chinese-to-English translation tasks.

Copied to clipboard

Zhen Wang, Xi Zhou, Yating Yang, Bo Ma, Lei Wang, Rui Dong, Azmat Anwar

Challenge:	Existing closed-ended event forecasting methods are constrained by a limited answer space.
Approach:	They introduce OpenForecast, a large-scale open-ended dataset with three open-ending event forecasting tasks and an automatic LLM-based method for complex events.
Outcome:	The proposed method can be used to evaluate the ability of complex event forecasting of large language models.

Knowledge-Infused Legal Wisdom: Navigating LLM Consultation through the Lens of Diagnostics and Positive-Unlabeled Reinforcement Learning (2024.findings-acl)

Copied to clipboard

Yang Wu, Chenghao Wang, Ece Gumusel, Xiaozhong Liu

A Dialogue-based Information Extraction System for Medical Insurance Assessment (2021.findings-acl)

Challenge:	Recent years have witnessed a substantial increase in the demand for legal services, especially for individuals with modest means.
Approach:	They propose a diagnostic legal large language model which uses adaptive lawyer-like diagnostic questions to collect additional case information and then provides high-quality feedback.
Outcome:	The proposed model surpasses classical LLMs by providing outstanding performance and a remarkable user experience in the legal domain.

Copied to clipboard

Shuang Peng, Mengdi Zhou, Minghui Yang, Haitao Mi, Shaosheng Cao, Zujie Wen, Teng Xu, Hongbin Wang, Lei Liu

Beyond the Final Actor: Modeling the Dual Roles of Creator and Editor for Fine-Grained LLM-Generated Text Detection (2026.acl-long)

Challenge:	a new system that integrates advanced NLP technologies for medical insurance assessment is proposed . the average time cost of the procedure is reduced from 55 minutes to 35 minutes .
Approach:	They propose a dialogue-based information extraction system that integrates advanced NLP technologies for medical insurance assessment.
Outcome:	The proposed system reduces the time cost of the procedure from 55 minutes to 35 minutes and saves 30% human resources cost compared with the previous offline procedure.

Copied to clipboard

Yang Li, Qiang Sheng, Zhengjia Wang, Yehan Yang, Danding Wang, Juan Cao

CART: A Generative Cross-Modal Retrieval Framework With Coarse-To-Fine Semantic Modeling (2025.acl-long)

Challenge:	Existing methods to detect large language models (LLMs) use binary or ternary classifications, which can only distinguish pure human/LLM text or collaborative text at best.
Approach:	They propose a fine-grained method that characterizes distinct signatures of creator and editor by using Rhetorical Structure Theory to construct a logic graph for creator's foundation and extracting Elementary Discourse Unit (EDU)-level features for the editor's style.
Outcome:	The proposed method outperforms 12 baselines in identifying fine-grained types with low false alarms, offering a policy-aligned solution for LLM regulation.

Copied to clipboard

Minghui Fang, Shengpeng Ji, Jialong Zuo, Hai Huang, Yan Xia, Jieming Zhu, Xize Cheng, Xiaoda Yang, Wenrui Liu, Gang Wang, Zhenhua Dong, Zhou Zhao

SMARTAVE: Structured Multimodal Transformer for Product Attribute Value Extraction (2022.findings-emnlp)

Challenge:	Cross-modal retrieval tasks are used to retrieve data from one modality or another based on a query from another modality.
Approach:	They propose a generative cross-modal retrieval framework based on coarse-to-fine semantic modeling . they propose combining K-Means and RQ-VAE to discretize multimodal data into token sequences that support autoregressive generation.
Outcome:	The proposed framework achieves excellent performance and efficiency in multimodal retrieval tasks.

Copied to clipboard

Qifan Wang, Li Yang, Jingang Wang, Jitin Krishnan, Bo Dai, Sinong Wang, Zenglin Xu, Madian Khabsa, Hao Ma

A Mousetrap: Fooling Large Reasoning Models for Jailbreak with Chain of Iterative Chaos (2025.findings-acl)

Challenge:	Existing methods for product attribute value extraction are noisy and incomplete with missing values for most retailers.
Approach:	They propose a Structure Mltimodal trAnsformeR for producT Attribute Value Extraction which jointly encodes the structured product information from multiple modalities.
Outcome:	The proposed method outperforms state-of-the-art methods on two multimodal product datasets.

Copied to clipboard

Yang Yao, Xuan Tong, Ruofan Wang, Yixu Wang, Lujundong Li, Liang Liu, Yan Teng, Yingchun Wang

Reinforcement Learning for Diffusion LLMs via Energy-Based Gibbs Alignment (2026.acl-long)

Challenge:	Large Reasoning Models (LRMs) have advanced beyond traditional Large Language Models, yet they pose heightened safety risks.
Approach:	They propose a first jailbreak attack targeting Large Reasoning Models . they exploit a Chaos Machine component to transform attack prompts with diverse one-to-one mappings based on the reasoning chain .
Outcome:	The proposed attack exploits the unique vulnerabilities of LRMs by integrating a Chaos Machine. success rates of the mousetrap attack are as high as 96%, 86% and 98% respectively.

Copied to clipboard

Yijia Fan, Jing Yang, Mingyu Liu, Kaitong Cai, Jian Wang, Keze Wang, Jusheng Zhang

VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Models (2024.emnlp-main)

Challenge:	Diffusion Large Language Models (dLLMs) offer parallel decoding and bidirectional context modeling . aligning dLLms with reinforcement learning (RL) remains a challenge .
Approach:	They propose a variational framework that reformulates RL for dLLMs as a distribution matching problem.
Outcome:	The proposed framework reformulates RL for dLLMs as a distribution matching problem.

Copied to clipboard

Yifei Liu, Jicheng Wen, Yang Wang, Shengyu Ye, Li Lyna Zhang, Ting Cao, Cheng Li, Mao Yang

DentalGPT: Incentivizing Multimodal Reasoning in Dentistry (2026.findings-acl)

Challenge:	Recent research has focused on pushing weight-only quantization to extremely low-bit due to numerical representation limitations.
Approach:	They propose a vector-based quantization approach that pushes LLMs to extremely low-bit . they propose scalar-based weight quantization that reduces memory requirements and optimizes storage costs .
Outcome:	The proposed method reduces model quantization perplexity by 0.01-0.34 on LLaMA-2, 0.38-0.68 on mistral-7B, 4.41-7.34, on llaMA-3 on QA tasks on average.

Copied to clipboard

Zhenyang Cai, Jiaming Zhang, Junjie Zhao, Ziyi Zeng, Yanchao Li, Liang Jingyi, Junying Chen, Yunjin Yang, Jiajun You, Shuzhi Deng, null Xieruiqiii, Yuanting Chen, Xiangyi Feng, Jianquan Li, Liangyi Chen, Junwen Wang, Shan Jiang, Benyou Wang

TreeBoN: Enhancing Inference-Time Alignment with Speculative Tree-Search and Best-of-N Sampling (2025.findings-emnlp)

Challenge:	Current multimodal large language models (MLLMs) show limited understanding of dental images.
Approach:	They propose a dental-specialized multimodal large language model trained via staged multimodal alignment and reinforcement learning.
Outcome:	The proposed model outperforms state-of-the-art models on disease classification and dental VQA tasks.

Copied to clipboard

Jiahao Qiu, Yifu Lu, Yifan Zeng, Jiacheng Guo, Jiayi Geng, Chenhao Zhu, Xinzhe Juan, Ling Yang, Huazheng Wang, Kaixuan Huang, Yue Wu, Mengdi Wang

Model Composition for Multimodal Large Language Models (2024.acl-long)

Challenge:	Best-of-N (BoN) sampling generates multiple responses and selects the best one, achieving improved performance but with a high computational cost.
Approach:	They propose a framework that integrates a speculative tree-search strategy into Best-of-N (BoN) Sampling.
Outcome:	The proposed framework outperforms Best-of-N (BoN) sampling but has high computational cost . tree-search strategy reduces computational overhead while maintaining high output quality .

Copied to clipboard

Chi Chen, Yiyang Du, Zheng Fang, Ziyue Wang, Fuwen Luo, Peng Li, Ming Yan, Ji Zhang, Fei Huang, Maosong Sun, Yang Liu

Gradient-based Intra-attention Pruning on Pre-trained Language Models (2023.acl-long)

Challenge:	Existing methods for creating versatile MLLMs rely on joint training with paired instruction data, which is resource-intensive and challenging to extend to new modalities.
Approach:	They propose a new paradigm for multimodal large language models by reusing modality encoders and merging LLM parameters.
Outcome:	The proposed model retains the modal understanding capabilities of each original model.

Copied to clipboard

Ziqing Yang, Yiming Cui, Xin Yao, Shijin Wang

Human-Inspired Obfuscation for Model Unlearning: Local and Global Strategies with Hyperbolic Representations (2025.findings-emnlp)

Challenge:	Pre-trained language models are computationally expensive and slow in inference due to their large sizes.
Approach:	They propose a structured pruning method which combines pruning with knowledge distillation to yield highly effective models.
Outcome:	The proposed method outperforms other pruning methods in sparsity regimes while maintaining 93% 99% performance.

Copied to clipboard

Zekun Wang, Jingjie Zeng, Yingxu Li, Liang Yang, Hongfei Lin

LightSeq: A High Performance Inference Library for Transformers (2021.naacl-industry)

Challenge:	Existing methods for unlearning large language models struggle to balance effective forgetting with maintaining model utility.
Approach:	They propose a human-inspired unlearning framework that simulates forgetting on fuzzy data and represents them in hyperbolic and Euclidean spaces.
Outcome:	The proposed framework is able to forget sensitive content while maintaining the model’s language understanding, fluency, and benchmark performance.

Copied to clipboard

Xiaohui Wang, Ying Xiong, Yang Wei, Mingxuan Wang, Lei Li

HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference (2025.findings-acl)

Challenge:	Existing inference frameworks for natural language processing are not the best choice for online service of sequence processing problems.
Approach:	They propose a highly efficient inference library for Transformer models that includes GPU optimization techniques to streamline computation and reduce memory footprint.
Outcome:	The proposed library achieves 14x speedup compared with TensorFlow and 1.4x speed up compared to a concurrent CUDA implementation.

Copied to clipboard

Ping Gong, Jiawei Yi, Shengnan Wang, Juncheng Zhang, Zewen Jin, Ouxiang Zhou, Ruibo Liu, Guanbin Xu, Youhui Bai, Bowen Ye, Kun Yuan, Tong Yang, Gong Zhang, Renhai Chen, Feng Wu, Cheng Li

Two Pathways to Truthfulness: On the Intrinsic Encoding of LLM Hallucinations (2026.acl-long)

Challenge:	Existing top-k attention methods struggle to strike a balance between efficiency and accuracy.
Approach:	They propose a top-k attention approach that integrates low-overhead techniques into the Top-k Attention process to achieve 7.2 speedup compared to vanilla full attention.
Outcome:	The proposed approach achieves 7.2 speedup compared to current top-k attention methods while maintaining model accuracy.

Copied to clipboard

Wen Luo, Guangyue Peng, Wei Li, Shaohang Wei, Feifan Song, Liang Wang, Nan Yang, Xingxing Zhang, Jing Jin, Furu Wei, Houfeng Wang

Do Large Language Models excel in Complex Logical Reasoning with Formal Language? (2025.emnlp-main)

Challenge:	Previous work shows that large language models generate hallucinations, yet the origins and mechanisms of these signals remain unclear.
Approach:	They propose to validate and disentangle two different pathways for truthfulness cues . they also propose to use the same mechanism to derive self-contained evidence from the generated answer .
Outcome:	The proposed applications improve hallucination detection performance by integrating two different inputs.

Copied to clipboard

Jin Jiang, Jianing Wang, Yuchen Yan, Yang Liu, Jianhua Zhu, Mengdi Zhang, Liangcai Gao

Mixture-of-Supernets: Improving Weight-Sharing Supernet Training with Architecture-Routed Mixture-of-Experts (2024.findings-acl)

Challenge:	Existing studies on LLMs have focused on formal language, but evaluations of their performance are limited.
Approach:	They propose to use a formal language to evaluate LLMs across logical reasoning problems using formal languages.
Outcome:	The proposed model outperforms Instruct models in three dimensions, taxonomy of tasks, and format of trajectories, and achieves the best generalization performance across other languages.

Copied to clipboard

Ganesh Jawahar, Haichuan Yang, Yunyang Xiong, Zechun Liu, Dilin Wang, Fei Sun, Meng Li, Aasish Pappu, Barlas Oguz, Muhammad Abdul-Mageed, Laks Lakshmanan, Raghuraman Krishnamoorthi, Vikas Chandra

Innovative Image Fraud Detection with Cross-Sample Anomaly Analysis: The Power of LLMs (2025.acl-long)

Challenge:	Neural architecture search (NAS) uses weight-sharing supernets to generate diverse subnetworks without retraining.
Approach:	They propose a weight-sharing supernet that leverages mixture-of-experts to enhance supernet model expressiveness with minimal training overhead.
Outcome:	The proposed method achieves state-of-the-art (SoTA) performance in NAS for fast machine translation models, surpassing NAS-BERT and AutoDistil across various model sizes.

Copied to clipboard

QiWen Wang, Junqi Yang, Zhenghao Lin, Zhenzhe Ying, Weiqiang Wang, Chen Lin

USB: A COMPREHENSIVE AND UNIFIED SAFETY EVALUATION BENCHMARK FOR MULTIMODAL LARGE LANGUAGE MODELS (2026.acl-long)

Challenge:	Existing methods for document image fraud detection lack visual clues on tampered regions.
Approach:	They propose a framework for detecting logical inconsistencies in document images by leveraging LLMs.
Outcome:	The proposed framework outperforms state-of-the-art fraud detection methods by 79.6% on CrossCred and industrial solutions by 21.7% on business data.

Copied to clipboard

Baolin Zheng, Guanlin Chen, Qingyang Teng, Hongqiong Zhong, Yingshui Tan, Zhendong Liu, Weixun Wang, Jiaheng Liu, Jian Yang, Huiyun Jing, Jincheng Wei, Wenbo Su, Xiaoyong Zhu, Bo Zheng, Kaifu Zhang

Gaussian Process based Deep Dyna-Q approach for Dialogue Policy Learning (2021.findings-acl)

Challenge:	Existing safety benchmarks fail to provide reliable assessments due to limited risk coverage, insufficient scale and the oversight of complex modality combinations.
Approach:	They propose a framework that covers 61 risk categories across four modality interactions to address this gap.
Outcome:	The proposed framework covers 61 risk categories across four distinct modality interactions.

Copied to clipboard

Guanlin Wu, Wenqi Fang, Ji Wang, Jiang Cao, Weidong Bao, Yang Ping, Xiaomin Zhu, Zheng Wang

Lookahead Q-Cache: Achieving More Consistent KV Cache Eviction via Pseudo Query (2025.emnlp-main)

Challenge:	Reinforcement learning (RL) is the main dialogue policy learning method in recent years.
Approach:	They propose a Gaussian Process based Deep Dyna-Q approach to dialogue policy learning . they propose evaluating the quality of experiences generated by the world model using a discriminator .
Outcome:	The proposed approach improves the effectiveness and efficiency of dialogue policy learning by 20% with fewer human-machine interactions.

Copied to clipboard

Yixuan Wang, Shiyu Ji, Yijun Liu, Yuzhuang Xu, Yang Xu, Qingfu Zhu, Wanxiang Che

Challenge:	Existing KV cache eviction methods prune tokens using prefilling-stage attention scores, causing inconsistency with actual inference queries.
Approach:	They propose a lookahead q-cache framework that generates low-cost pseudo lookaheaded queries to better approximate the true decoding-stage queries.
Outcome:	The proposed framework outperforms existing methods on LongBench and Needle-in-a-Haystack benchmarks and can be flexibly combined to yield further improvements.

Self-Supervised Learning for Pairwise Data Refinement (2020.aacl-main)

Copied to clipboard

Gustavo Hernandez Abrego, Bowen Liang, Wei Wang, Zarana Parekh, Yinfei Yang, Yunhsuan Sung

Reinforced Efficient Reasoning via Semantically Diverse Exploration (2026.acl-long)

Challenge:	Pairwise data constructed from weakly supervised signals is widely used for training deep learning models.
Approach:	They propose two methods to refine pairwise data that are aimed to obtain subsets that are more useful as learning examples.
Outcome:	The proposed methods achieve most machine translation gains in the first iteration, but following iterations further improve its intrinsic evaluation.

Copied to clipboard

Ziqi Zhao, Zhaochun Ren, Jiahong Zou, Liu Yang, Zhiwei Xu, Xuri Ge, Zhumin Chen, Xinyu Ma, Daiting Shi, Shuaiqiang Wang, Dawei Yin, Xin Xin

Mid-Think: Training-Free Intermediate-Budget Reasoning via Token-Level Triggers (2026.findings-acl)

Challenge:	Existing methods for reinforcement learning with verifiable rewards suffer from limited exploration diversity and inefficient reasoning.
Approach:	They propose a method that rewards concise and correct reasoning while penalizing unnecessarily long reasoning chains.
Outcome:	Extensive experiments on Qwen and Llama models validate the effectiveness and efficiency of ROSE.

Copied to clipboard

Van Yang, Shouren Wang, Debargha Ganguly, Xinpeng Li, Chaoda Song, Vikash Singh, Vipin Chaudhary, Xiaotian Han

WhitenedCSE: Whitening-based Contrastive Learning of Sentence Embeddings (2023.acl-long)

Challenge:	Explicit /think> tags are used to expose intermediate reasoning and enable hybrid thinking behaviors.
Approach:	They propose a training-free prompting format that combines these triggers to achieve intermediate-budget reasoning, outperforming fixed-token and prompt-based baselines in terms of the accuracy–length trade-off.
Outcome:	The proposed method outperforms fixed-token and prompt-based prompts in accuracy–length trade-offs while improving Qwen3-8B on AIME from 69.8% to 72.4% and on GPQA from 58.5% to 61.1%.

Copied to clipboard

Wenjie Zhuo, Yifan Sun, Xiaohan Wang, Linchao Zhu, Yi Yang

GIFT: Guided Fine-Tuning and Transfer for Enhancing Instruction-Tuned Language Models (2026.acl-long)

Challenge:	Extensive experiments on seven semantic textual similarity tasks show our method achieves consistent improvement over the contrastive learning baseline and sets new states of the art.
Approach:	They propose a whitening-based contrastive learning method for sentence embedding learning which combines contrastive and shuffled group whitening.
Outcome:	The proposed method achieves better alignment and uniformity on seven semantic textual similarity tasks.

Copied to clipboard

Zhiwen Ruan, Yichao Du, Jianjie Zheng, Longyue Wang, Yun Chen, Peng Li, Jinsong Su, Yang Liu, Guanhua Chen

CTSM: Combining Trait and State Emotions for Empathetic Response Model (2024.lrec-main)

Challenge:	Existing adapter-based transfer methods treat instruction-tuned models as passive targets . direct fine-tuning can disrupt this delicate balance and lead to instability or performance degradation.
Approach:	They propose a framework that incorporates instruction-level guidance into task adaptation.
Outcome:	The proposed framework outperforms direct fine-tuning and representative transfer-based baselines while maintaining robust generalization and favorable test-time scaling behavior.

Copied to clipboard

Yufeng Wang, Chao Chen, Zhou Yang, Shuhui Wang, Xiangwen Liao

TellWhisper: Tell Whisper Who Speaks When (2026.acl-long)

Challenge:	Empathetic response generation attempts to empower dialogue systems to perceive speakers’ emotions and generate empathetic responses accordingly.
Approach:	They propose to combine trait and state emotions for Empathetic Response Model to enable dialogue systems to perceive speakers' emotions and generate empathetic responses accordingly.
Outcome:	The proposed model outperforms state-of-the-art models and generates more empathetic responses.

Copied to clipboard

Yifan Hu, Peiji Yang, Zhisheng Wang, Yicheng Zhong, Rui Liu

LadaBERT: Lightweight Adaptation of BERT through Hybrid Model Compression (2020.coling-main)

Challenge:	Existing approaches decouple temporal modeling and speaker modeling when addressing 'when' and 'who' . a new framework that couples temporal structure with speaker dynamics is proposed to address these limitations .
Approach:	They propose a framework that couples temporal and speaker identity within the speech encoder . they propose TS-RoPE, a time-speaker rotary positional encoding that partitions Query/Key channels into temporal, speaker subspaces and applies region-specific rotations to align "when" and "who" cues in selfattention.
Outcome:	The proposed framework couples temporal structure with speaker dynamics in speech encoder . it uses frame-level speaker activity to estimate speaker-activity estimates .

Copied to clipboard

Yihuan Mao, Yujing Wang, Chufan Wu, Chen Zhang, Yang Wang, Quanlu Zhang, Yaming Yang, Yunhai Tong, Jing Bai

Exploring the Impact of Personality Traits on LLM Toxicity and Bias (2025.emnlp-main)

Challenge:	Existing models that use knowledge distillation are memory-intensive and latency-prohibitive . Existing solutions that use this knowledge distilling framework are expensive .
Approach:	They propose a solution that uses weight pruning, matrix factorization and knowledge distillation to learn a smaller model.
Outcome:	The proposed model reduces the training overheads by an order of magnitude on public datasets while preserving state-of-the-art accuracy.

Copied to clipboard

Shuo Wang, Renhao Li, Xi Chen, Yulin Yuan, Min Yang, Derek F. Wong

Mitigating the Inconsistency Between Word Saliency and Model Confidence with Pathological Contrastive Training (2022.findings-acl)

Challenge:	anthropomorphic LLMs are being developed to serve diversified roles, but content safety concerns remain regarding their toxicity and toxicity.
Approach:	They propose to assign personality traits to large language models (LLMs) to reduce toxic language and social biases in their outputs by using the widely accepted HEXACO personality framework developed in social psychology.
Outcome:	The proposed model is able to perform on three toxic and bias benchmarks and shows that assigning personality traits reduces bias and toxicity similar to humans’ correlations between personality traits and toxic behaviors.

Copied to clipboard

Pengwei Zhan, Yang Wu, Shaolei Zhou, Yunjian Zhang, Liming Wang

N24News: A New Dataset for Multimodal News Classification (2022.lrec-1)

Challenge:	Neural networks are used for various NLP tasks, but their complexity makes them difficult to interpret.
Approach:	They propose a framework to mitigate the model pathology and obtain more interpretable models by using contrastive learning and saliency-based samples augmentation to calibrate the sentences representation.
Outcome:	The proposed framework can mitigate the model pathology and generate more interpretable models while keeping the model performance.

Copied to clipboard

Zhen Wang, Xu Shan, Xiangxie Zhang, Jie Yang

Enhancing Self-Attention with Knowledge-Assisted Attention Maps (2022.naacl-main)

Challenge:	Current news datasets focus on text features and rarely leverage the feature of images.
Approach:	They propose a news dataset that uses both images and text to achieve better news classification.
Outcome:	The proposed model improves on the existing dataset N24News with text and image information.

Copied to clipboard

Jiangang Bai, Yujing Wang, Hong Sun, Ruonan Wu, Tianmeng Yang, Pengfei Tang, Defu Cao, Mingliang Zhang1, Yunhai Tong, Yaming Yang, Jing Bai, Ruofei Zhang, Hao Sun, Wei Shen

PrivacyRestore: Privacy-Preserving Inference in Large Language Models via Privacy Removal and Restoration (2025.acl-long)

Challenge:	Existing works of knowledge infusion depend on multi-task learning frameworks, which are inefficient and require large-scale retraining when new knowledge is considered.
Approach:	They propose a method which integrates knowledge-generated attention maps into the self-attention mechanism and integrates it into the model.
Outcome:	The proposed model outperforms existing methods on academic datasets and industry-scale ad relevance applications.

Copied to clipboard

Ziqian Zeng, Jianwei Wang, Junyao Yang, Zhengdong Lu, Haoran Li, Huiping Zhuang, Cen Chen

Dual Hierarchical Dialogue Policy Learning for Legal Inquisitive Conversational Agents (2026.findings-acl)

Challenge:	Existing privacy protection methods for large language models suffer from performance degradation or large inference time overhead.
Approach:	They propose a plug-and-play method to protect the privacy of user inputs during LLM inference . they use offline restoration vectors to train restoration vector for each privacy span type .
Outcome:	The proposed method can prevent the linear growth of the privacy budget.

Copied to clipboard

Xubo Lin, Zezhi Deng, Shihao Wang, Grace Hui Yang, Yang Deng

ChessArena: A Chess Testbed for Evaluating Strategic Reasoning Capabilities of Large Language Models (2026.acl-long)

Challenge:	Existing systems for conversational AI are user-driven, but in many real-world situations, they do not extract information to achieve its own objectives.
Approach:	They propose an inquisitive conversational agent that learns when and how to ask probing questions . they also propose a framework for a conversational ICA specifically tailored to the court .
Outcome:	The proposed method outperforms single-agent RL baselines on a U.S. Supreme Court dataset.

Copied to clipboard

Jincheng Liu, Sijun He, Jingjing Wu, Xiangsen Wang, Yang Chen, Zhaoqi Kuang, Siqi Bao, Yuan Yao

CamoQuery: Language-Guided Reasoning Camouflaged Object Segmentation (2026.acl-long)

Challenge:	Existing evaluation frameworks focus on isolated question-answering tasks that may not capture the essential aspects of strategic reasoning.
Approach:	They evaluate 13 large language models across over 800 games in chess . they use a chessian-based framework to test strategic reasoning and pattern recognition .
Outcome:	The proposed framework improves performance and basic understanding of large language models.

Copied to clipboard

Tianxin Han, Qing Dong, Xingwei Wang, Jie Jia, Gang Wu, Bowen Yang, Fu Zhang

Research Replication Prediction Using Weakly Supervised Learning (2020.findings-emnlp)

Challenge:	Existing methods for camouflaged object segmentation are limited to vision-only mask prediction under fixed task assumptions.
Approach:	They propose a language-guided reasoning camouflaged object segmentation task that generates an intent-consistent segmentation mask from an image and an implicit query text instruction.
Outcome:	The proposed task can generate an intent-consistent segmentation mask from a camouflaged image and an implicit query text instruction.

Copied to clipboard

Tianyi Luo, Xingyu Li, Hainan Wang, Yang Liu

ReviewRL: Towards Automated Scientific Review with RL (2025.emnlp-main)

Challenge:	Existing methods to predict scientific claims’ replicability use only hand-extracted statistics features without utilizing research papers’ text information.
Approach:	They propose two weakly supervised learning approaches that use automatically extracted text information of research papers to improve the prediction accuracy of research replication using both labeled and unlabeled datasets.
Outcome:	The proposed methods achieve an accuracy of 75.76% over real-world datasets.

Copied to clipboard

Sihang Zeng, Kai Tian, Kaiyan Zhang, Yuru Wang, Junqi Gao, Runze Liu, Sa Yang, Jingxuan Li, Xinwei Long, Jiaheng Ma, Biqing Qi, Bowen Zhou

Challenge:	Existing automated review systems struggle with factual accuracy, rating consistency, and analytical depth.
Approach:	They propose a framework for generating comprehensive and factually grounded scientific paper reviews using supervised fine-tuning and reinforcement learning.
Outcome:	The proposed framework outperforms existing methods on ICLR 2025 papers.

MedQA-CS: Objective Structured Clinical Examination (OSCE)-Style Benchmark for Evaluating LLM Clinical Skills (2026.eacl-long)

Copied to clipboard

Zonghai Yao, Zihao Zhang, Chaolong Tang, Xingyu Bian, Youxia Zhao, Zhichao Yang, Junda Wang, Huixue Zhou, Won Seok Jang, Feiyun Ouyang, Hong Yu

Challenge:	Current clinical LLM benchmarks fail to evaluate advanced clinical skills in AI and large language models (LLMs).
Approach:	They propose a framework to evaluate large language models (LLMs) using two instruction-following tasks designed to reflect real clinical scenarios.
Outcome:	The proposed framework evaluates LLMs through two instruction-following tasks designed to reflect real clinical scenarios.

Enabling Stroke-Level Structural Analysis of Hieroglyphic Scripts without Language-Specific Priors (2026.findings-acl)

Copied to clipboard

Fuwen Luo, Zihao Wan, Ziyue Wang, Yaluo Liu, Pau Tong Lin Xu, Xuanjia Qiao, Xiaolong Wang, Peng Li, Yang Liu

Challenge:	Existing structural analysis methods for hieroglyphic scripts are script-specific and labor-intensive.
Approach:	They propose a hieroglyphic Stroke Analyzer framework that captures character-internal structures and semantics without handcrafted data.
Outcome:	The proposed framework captures character-internal structures and semantics without priors . it can be used to generalize hieroglyphic scripts across languages .

Breaking Down Power Barriers in On-Device Streaming ASR: Insights and Solutions (2025.naacl-industry)

Copied to clipboard

Yang Li, Yuan Shangguan, Yuhao Wang, Liangzhen Lai, Ernie Chang, Changsheng Zhao, Yangyang Shi, Vikas Chandra

Comprehensive and Efficient Distillation for Lightweight Sentiment Analysis Models (2025.emnlp-main)

Challenge:	Streaming automatic speech recognition models use high power consumption to improve usability and accuracy.
Approach:	They propose to optimize on-device speech recognition models by adjusting component energy sensitivities based on their specific energy sensitities to reduce power consumption.
Outcome:	The proposed approach achieves up to 47% lower energy usage while preserving comparable model accuracy and improving real-time performance compared to leading methods.

Copied to clipboard

Guangyu Xie, Yice Zhang, Jianzhu Bao, Qianlong Wang, Yang Sun, Bingbing Wang, Ruifeng Xu

Prototype-Guided Pseudo Labeling for Semi-Supervised Text Classification (2023.acl-long)

Challenge:	Recent efforts to develop lightweight and practical sentiment analysis models are limited by manual instruction and large-scale user texts.
Approach:	They propose a framework for sentiment analysis that uses attribute-based instruction construction and difficulty-based data filtering to distill knowledge.
Outcome:	The proposed framework outperforms baseline methods in data efficiency and performance.

Copied to clipboard

Weiyi Yang, Richong Zhang, Junfan Chen, Lihong Wang, Jaein Kim

Resource-Limited Joint Multimodal Sentiment Reasoning and Classification via Chain-of-Thought Enhancement and Distillation (2026.findings-acl)

Challenge:	Existing semi-supervised text classification methods suffer from categorical boundary issues . existing methods suffer by ambiguous categoric boundaries, making it difficult to generate reliable pseudo-labels for each category.
Approach:	They propose a semi-supervised framework that assigns pseudo-labels to unlabeled data . they exploit categorical prototypes to assimilate instance representations within the same category .
Outcome:	Empirical studies show that the proposed framework is effective . it uses prototypical cluster separation and prototypical-center data selection .

Copied to clipboard

Haonan Shangguan, Xiaocui Yang, Shi Feng, Daling Wang, Yifei Zhang, Feiliang Ren, Ge Yu

MorphMark: Flexible Adaptive Watermarking for Large Language Models (2025.acl-long)

Challenge:	Current approaches for Multimodal Sentiment Analysis (MSA) rely on parameter-heavy LLMs for classification, overlooking multimodal sentiment reasoning generation in resource-limited environments.
Approach:	They propose a multimodal sentiment reasoning distillation model that employs a teacher-assistant-student paradigm to address deployment constraints in resource-limited environments.
Outcome:	The proposed model performs well on a resource-limited JMSRC task with only 3B parameters and shows generalization and interpretability.

Copied to clipboard

Zongqi Wang, Tianle Gu, Baoyuan Wu, Yujiu Yang

On the Sentence Embeddings from Pre-trained Language Models (2020.emnlp-main)

Challenge:	Existing methods for tracing text origins struggle with a watermark effectiveness dilemma . weaker watermarks preserve text quality, while stronger ones enhance effectiveness .
Approach:	They propose a method that adjusts watermark strength in response to changes in a key factor . they first formalize the problem within a multi-objective trade-off analysis framework .
Outcome:	The proposed method improves watermark effectiveness but reduces text quality . the proposed method prioritizes flexibility and time and space efficiency .

Copied to clipboard

Bohan Li, Hao Zhou, Junxian He, Mingxuan Wang, Yiming Yang, Lei Li

Reducing Spurious Correlations in Aspect-based Sentiment Analysis with Explanation from Large Language Models (2023.findings-emnlp)

Challenge:	Pre-trained contextual representations like BERT have been widely used for NLP tasks.
Approach:	They propose to transform anisotropic sentence embedding distribution to smooth and isotropic Gaussian distribution by normalizing flows that are learned with an unsupervised objective.
Outcome:	The proposed method achieves significant performance gains over state-of-the-art embeddings on a variety of semantic textual similarity tasks.

Copied to clipboard

Qianlong Wang, Keyang Ding, Bin Liang, Min Yang, Ruifeng Xu

Repairing Catastrophic-Neglect in Text-to-Image Diffusion Models via Attention-Guided Feature Enhancement (2024.findings-emnlp)

Challenge:	Aspect-based sentiment analysis models are susceptible to learning spurious correlations between words . a recent study shows that feature engineering is time-consuming and costly .
Approach:	They propose to use a template to prompt LLMs to generate an appropriate explanation for the sentiment polarity of each aspect to reduce spurious correlations.
Outcome:	The proposed methods improve ABSA models and their generalization ability.

Copied to clipboard

Zhiyuan Chang, Mingyang Li, Junjie Wang, Yi Liu, Qing Wang, Yang Liu

AgentGym2: Benchmarking Large Language Model Agents in De-Idealized Real-World Environments (2026.acl-long)

Challenge:	Text-to-Image Diffusion models generate high-quality images from textual descriptions, but they often produce images that do not fully align with the input prompts, resulting in semantic inconsistencies.
Approach:	They propose an automated repair approach to address catastrophic-neglect in T2I DMs.
Outcome:	The proposed model achieves 10.1%-16.3% higher Correct Rate in image generation compared to baselines.

Copied to clipboard

Zhiheng Xi, Dingwen Yang, Jiaqi Liu, Jixuan Huang, Honglin Guo, Baodai Huang, Tinggang Chen, Qi Zhang, Zhonghang Lu, Chenyu Liu, Jiajun Sun, Jiazheng Zhang, Dingwei Zhu, Xin Guo, Junzhe Wang, Zhihao Zhang, Yuming Yang, Junjie Ye, Minghe Gao, Dongrui Liu, Jiaming Ji, Guohao Li, Tao Gui, Qi Zhang, Xuanjing Huang

Know You First and Be You Better: Modeling Human-Like User Simulators via Implicit Profiles (2025.acl-long)

Challenge:	Existing benchmarks evaluate agents in simplified, idealized settings, relying on pre-packaged tool interfaces, overlooking critical steps, and assume inputs are clean and fully specified.
Approach:	They propose a framework that evaluates language agents in simplified, idealized settings . they show that even SOTA systems like Gemini and GPT-5 struggle on AgentGym2 .
Outcome:	Experiments on 15 proprietary and open-source models show that even SOTA systems like Gemini and GPT-5 struggle on AgentGym2 .

Copied to clipboard

Kuang Wang, Xianfei Li, Shenghao Yang, Li Zhou, Feng Jiang, Haizhou Li

Reason from Fallacy: Enhancing Large Language Models’ Logical Reasoning through Logical Fallacy Understanding (2024.findings-naacl)

Challenge:	Existing user simulators lack authenticity and user-level diversity in interactions with large language models.
Approach:	They propose a user simulator with implicit user profiles that infers user profiles from human-machine interactions to simulate personalized and realistic dialogues.
Outcome:	The proposed framework outperforms baselines in authenticity and diversity while maintaining comparable consistency.

Copied to clipboard

Yanda Li, Dixuan Wang, Jiaqing Liang, Guochao Jiang, Qianyu He, Yanghua Xiao, Deqing Yang

From Charts to Code: A Hierarchical Benchmark for Multimodal Models (2026.acl-long)

Challenge:	Large Language Models (LLMs) have demonstrated good performance in many reasoning tasks, but struggle with some more complex reasoning tasks including logical reasoning.
Approach:	They propose five concrete tasks from three cognitive dimensions of WHAT, WHY, and HOW to evaluate LLMs’ capability of logical fallacy understanding.
Outcome:	The proposed dataset can be used to evaluate LLMs’ LFU capability and to fine-tune LLM models to obtain significantly enhanced performance on logical reasoning.

Copied to clipboard

Jiahao Tang, Henry Hengyuan Zhao, Lijian Wu, Zijian Zhang, Yifei Tao, Dongxing Mao, Yang Wan, Jingru Tan, Min Zeng, Min Li, Alex Jinpeng Wang

HERB: Measuring Hierarchical Regional Bias in Pre-trained Language Models (2022.findings-aacl)

Challenge:	Chart2Code is a new benchmark for evaluating the natural language to chart code generation capabilities of large multimodal models.
Approach:	They introduce Chart2Code, a new benchmark for evaluating the natural language to chart code generation capabilities of large multimodal models.
Outcome:	The proposed benchmark is the first to scale task complexity while capturing diverse scenarios.

Copied to clipboard

Yizhi Li, Ge Zhang, Bohao Yang, Chenghua Lin, Anton Ragni, Shi Wang, Jie Fu

Parallax: Visualizing and Understanding the Semantics of Embedding Spaces via Algebraic Formulae (P19-3)

Challenge:	Existing methods do not examine social groups categorised by geographical information, leaving the region-related biases in pre-trained LMs unexplored.
Approach:	They propose a hierarchical regional bias evaluation method to quantify regional bias in pre-trained language models.
Outcome:	The proposed method evaluates regional bias with regard to comprehensive topics and measures potential regional bias that can be propagated to downstream tasks.

Copied to clipboard

Piero Molino, Yang Wang, Jiawei Zhang

ActiView: Evaluating Active Perception Ability for Multimodal Large Language Models (2025.acl-long)

Challenge:	Embeddings are a fundamental component of many modern machine learning and natural language processing models.
Approach:	They propose a tool for visualizing embedding spaces using parametric projections . they demonstrate the power of Parallax and propose % task-oriented approach .
Outcome:	The proposed tool is based on two-dimensional projections without interpretable semantics . it enhances interpretability and allows for more fine-grained analysis .

Copied to clipboard

Ziyue Wang, Chi Chen, Fuwen Luo, Yurui Dong, Yuanchi Zhang, Yuzhuang Xu, Xiaolong Wang, Peng Li, Yang Liu

Exploring Union and Intersection of Visual Regions for Generating Questions, Answers, and Distractors (2024.emnlp-main)

Challenge:	Existing benchmarks for evaluating MLLMs have not addressed active perception . a novel benchmark is proposed to evaluate active perception in ML models .
Approach:	They propose a benchmark to evaluate active perception in Multimodal Large Language Models . they restrict the perceptual field of a model and require it to actively zoom or shift it .
Outcome:	The proposed benchmark focuses on a specialized form of Visual Question Answering (VQA) that eases and quantifies the evaluation yet challenging for existing MLLMs.

Copied to clipboard

Wenjian Ding, Yao Zhang, Jun Wang, Adam Jatowt, Zhenglu Yang

SeaD: End-to-end Text-to-SQL Generation with Schema-aware Denoising (2022.findings-naacl)

Challenge:	Existing efforts to generate image-related questions, correct answers, or challenge distractors are limited.
Approach:	They propose to put the spotlight on different image regions to diversify QADs . they propose a framework that generates each QAD based on a recurrent multimodal encoder .
Outcome:	The proposed framework puts the spotlight on different image regions to diversify QADs.

Copied to clipboard

Kuan Xu, Yongbo Wang, Yongliang Wang, Zihao Wang, Zujie Wen, Yang Dong

MS2SL: Multimodal Spoken Data-Driven Continuous Sign Language Production (2024.findings-acl)

Challenge:	Using sketch-based slot filling, text-to-SQL models suffer from over-complexity . et al., e.al., and d.albert, dr., propose a novel method for text- to-Sql generation .
Approach:	They propose to train sequence-to-sequence model with Schema-aware Denoising . they propose a clause-sensitive execution guided (EG) decoding strategy .
Outcome:	The proposed method improves performance in schema linking and grammar correctness . it also establishes new state-of-the-art on the WikiSQL benchmark .

Copied to clipboard

Jian Ma, Wenguan Wang, Yi Yang, Feng Zheng

MC2: A Minimum-Coverage and Dataset-Agnostic Framework for Compositional Generalization of LLMs on Semantic Parsing (2025.findings-emnlp)

Challenge:	Existing solutions for sign language production are limited due to phonological differences and data scarcity.
Approach:	They propose a unified framework for continuous sign language production that generates sign predictions step by step from text or speech embeddings.
Outcome:	The proposed model achieves competitive performance on how2sign and PHOENIX14T datasets.

Copied to clipboard

Ziyao Xu, Zhe Yang, Houfeng Wang

From Facts to Insights: A Study on the Generation and Evaluation of Analytical Reports for Deciphering Earnings Calls (2025.coling-main)

Challenge:	Existing research relies on dataset-specific designs or a large number of samples to improve compositional generalization of large language models (LLMs) .
Approach:	They propose a minimum-coverage framework that can help LLMs achieve compositional generalization by selecting and organizing samples that satisfy the primitive coverage.
Outcome:	The proposed framework can improve compositional generalization on different parsing datasets in the minimum-coverage setting.

Copied to clipboard

Tomas Goldsack, Yang Wang, Chenghua Lin, Chung-Chi Chen

Challenge:	Existing studies have focused on the generation and evaluation of analytical reports derived from Earnings Calls (ECs).
Approach:	They propose to use Large Language Models to generate and evaluate analytical reports derived from Earnings Calls (ECs) they propose to introduce specialized agents that introduce diverse viewpoints and desirable topics into the report generation process.
Outcome:	The proposed model improves the quality of reports in different settings, while human-written reports remain preferred in the majority of cases.

Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search (2026.findings-acl)

Copied to clipboard

Yifei Zhang, Xu Yang, Xiao Yang, Bowen Xian, Qizheng Li, Shikai Fang, Jingyuan Li, Jian Wang, Minrui Xu, Yuge Zhang, Weiqing Liu, Jiang Bian

Flattery in Motion: Benchmarking and Analyzing Sycophancy in Video-LLMs (2026.acl-long)

Challenge:	LLM-based agents for machine learning engineering rely on tree search to rank candidates.
Approach:	They propose an LLM-based agent that operationalizes gradient-based optimization.
Outcome:	The proposed agent achieves a state-of-the-art 35.1% any-medal rate on MLE-Bench with a limited budget on a single GPU.

Copied to clipboard

Wenrui Zhou, Mohamed Hendy, Shu Yang, Qingsong Yang, Zikun Guo, Yuyu Luo, Lijie Hu, Di Wang

Extracting Commonsense Properties from Embeddings with Limited Human Guidance (P18-2)

Challenge:	Current sycophancy research has largely overlooked its specific manifestations in the video-language domain.
Approach:	They propose a video-LLM sycophancy benchmarking and evaluation to evaluate scophancies in video-LLMs.
Outcome:	The proposed benchmark evaluates sycophantic behavior in state-of-the-art Video-LLMs across diverse question formats, prompt biases, and visual reasoning tasks.

Copied to clipboard

Yiben Yang, Larry Birnbaum, Ji-Ping Wang, Doug Downey

Omni-Chart-600K: A Comprehensive Dataset of Chart Types for Chart Understanding (2025.findings-naacl)

Challenge:	Existing methods for learning common sense from text require dozens of hand-annotated frames to connect the property to how it is indirectly reflected in text.
Approach:	They propose a method for extracting object-property comparisons from pre-trained embeddings.
Outcome:	The proposed approach exceeds previous work but requires less hand-annotated knowledge.

Copied to clipboard

Shulei Wang, Shuai Yang, Wang Lin, Zirun Guo, Sihang Cai, Hai Huang, Ye Wang, Jingyuan Chen, Tao Jin

SG-FSM: A Self-Guiding Zero-Shot Prompting Paradigm for Multi-Hop Question Answering Based on Finite State Machine (2025.findings-naacl)

Challenge:	Existing chart-related training methods lack capabilities in information extraction, mathematical reasoning, and understanding of multiple chart types.
Approach:	They propose a two-stage training strategy and method for jointly training a vision encoder tailored for multi-type charts to address the deficiencies in chart types and limited scope of chart tasks in existing datasets.
Outcome:	The proposed dataset includes 21 diverse chart types and tasks, including data retrieval and mathematical reasoning.

Copied to clipboard

Xiaochen Wang, Junqing He, Liang Chen, Gholamreza Haffari, Yiru Wang, Zhe Yang, Xiangdi Meng, Kunhao Pan, Zhifang Sui

Learning Personalized Alignment for Evaluating Open-ended Text Generation (2024.emnlp-main)

Challenge:	Multi-hop Question Answering (MHQA) is a challenging task that requires models to answer multiple questions with multiple passages.
Approach:	They propose a self-guided prompting finite state machine to improve multi-hop reasoning abilities by iterating over multiple questions and correcting itself to improve accuracy.
Outcome:	The proposed approach outperforms baselines on Musique and other datasets.

Copied to clipboard

Danqing Wang, Kevin Yang, Hanlin Zhu, Xiaomeng Yang, Andrew Cohen, Lei Li, Yuandong Tian

NOTABLE: Transferable Backdoor Attacks Against Prompt-based NLP Models (2023.acl-long)

Challenge:	Traditional evaluation metrics rely heavily on lexical similarity with human-written references, showing poor correlation with human judgments and failing to account for alignment with the diversity of human preferences.
Approach:	They propose an interpretable evaluation framework that evaluates alignment with specific human preferences by providing detailed comments and fine-grained scoring.
Outcome:	The proposed framework outperforms GPT-4 in Kendall correlation and accuracy with zero-shot reviewers.

Copied to clipboard

Kai Mei, Zheng Li, Zhenting Wang, Yang Zhang, Shiqing Ma

UnCo: Uncertainty-Driven Collaborative Framework of Large and Small Models for Grounded Multimodal NER (2025.emnlp-main)

Challenge:	Existing backdoor attacks against prompt-based learning involve injecting back doors into embedding layers or word embedders.
Approach:	They propose a backdoor attack against prompt-based learning that injects backdoors into embedding layers or word embeddable vectors.
Outcome:	The proposed backdoor attack outperforms two state-of-the-art models on six NLP tasks and three prompting strategies.

Copied to clipboard

Jielong Tang, Yang Yang, Jianxing Yu, Zhen-Xing Wang, Haoyuan Liang, Liang Yao, Jian Yin

Task-oriented Domain-specific Meta-Embedding for Text Classification (2020.emnlp-main)

Challenge:	Existing methods to identify unseen multimodal entities struggle with limited knowledge and generalization.
Approach:	They propose a framework that leverages the strengths of small fine-tuned models and MLLMs to generate unambiguous predictions.
Outcome:	Extensive experiments show that the proposed framework retains the in-domain knowledge of small models while utilizing the capabilities of MLLMs to handle unseen entities.

Copied to clipboard

Xin Wu, Yi Cai, Yang Kai, Tao Wang, Qing Li

OpenHuEval: Evaluating Large Language Model on Hungarian Specifics (2025.findings-acl)

Challenge:	Existing methods neglect domain-specific knowledge and use the same word embedding for each word in all domain-specified datasets.
Approach:	They propose a method to incorporate domain-specific and task-oriented information into meta-embeddings by combining pre-trained word embeddings.
Outcome:	The proposed method performs well on four text classification datasets and shows that it is compatible with existing methods.

Copied to clipboard

Haote Yang, Xingjian Wei, Jiang Wu, Noémi Ligeti-Nagy, Jiaxing Sun, Yinfan Wang, Győző Zijian Yang, Junyuan Gao, Jingchao Wang, Bowen Jiang, Shasha Wang, Nanjun Yu, Zihao Zhang, Shixin Hong, Hongwei Liu, Wei Li, Songyang Zhang, Dahua Lin, Lijun Wu, Gábor Prószéky, Conghui He

Context-DPO: Aligning Language Models for Context-Faithfulness (2025.findings-acl)

Challenge:	Recent advances in Large Language Models (LLMs) represent significant strides toward artificial general intelligence (AGI).
Approach:	They introduce OpenHuEval, the first benchmark for LLMs focusing on the Hungarian language and specifics.
Outcome:	The framework reveals intrinsic patterns and mechanisms of LLMs in non-English languages, with Hungarian serving as an example.

Copied to clipboard

Baolong Bi, Shaohan Huang, Yiwei Wang, Tianchi Yang, Zihan Zhang, Haizhen Huang, Lingrui Mei, Junfeng Fang, Zehao Li, Furu Wei, Weiwei Deng, Feng Sun, Qi Zhang, Shenghua Liu

Mining the Past with Dual Criteria: Integrating Three types of Historical Information for Context-aware Event Forecasting (2025.emnlp-main)

Challenge:	Context-DPO is the first alignment method specifically designed to enhance contextfaithfulness for large language models.
Approach:	They propose a benchmark that simulates Retrieval-Augmented Generation scenarios with knowledge conflicts to evaluate context-faithfulness.
Outcome:	The proposed method improves LLMs' context-faithfulness by 35% to 280% over open-source models.

Copied to clipboard

Rong Ma, Lei Wang, Yating Yang, Bo Ma, Rui Dong, Fengyi Yang, Ahtamjan Ahmat, Kaiwen Lu, Xinyue Wang

Defending against Indirect Prompt Injection by Instruction Detection (2025.findings-emnlp)

Challenge:	Existing methods focus on entities and structural dependencies but overlook implicitly relevant information.
Approach:	They propose a method that leverages event semantics for relevance modeling and incorporates a self-supervised semantic filter based on factual event associations to capture implicitly relevant historical information.
Outcome:	The proposed method outperforms existing methods on three public benchmark datasets and is highly effective on two structured temporal knowledge graph forecasting datasets.

Copied to clipboard

Tongyu Wen, Chenglong Wang, Xiyuan Yang, Haoyu Tang, Yueqi Xie, Lingjuan Lyu, Zhicheng Dou, Fangzhao Wu

Revealing COVID-19’s Social Dynamics: Diachronic Semantic Analysis of Vaccine and Symptom Discourse on Twitter (2024.findings-emnlp)

Challenge:	Indirect Prompt Injection attacks can be exploited by LLMs that are embedded with external data.
Approach:	They propose a detection-based approach that leverages the behavioral states of LLMs to identify potential IPI attacks.
Outcome:	The proposed approach reduces the success rate of attacks to 0.03% on the BIPIA benchmark.

Copied to clipboard

Zeqiang Wang, Jiageng Wu, Yuqi Wang, Wei Xjtlu, Jie Yang, Nishanth Sastry, Jon Johnson, Suparna De

S+PAGE: A Speaker and Position-Aware Graph Neural Network Model for Emotion Recognition in Conversation (2022.aacl-main)

Challenge:	Social media data provide a new source for social science and cultural analysis research, but its analysis is challenging due to the semantic shift phenomenon, where word meanings evolve over time.
Approach:	They propose an unsupervised dynamic word embedding method to capture longitudinal semantic shifts in social media data without predefined anchor words.
Outcome:	The proposed method captures longitudinal semantic shifts in social media data without predefined anchor words and leverages word co-occurrence statistics and dynamic updating to adapt embeddings over time.

Copied to clipboard

Chen Liang, Jing Xu, Yangkun Lin, Chong Yang, Yongliang Wang

Distributional Clarity: The Hidden Driver of RL-Friendliness in Large Language Models (2026.acl-long)

Challenge:	Emotion recognition in conversation (ERC) is a task arousing increasing interest in many fields.
Approach:	They propose a novel GNN-based ERC model that captures speaker and position information.
Outcome:	The proposed model captures speaker and position-aware conversation structure information.

Copied to clipboard

Shaoning Sun, Mingzhu Cai, Huang He, Bingjin Chen, Siqi Bao, Yujiu Yang, Hua Wu, Haifeng Wang

ShifCon: Enhancing Non-Dominant Language Capabilities with a Shift-based Multilingual Contrastive Framework (2025.acl-long)

Challenge:	RL-friendly models exhibit intra-class compactness and inter-class separation in probability assignments . under identical training, Qwen models achieve substantial gains, while others like Llama yield limited improvements.
Approach:	They propose a method to quantify distributional clarity in probability space . they show distributional clearness is a trainable property underlying RL-Friendliness .
Outcome:	The proposed model families achieve substantial gains under identical training, while others like Llama yield limited improvements.

Copied to clipboard

Hengyuan Zhang, Chenming Shang, Sizhe Wang, Dongdong Zhang, Yiyao Yu, Feng Yao, Renliang Sun, Yujiu Yang, Furu Wei

Law in Silico: Simulating Legal Society with LLM-Based Agents (2026.findings-acl)

Challenge:	Experiments show that ShifCon significantly enhances the performance of non-dominant languages due to the imbalance in training data across languages.
Approach:	They propose a Shift-based multilingual Contrastive framework that aligns the internal forward process of other languages toward that of the dominant one.
Outcome:	The proposed framework significantly improves performance of non-dominant languages, particularly for low-resource ones.

Copied to clipboard

Yiding Wang, Yuxuan Chen, Fanxu Meng, Xifan Chen, Xiaolei Yang, Muhan Zhang

Challenge:	Large Language Models (LLMs) are powerful tools for legal simulation, but their application remains underexplored.
Approach:	They propose a unified LLM-based agent framework for simulating legal scenarios . they calibrate agent behaviors against real-world crime data .
Outcome:	The proposed framework calibrates agent behaviors against real-world crime data.

SLARD: A Chinese Superior Legal Article Retrieval Dataset (2025.coling-main)

Copied to clipboard

Zhe Chen, Pengjie Ren, Fuhui Sun, Xiaoyan Wang, Yujun Li, Siwen Zhao, Tengyi Yang

Detecting Subtle Differences between Human and Model Languages Using Spectrum of Relative Likelihood (2024.emnlp-main)

Challenge:	Existing retrieval methods struggle to achieve ideal results, a study finds . existing large language models lack prior knowledge of the content of superior legal articles .
Approach:	They propose to use a Chinese superior legal article retrieval dataset to find relevant articles with higher legal effectiveness.
Outcome:	The proposed dataset shows that existing retrieval methods struggle to achieve ideal results.

Copied to clipboard

Yang Xu, Yu Wang, Hao An, Zhichen Liu, Yongyuan Li

Psycholinguistics

Challenge:	Existing methods for detecting modelgenerated texts from human texts are limited by the fact that absolute likelihood values of texts are bound to certain linguistic and cognitive constraints.
Approach:	They propose to use relative likelihood values instead of absolute ones to extract useful features from the spectrum-view of likelihood for the human-model text detection task.
Outcome:	The proposed method can reveal subtle differences between human and model languages, which find theoretical roots in psycholinguistics studies.

OptiCo: Adaptive Distributed Training Optimization via Collaborative Agent Reasoning (2026.acl-long)

Copied to clipboard

Sheng Chen, Tang Zhe, Weixing Zhang, Fei Yang, Yuanyuan. Wang, Tianlin Li, Yang Liu

PhotoChat: A Human-Human Dialogue Dataset With Photo Sharing Behavior For Joint Image-Text Modeling (2021.acl-long)

Challenge:	Existing distributed training frameworks are plagued by over-reliance on prior profiling and poor generalization across models/hardware.
Approach:	They propose a model-driven multi-agent framework that leverages Large Language Models to enable automatic and explainable distributed training strategy configuration.
Outcome:	The proposed framework outperforms expert-designed training strategies within 20 iterations.

Copied to clipboard

Xiaoxue Zang, Lijuan Liu, Maria Wang, Yang Song, Hao Zhang, Jindong Chen

WebClipper: Efficient Evolution of Web Agents with Graph-based Trajectory Pruning (2026.acl-long)

Challenge:	PhotoChat contains 12k dialogues, each of which is paired with a user photo that is shared during the conversation.
Approach:	They propose to use PhotoChat to facilitate research on image-text modeling by combining a photo-sharing intent prediction task and a picture retrieval task to retrieve the most relevant photo according to the dialogue context.
Outcome:	The proposed tasks achieve 10.4% recall@1 and 58.1% F1 scores, indicating that the proposed dataset presents interesting yet challenging real-world problems.

Copied to clipboard

Junjie Wang, Zequn Xie, Dan Yang, Jie Feng, Yue Shen, Duolin Sun, Meixiu Long, Yihan Jiao, Zhehao Tan, Jian Wang, Peng Wei, Jinjie Gu

DevEval: A Manually-Annotated Code Generation Benchmark Aligned with Real-World Code Repositories (2024.findings-acl)

Challenge:	Open-source web agents rely on long tool-call trajectories with cyclic reasoning loops and exploration of unproductive branches.
Approach:	They propose a framework that compresses web agent trajectories via graph-based pruning.
Outcome:	The proposed framework reduces tool-call rounds by 20% while improving accuracy and efficiency while maintaining the same level of performance as existing models.

Copied to clipboard

Jia Li, Ge Li, Yunfei Zhao, Yongmin Li, Huanyu Liu, Hao Zhu, Lecheng Wang, Kaibo Liu, Zheng Fang, Lanshen Wang, Jiazheng Ding, Xuanming Zhang, Yuqi Zhu, Yihong Dong, Zhi Jin, Binhua Li, Fei Huang, Yongbin Li, Bin Gu, Mengfei Yang

CREATER: CTR-driven Advertising Text Generation with Controlled Pre-Training and Contrastive Fine-Tuning (2022.naacl-industry)

Challenge:	Existing benchmarks are poorly aligned with real-world code repositories and are insufficient to evaluate the coding abilities of Large Language Models (LLMs).
Approach:	They propose a repository-level benchmark named DevEval to evaluate LLMs' coding abilities in real-world code repositories.
Outcome:	The proposed benchmarks show that the LLMs perform better in real-world code repositories than existing benchmarks.

Copied to clipboard

Penghui Wei, Xuanhua Yang, ShaoGuo Liu, Liang Wang, Bo Zheng

Beyond "I Don’t Know": Evaluating LLM Self-Awareness in Discriminating Data and Model Uncertainty (2026.acl-long)

Challenge:	a paper focuses on automatically generating the text of an ad to capture user interest for achieving higher click-through rate.
Approach:	They propose a CTR-driven advertising text generation approach to generate ad texts based on user reviews.
Outcome:	The proposed approach outperforms existing approaches on industrial datasets and on large-scale unpaired reviews.

Copied to clipboard

Jingyi Ren, Ante Wang, Yunghwei Lai, Xiaolong Wang, Linlu Gong, Weitao Li, Weizhi Ma, Yang Liu

Challenge:	Prior studies treat refusal as a generic "I don't know" lack of distinction limits downstream action decisions like requesting clarification or invoking external tools.
Approach:	They propose a benchmark to evaluate explicit uncertainty attribution in large language models.
Outcome:	The proposed method improves uncertainty attribution while preserving answer accuracy.

DrAgent: Empowering Large Language Models as Medical Agents for Multi-hop Medical Reasoning (2025.findings-emnlp)

Copied to clipboard

Fenglin Liu, Zheng Li, Hongjian Zhou, Qingyu Yin, Jingfeng Yang, Xin Liu, Zhengyang Wang, Xianfeng Tang, Shiyang Li, Xiang He, Ruijie Wang, Bing Yin, Xiao Gu, Lei Clifton, David A. Clifton

LoopCoder: Scaling Code Intelligence via Looped Language Models (2026.findings-acl)

Challenge:	commercial LLMs can be difficult to use in real-world clinical decision-making . a lightweight LLM can be used to collaborate with diverse clinical tools .
Approach:	They propose a lightweight LLM that can be used to build medical LLMs as agents . they use recursive curriculum learning to optimize the LLM in an easy-to-hard progression .
Outcome:	The proposed approach outperforms human experts in medical examinations on diverse datasets.

Copied to clipboard

Jian Yang, Wei Zhang, Shuyue Guo, Yizhi LI, Linzheng Chai, Zhengmao Ye, Shukai Liu, Yuyang Song, Jiajun Wu, Che Liu, Tianyu Zheng, Siwei Wu, Leo L, Xudong Ma, Chuan Hao, Ran Tao, Yan Xing, Jianzhou Wang, Mingjie Tang, Aishan Liu, Zhoujun Li, Xianglong Liu, Weifeng Lv, Bryan Dai

OD-RTE: A One-Stage Object Detection Framework for Relational Triple Extraction (2023.acl-long)

Challenge:	Large language models have mastered syntax-level code generation, but complex algorithmic reasoning remains a challenge.
Approach:	They propose a recurrent inductive bias that aligns with the recursive nature of programming logic.
Outcome:	The proposed model achieves comparable performance to standard dense models with more parameters.

Copied to clipboard

Jinzhong Ning, Zhihao Yang, Yuanyuan Sun, Zhizheng Wang, Hongfei Lin

Evaluating Text Generation Quality Using Spectral Distances of Surprisal (2025.findings-emnlp)

Challenge:	Existing pipelines for relational triple extraction are underutilizing regional information of triple.
Approach:	They propose a one-stage Object Detection framework for Relational Triple Extraction . framework uses vertices-based bounding box detection and global relational triple region detection .
Outcome:	The proposed framework could extract all types of triples on two widely used datasets.

Copied to clipboard

Zhichen Liu, Yongyuan Li, Yang Xu, Yu Wang, Yingfang Yuan, Zuhao Yang

On LLM-Based Scientific Inductive Reasoning Beyond Equations (2025.emnlp-main)

Challenge:	Existing metric fails to capture text surprisal, but FACE-2 produces stronger agreement with human preferences.
Approach:	They propose a new automatic evaluation metric for open-ended text generation . they propose metric that extracts the dynamic patterns (spectrum) of text surprisal .
Outcome:	The proposed metric outperforms existing methods in revealing the model scaling effect . it produces stronger agreement with human preferences from a large human-annotated dataset .

Copied to clipboard

Brian S. Lin, Jiaxin Yuan, Zihan Zhou, Shouli Wang, Shuo Wang, Cunliang Kong, Qi Shi, Yuxuan Li, Liner Yang, Zhiyuan Liu, Maosong Sun

Turning the Tide: Repository-based Code Reflection (2025.findings-emnlp)

Challenge:	Existing research on inductive reasoning models emphasizes rule design without grounding them in specific scenarios.
Approach:	They propose to use LLMs to learn underlying patterns from limited examples in entirely new environments.
Outcome:	The proposed benchmark evaluates the inductive reasoning abilities of large language models in scientific settings.

Copied to clipboard

Wei Zhang, Jian Yang, Jiaxi Yang, Ya Wang, Zhoujun Li, Zeyu Cui, Binyuan Hui, Junyang Lin

Skeleton-Guided-Translation: A Benchmarking Framework for Code Repository Translation with Fine-Grained Quality Evaluation (2025.findings-emnlp)

Challenge:	Code large language models (LLMs) enhance programming by understanding and generating code across languages.
Approach:	a new benchmark evaluates code understanding and generation in repositories using code large language models.
Outcome:	The proposed model improves code understanding and generation in repositories by evaluating 1,888 test cases across 6 programming languages.

Copied to clipboard

Xing Zhang, Jiaheng Wen, Fangkai Yang, Yu Kang, Pu Zhao, Junhao Wang, Maoquan Wang, Yufan Huang, Shengyu Fu, Elsie Nallipogu, Qingwei Lin, Yingnong Dang, Saravan Rajmohan, Dongmei Zhang

Multiple Knowledge-Enhanced Interactive Graph Network for Multimodal Conversational Emotion Recognition (2024.findings-emnlp)

Challenge:	Existing code translation benchmarks focus on individual functions, overlooking repository-level challenges like intermodule coherence and dependency management.
Approach:	They propose a framework for benchmarking Java-to-C# translation at the repository level . it uses a translation framework guided by skeletons and fine-grained quality evaluation .
Outcome:	The proposed framework improves Java-to-C# translation quality at the repository level.

Copied to clipboard

Geng Tu, Jun Wang, Zhenyu Li, Shiwei Chen, Bin Liang, Xi Zeng, Min Yang, Ruifeng Xu

PLOME: Pre-training with Misspelled Knowledge for Chinese Spelling Correction (2021.acl-long)

Challenge:	Multimodal Emotion Recognition in Conversations models struggle due to lack of Common Sense Knowledge (CSK).
Approach:	They propose a multimodal approach to integrate multiple knowledge into the edge representations by integrating textual and visual CSK.
Outcome:	The proposed model outperforms state-of-the-art methods on two popular datasets.

Copied to clipboard

Shulin Liu, Tao Yang, Tianchi Yue, Feng Zhang, Di Wang

LLM-A*: Large Language Model Enhanced Incremental Heuristic Search on Path Planning (2024.findings-emnlp)

Challenge:	Chinese spelling correction (CSC) is a task to detect and correct spelling errors in texts.
Approach:	They propose a Pre-trained masked Language model with Misspelled knowledgE (PLOME) which jointly learns how to understand language and correct spelling errors.
Outcome:	The proposed model outperforms state-of-the-art methods on widely used benchmarks and achieves superior performance against existing models.

Copied to clipboard

Silin Meng, Yiwei Wang, Cheng-Fu Yang, Nanyun Peng, Kai-Wei Chang

Identifying the Periodicity of Information in Natural Language (2026.acl-long)

Challenge:	Existing path planning algorithms suffer from significant computational and memory inefficiencies as the state space grows . large language models excel in environmental analysis but fall short in detailed spatial and temporal reasoning .
Approach:	They propose a new path planning method that synergistically combines A* and LLMs to improve pathfinding efficiency.
Outcome:	The proposed method improves pathfinding efficiency while maintaining integrity of path validity in large-scale scenarios.

Copied to clipboard

Yulin OU, Yu Wang, Yang Xu, Hendrik Buschmeier

Discourse & Pragmatics

Challenge:	Existing methods to detect periodicity of information in natural language are based on a canonical periodicity detection algorithm.
Approach:	They propose a method to detect periods in surprisal sequences in natural language . they propose to use this method to identify periods outside the distributions of typical units .
Outcome:	The proposed method can detect significant periods in a single document.

MSP: Multi-Stage Prompting for Making Pre-trained Language Models Better Translators (2022.acl-long)

Copied to clipboard

Zhixing Tan, Xiangwen Zhang, Shuo Wang, Yang Liu

DELMAN: Dynamic Defense Against Large Language Model Jailbreaking with Model Editing (2025.findings-acl)

Challenge:	Prompting has been shown to be a promising approach for applying pre-trained language models to perform downstream tasks.
Approach:	They propose a method that divides the translation process into three stages using pre-trained language models.
Outcome:	The proposed method significantly improves translation performance of pre-trained language models on three translation tasks.

Copied to clipboard

Yi Wang, Fenghua Weng, Sibei Yang, Zhan Qin, Minlie Huang, Wenjie Wang

PTD-SQL: Partitioning and Targeted Drilling with LLMs in Text-to-SQL (2024.emnlp-main)

Challenge:	Existing safety mechanisms for Large Language Models (LLMs) are inadequate to protect against jailbreak attacks, resulting in performance degradation on general tasks.
Approach:	They propose a method that directly updates a minimal set of relevant parameters to neutralize harmful behaviors while preserving the model’s utility.
Outcome:	The proposed model outperforms baseline methods in mitigating jailbreak attacks while preserving the model’s utility.

Copied to clipboard

Ruilin Luo, Liyuan Wang, Binghuai Lin, Zicheng Lin, Yujiu Yang

MCTS: A Multi-Reference Chinese Text Simplification Dataset (2024.lrec-main)

Challenge:	Large Language Models (LLMs) are powerful tools for Text-to-SQL tasks . SQL solutions have a relatively fixed pattern, allowing for categorical thinking .
Approach:	They propose that query group partitioning allows LLMs to focus on learning the thought processes specific to a single problem type, thus enhancing their reasoning abilities across diverse difficulty levels and problem categories.
Outcome:	The proposed model outperforms state-of-the-art models on the Spider and BIRD datasets.

Copied to clipboard

Ruining Chong, Luming Lu, Liner Yang, Jinran Nie, Zhenghao Liu, Shuo Wang, Shuhan Zhou, Yaoxin Li, Erhong Yang

MedAdapter: Efficient Test-Time Adaptation of Large Language Models Towards Medical Reasoning (2024.emnlp-main)

Challenge:	Existing studies on text simplification systems have focused on unsupervised methods due to the limited evaluation data in language and domain.
Approach:	They propose a Chinese text simplification dataset that provides a detailed analysis and an annotation process.
Outcome:	The proposed dataset evaluates the performance of unsupervised methods and advanced large language models.

Copied to clipboard

Wenqi Shi, Ran Xu, Yuchen Zhuang, Yue Yu, Haotian Sun, Hang Wu, Carl Yang, May Dongmei Wang

TableDreamer: Progressive and Weakness-guided Data Synthesis from Scratch for Table Instruction Tuning (2025.findings-acl)

Challenge:	Large language models (LLMs) have improved generation and reasoning capabilities compared to traditional BERT-sized models due to massive number of parameters and extensive pre-training on vast textual corpora.
Approach:	They propose a unified post-hoc adapter for test-time adaptation of large language models . they propose to fine-tune only a small BERT-sized adapter to rank candidate LLMs .
Outcome:	The proposed adapter improves performance on four biomedical tasks without requiring computational resources or sharing data with third parties.

Copied to clipboard

Mingyu Zheng, Zhifan Feng, Jia Wang, Lanrui Wang, Zheng Lin, Hao Yang, Weiping Wang

PLATO-Ad: A Unified Advertisement Text Generation Framework with Multi-Task Prompt Learning (2022.emnlp-industry)

Challenge:	Existing methods for table instruction tuning are limited due to limited data diversity and lack of data quality.
Approach:	They propose a weakness-guided data synthesis framework for table instruction tuning that explores the vast input space of table understanding tasks and then iterates through the input space.
Outcome:	The proposed framework boosts the average accuracy of Llama3.1-8B-instruct by 11.62% with 27K GPT-4o synthetic data and outperforms state-of-the-art data synthesis baselines which use more training data.

Copied to clipboard

Zeyang Lei, Chao Zhang, Xinchao Xu, Wenquan Wu, Zheng-yu Niu, Hua Wu, Haifeng Wang, Yi Yang, Shuanglong Li

EventRAG: Enhancing LLM Generation with Event Knowledge Graphs (2025.acl-long)

Challenge:	Online advertisement text generation models have achieved remarkable success in generating high-quality text ads, but some challenges remain, such as low-resource scenarios and training efficiency for multiple ad tasks.
Approach:	They propose a unified text ad generation framework with multi-task prompt learning to tackle low-resource ade generation problem and a multi-step prompt learning mechanism to efficiently solve multiple aed generation tasks.
Outcome:	The proposed framework outperforms the state-of-the-art on offline and online metrics.

Copied to clipboard

Zairun Yang, Yilin Wang, Zhengyan Shi, Yuan Yao, Lei Liang, Keyan Ding, Emine Yilmaz, Huajun Chen, Qiang Zhang

Make-A-Voice: Revisiting Voice Large Language Models as Scalable Multilingual and Multitask Learners (2024.acl-long)

Challenge:	Existing approaches to text generation often neglect event structures that shape real-world narratives.
Approach:	They propose a framework that integrates structured event semantics with iterative retrieval and inference to enhance text generation.
Outcome:	Experiments on UltraDomain and MultiHopRAG show that the proposed framework outperforms baseline RAG systems in generation effectiveness, logical consistency, and multi-hop reasoning accuracy.

Copied to clipboard

Rongjie Huang, Chunlei Zhang, Yongqi Wang, Dongchao Yang, Jinchuan Tian, Zhenhui Ye, Luping Liu, Zehan Wang, Ziyue Jiang, Xuankai Chang, Jiatong Shi, Chao Weng, Zhou Zhao, Dong Yu

ToolBeHonest: A Multi-level Hallucination Diagnostic Benchmark for Tool-Augmented Large Language Models (2024.emnlp-main)

Challenge:	Large language models (LLMs) have been used for general-purpose interfaces across multiple tasks and languages.
Approach:	They propose to use large language models as a general-purpose interface across multiple tasks and languages.
Outcome:	The proposed model performs better on 200K hours of 6-language data for voice generation applications.

Copied to clipboard

Yuxiang Zhang, Jing Chen, Junjie Wang, Yaxin Liu, Cheng Yang, Chufan Shi, Xinyu Zhu, Zihao Lin, Hanwen Wan, Yujiu Yang, Tetsuya Sakai, Tian Feng, Hayato Yamana

Cross-layer Attention Sharing for Pre-trained Large Language Models (2026.tacl-1)

Challenge:	Currently, tool-augmented large language models (LLMs) only achieve total scores of 45.3 and 37.0, respectively, on a scale of 100.
Approach:	They propose a multi-level diagnostic process to assess the LLM's hallucinations through two perspectives: depth and breadth.
Outcome:	The proposed diagnostic process assesses the hallucinations of large language models through two perspectives: depth and breadth.

Copied to clipboard

Yongyu Mu, Yuzhang Wu, Yuchun Fan, Chenglong Wang, Hengyu Li, Jiali Zeng, Qiaozhi He, Murun Yang, Fandong Meng, Jie Zhou, Tong Xiao, Jingbo Zhu

Understanding and Mitigating Political Stance Cross-topic Generalization in Large Language Models (2026.acl-long)

Challenge:	Existing studies focus on compressing the Key-Value cache or grouping attention heads, while overlooking redundancy between layers.
Approach:	They propose a lightweight substitute for self-attention in well-trained LLMs that uses feed-forward networks to align attention heads between adjacent layers and low-rank matrices to approximate differences in layer-wise attention weights.
Outcome:	The proposed model reduces redundancy by sharing weights across layers while maintaining high response quality while reducing redundant calculations within 53% 84% of the total layers.

Copied to clipboard

Jiayi Zhang, Shu Yang, Junchao Wu, Derek F. Wong, Di Wang

Attack Prompt Generation for Red Teaming and Defending Large Language Models (2023.findings-emnlp)

Challenge:	Recent studies have focused on the internal representations of large language models and the mechanisms that lead to unintended cross-topic generalization.
Approach:	They propose a method that uses inhibition to localize political neurons and a technique that uses topic-specific blocking to mitigate the cross-topic generalization.
Outcome:	The proposed method reduces cross-topic generalization by 20% while preserving topic-specific performance.

Copied to clipboard

Boyi Deng, Wenjie Wang, Fuli Feng, Yang Deng, Qifan Wang, Xiangnan He

Masked Text-to-Audio Flow-Matching and Reward Feedback Optimization (2026.findings-acl)

Challenge:	Existing studies construct attack prompts via manual or automatic methods, but these methods have limitations on cost and quality.
Approach:	They propose an attack framework to instruct LLMs to mimic human-generated prompts through in-context learning and a defense framework that fine-tunes victim LLM's through iterative interactions with the attack framework.
Outcome:	The proposed approach is based on experiments on different LLMs to evaluate their effectiveness against red teaming attacks.

Copied to clipboard

Rongjie Huang, Dongchao Yang, Wenxiang Guo, Huadai Liu, Xize Cheng, Zehan Wang, Zhou Zhao, Xixin Wu, Helen M. Meng

Understanding GUI Agent Localization Biases through Logit Sharpness (2025.findings-emnlp)

Challenge:	Experimental results show that Flow-matching generative models can scale training by increasing data, computational resources, and model size.
Approach:	They propose a flow-matching transformer with masked generative modeling for scaling text-to-audio inference-time prediction.
Outcome:	The proposed model scales inference-time computations by masking generation and re-predicting them through iterative decoding.

Copied to clipboard

Xingjian Tao, Yiwei Wang, Yujun Cai, Zhicheng Yang, Jing Tang

Challenge:	Multimodal large language models often exhibit hallucinations that compromise reliability . despite promising performance, these models often display systematic localization errors .
Approach:	They propose a framework that categorizes model predictions into four distinct types . they propose metric that evaluates alignment between semantic continuity and logits distribution .
Outcome:	The proposed framework categorizes model predictions into four different types . it reveals nuanced failure modes beyond traditional accuracy metrics .

MathCoder-VL: Bridging Vision and Code for Enhanced Multimodal Mathematical Reasoning (2025.findings-acl)

Copied to clipboard

Ke Wang, Junting Pan, Linda Wei, Aojun Zhou, Weikang Shi, Zimu Lu, Han Xiao, Yunqiao Yang, Houxing Ren, Mingjie Zhan, Hongsheng Li

Large Language Model-Enhanced Multi-Armed Bandits (2026.acl-long)

Challenge:	Large Language Models (LMMs) struggle with simple tasks such as geometry, e.g., arithmetic, and reasoning.
Approach:	They propose to leverage code as supervision for cross-modal alignment . they propose to use FigCodifier and ImgCode-8.6M to synthesize novel mathematical figures .
Outcome:	The proposed model surpasses GPT-4o and Claude 3.5 Sonnet in the geometry problem-solving subset of MathVista, achieving improvements of 8.9% and 9.2%.

Copied to clipboard

Jiahang Sun, Zhiyong Wang, Runhan Yang, Chenjun Xiao, John C.s. Lui, Zhongxiang Dai

A Thorough Examination of Decoding Methods in the Era of LLMs (2024.emnlp-main)

Challenge:	Large language models (LLMs) have been used to sequential decision-making tasks like multi-armed bandits where an LLM is tasked with selecting arms in each iteration is often suboptimal.
Approach:	They propose to combine MAB and LLMs to leverage the in-context learning capability of LLM for reward prediction.
Outcome:	The proposed approach outperforms LLM-based direct arm selection on synthetic tasks where only preference feedback between arm pairs is available.

Copied to clipboard

Chufan Shi, Haoran Yang, Deng Cai, Zhisong Zhang, Yifan Wang, Yujiu Yang, Wai Lam

Generative Data Augmentation for Commonsense Reasoning (2020.findings-emnlp)

Challenge:	Decoding methods are essential for converting language models from next-token predictors into practical task solvers.
Approach:	They propose to evaluate decoding methods in general-purpose large language models . they find that decoding method performance is notably task-dependent .
Outcome:	The proposed methods perform task-dependently and are influenced by alignment, model size, and quantization.

Copied to clipboard

Yiben Yang, Chaitanya Malaviya, Jared Fernandez, Swabha Swayamdipta, Ronan Le Bras, Ji-Ping Wang, Chandra Bhagavatula, Yejin Choi, Doug Downey

Perspective Transition of Large Language Models for Solving Subjective Tasks (2025.findings-acl)

Challenge:	Recent advances in commonsense reasoning depend on large-scale human-authored training data.
Approach:	They propose a generative data augmentation technique that augments human-authored training data by using pretrained language models.
Outcome:	The proposed technique outperforms existing methods on commonsense reasoning benchmarks and enhances out-of-distribution generalization.

Copied to clipboard

Xiaolong Wang, Yuanchi Zhang, Ziyue Wang, Yuzhuang Xu, Fuwen Luo, Yile Wang, Peng Li, Yang Liu

RAG-Star: Enhancing Deliberative Reasoning with Retrieval Augmented Verification and Refinement (2025.naacl-long)

Challenge:	Large language models (LLMs) have revolutionized the field of natural language processing . performance of LLMs on subjective tasks is limited, authors say .
Approach:	They propose a method that allows LLMs to select between direct, role, and third-person perspectives for best way to solve corresponding subjective problem.
Outcome:	The proposed method outperforms widely used single fixed perspective based methods on 12 subjective tasks.

Copied to clipboard

Jinhao Jiang, Jiayi Chen, Junyi Li, Ruiyang Ren, Shijie Wang, Xin Zhao, Yang Song, Tao Zhang

Data Interpreter: An LLM Agent for Data Science (2025.findings-acl)

Challenge:	Existing large language models (LLMs) show exceptional problem-solving capabilities but struggle with complex reasoning tasks.
Approach:	They propose a novel RAG approach that integrates retrieved information to guide tree-based reasoning process based on LLMs.
Outcome:	The proposed approach outperforms existing methods in large language models . iteratively plans intermediate sub-queries and answers based on the LLM itself .

Copied to clipboard

Sirui Hong, Yizhang Lin, Bang Liu, Bangbang Liu, Binhao Wu, Ceyao Zhang, Danyang Li, Jiaqi Chen, Jiayi Zhang, Jinlin Wang, Li Zhang, Lingyao Zhang, Min Yang, Mingchen Zhuge, Taicheng Guo, Tuo Zhou, Wei Tao, Robert Tang, Xiangtao Lu, Xiawu Zheng, Xinbing Liang, Yaying Fei, Yuheng Cheng, Yongxin Ni, Zhibin Gou, Zongze Xu, Yuyu Luo, Chenglin Wu

PclGPT: A Large Language Model for Patronizing and Condescending Language Detection (2024.findings-emnlp)

Challenge:	Large Language Models (LLMs) excel in various domains but face challenges when applied to data science workflows due to their complex, multi-stage nature.
Approach:	They propose a hierarchical graph-based agent that represents complexity and a progressive strategy for step-by-step verification, refinement, and consistent context management.
Outcome:	The proposed agent surpasses state-of-the-art baselines on the MATH dataset and performs better on InfiAgent-DABench.

Copied to clipboard

Hongbo Wang, LiMingDa LiMingDa, Junyu Lu, Hebin Xia, Liang Yang, Bo Xu, Ruizhu Liu, Hongfei Lin

Don’t Say No: Jailbreaking LLM by Suppressing Refusal (2025.findings-acl)

Challenge:	Patronizing and condescending language is an essential branch of toxic language . pre-trained language models perform poorly in detecting PCL due to its implicit toxicity traits .
Approach:	They propose a novel LLM benchmark for patronizing and condescending language . they use a dataset to analyze the toxicity of patronizing condescending languages .
Outcome:	The proposed model can detect patronizing and condescending language (PCL) the model can be used to analyze the toxicity of the language and to improve the detection.

Copied to clipboard

Yukai Zhou, Jian Lou, Zhijie Huang, Zhan Qin, Sibei Yang, Wenjie Wang

ATFormer: A Learned Performance Model with Transfer Learning Across Devices for Deep Learning Tensor Programs (2023.emnlp-main)

Challenge:	Large Language Models (LLMs) are vulnerable to "jailbreaking" attacks where crafted prompts manipulate them into producing toxic content.
Approach:	They propose to improve the target loss objective by combining a cosine decay schedule method with refusal suppression to achieve higher success rates.
Outcome:	The proposed approach outperforms baseline attacks and achieves state-of-the-art attack success rates.

Copied to clipboard

Yang Bai, Wenqian Zhao, Shuo Yin, Zixiao Wang, Bei Yu

Applying BERT to Document Retrieval with Birch (D19-3)

Challenge:	Compilation-based methods with performance models have poor measurement accuracy and transferability between platforms.
Approach:	They propose a compiler that automatically generates tensors and automatically tunes them for different hardware platforms.
Outcome:	The proposed model reduces inference time and costs on modern DNN benchmarks.

Copied to clipboard

Zeynep Akkalyoncu Yilmaz, Shengjin Wang, Wei Yang, Haotian Zhang, Jimmy Lin

Learning to Plan for Retrieval-Augmented Large Language Models from Knowledge Graphs (2024.findings-emnlp)

Challenge:	Birch is an open-source document retrieval system that integrates with the Anserini information retrieval toolkit to demonstrate end-to-end search over large document collections.
Approach:	They propose to integrate Anserini with a BERT-based document ranking model that provides an end-to-end open-source search engine.
Outcome:	The proposed system outperforms existing approaches to document retrieval and question answering on standard newswire and social media test collections.

Copied to clipboard

Junjie Wang, Mingyang Chen, Binbin Hu, Dan Yang, Ziqi Liu, Yue Shen, Peng Wei, Zhiqiang Zhang, Jinjie Gu, Jun Zhou, Jeff Pan, Wen Zhang, Huajun Chen

BMRetriever: Tuning Large Language Models as Better Biomedical Text Retrievers (2024.emnlp-main)

Challenge:	Recent studies have attempted to enhance the performance of large language models (LLMs) in complex question-answering (QA) tasks by combining step-wise planning with external retrieval.
Approach:	They propose a framework for enhancing LLMs’ planning capabilities by using planning data derived from knowledge graphs (KGs).
Outcome:	The proposed framework improves LLMs’ planning capabilities by using knowledge graphs (KGs) the proposed framework is compared with existing frameworks on multiple datasets and shows that it is effective for large language models.

Copied to clipboard

Ran Xu, Wenqi Shi, Yue Yu, Yuchen Zhuang, Yanqiao Zhu, May Dongmei Wang, Joyce Ho, Chao Zhang, Carl Yang

From Local to Global: Revisiting Structured Pruning Paradigms for Large Language Models (2026.acl-long)

Challenge:	Developing effective biomedical retrieval models is important for excelling at knowledge-intensive biomedically tasks but still challenging due to the lack of sufficient publicly annotated biomedic data and computational resources.
Approach:	They propose a series of dense retrievers for enhancing biomedical retrieval via unsupervised pre-training on large biomedically corpora, followed by instruction fine-tuning on a combination of labeled datasets and synthetic pairs.
Outcome:	Experiments on 5 biomedical tasks across 11 datasets confirm the performance of the retrieval model on various biomedically demanding tasks.

Copied to clipboard

Ziyan Wang, Enmao Diao, Qi Le, Pu Wang, Minwoo Lee, Shu-ping Yeh, Evgeny Stupachenko, Hao Feng, Li Yang

Knowledge-Augmented Multimodal Clinical Rationale Generation for Disease Diagnosis with Small Language Models (2025.acl-long)

Challenge:	Structured pruning is a practical approach to deploying large language models (LLMs) but it fails to capitalize on modest task-specific calibration signals, causing limited downstream gains.
Approach:	They propose a method that removes attention heads and MLP channels using loss-based important scores . they use perplexity for language modeling and a margin-based objective for decision-style tasks .
Outcome:	The proposed method lowers perplexity and improves accuracy at higher sparsity . it also stabilizes accuracy and mitigates perxity collapse without fine-tuning .

Copied to clipboard

Shuai Niu, Jing Ma, Hongzhan Lin, Liang Bai, Zhihua Wang, Richard Yi Da Xu, Yunya Song, Xian Yang

Make Some Noise: Unlocking Language Model Parallel Inference Capability through Noisy Training (2024.emnlp-main)

Challenge:	Existing models struggle to balance predictive accuracy with human-understandable rationales.
Approach:	They propose to enhance LLMs by leveraging rationale distillation and domain knowledge injection for trustworthy multimodal rationale generation.
Outcome:	Experiments on real-world medical datasets show that ClinRaGen achieves state-of-the-art performance in disease diagnosis and rationale generation.

Copied to clipboard

Yixuan Wang, Xianzhen Luo, Fuxuan Wei, Yijun Liu, Qingfu Zhu, Xuanyu Zhang, Qing Yang, Dongliang Xu, Wanxiang Che

CRPO: Confidence-Reward Driven Preference Optimization for Machine Translation (2025.findings-acl)

Challenge:	Existing speculative decoding methods require additional model structure and training processes to assist the model for draft token generation.
Approach:	They propose a make some noise training framework that introduces some noise at the input for the model to learn the denoising task.
Outcome:	The proposed model improves inference speed by 2.3-2.7x times without compromising model performance.

Copied to clipboard

Guofeng Cui, Pichao Wang, Yang Liu, Zemian Ke, Zhu Liu, Vimal Bhat

Knowledge-Empowered Representation Learning for Chinese Medical Reading Comprehension: Task, Model and Resources (2021.findings-acl)

Challenge:	Large language models (LLMs) have shown great potential in natural language processing tasks, but their application to machine translation remains challenging due to pretraining on predominantly English-centric datasets.
Approach:	They propose a method that combines reward scores with model confidence to improve model selection for fine-tuning.
Outcome:	The proposed method outperforms existing methods in translation accuracy and data efficiency.

Copied to clipboard

Taolin Zhang, Chengyu Wang, Minghui Qiu, Bite Yang, Zerui Cai, Xiaofeng He, Jun Huang

Learn Like Humans: Use Meta-cognitive Reflection for Efficient Self-Improvement (2026.acl-long)

Challenge:	MRC is a popular task in NLP, aiming to understand a passage and answer the relevant questions.
Approach:	They propose a multi-target machine learning task for the medical domain that predicts answers to medical questions and corresponding support sentences from medical information sources simultaneously.
Outcome:	The proposed model outperforms baselines by fusing context-aware and knowledge-awful token representations.

Copied to clipboard

Xinmeng Hou, Bohao Qu, Wuqi Wang, Peiliang Gong, Qing Guo, Yang Liu

Perplexity-Aware Data Scaling Law: Perplexity Landscapes Predict Performance for Continual Pre-training (2026.acl-long)

Challenge:	Existing self-improving frameworks rely on inefficient, multi-turn recursive loops that incur high computational costs.
Approach:	They propose a framework that achieves efficient self-evolution within a single recurrence cycle.
Outcome:	The proposed framework outperforms state-of-the-art self-evolving systems while significantly reducing computational overhead.

Copied to clipboard

Lei Liu, Hao Zhu, Xiaoyan Yang, Yue Shen, Zhixuan Chu, Jian Wang, Jinjie Gu, Kui Ren

Self-Renewal Prompt Optimizing with Implicit Reasoning (2024.findings-emnlp)

Challenge:	Large language models (LLMs) have impressive capabilities across a wide range of domains, but their generalpurpose pre-training objectives often leave them illsuited for specialized applications such as healthcare.
Approach:	They propose a perplexity-aware data scaling law that establishes a predictive relationship between the perplexities of domain-specific data and the test loss.
Outcome:	Experiments on medical and general-domain benchmarks show that the proposed scaling law consistently identifies near-optimal training subsets with significantly reduced data consumption.

Copied to clipboard

Zihan Liang, Ben Chen, Zhuoran Ran, Zihan Wang, Huangyu Dai, Yufei Ma, Dehong Gao, Xiaoyan Cai, Libin Yang

X-Instruction: Aligning Language Model in Low-resource Languages with Self-curated Cross-lingual Instructions (2024.findings-acl)

Challenge:	Recent advances in NLP have been driven by the development of Large Language Models (LLMs).
Approach:	They propose a self-renewal approach to optimize LLM outputs to better align with human preferences without supervised fine-tuning.
Outcome:	The proposed approach improves outputs to better align with human preferences across LLMs and tasks without supervised fine-tuning.

Copied to clipboard

Chong Li, Wen Yang, Jiajun Zhang, Jinliang Lu, Shaonan Wang, Chengqing Zong

An Evaluation Resource for Grounding Translation Errors (2025.findings-emnlp)

Challenge:	Large language models respond well in high-resource languages but struggle in low-resourced languages.
Approach:	They propose a method to construct cross-lingual instruction following samples with instruction in English and response in low-resource languages.
Outcome:	The proposed method builds a large-scale cross-lingual instruction tuning dataset on 10 languages.

Copied to clipboard

Sujin Chen, Kang Wang, Zixuan Zhou, Xiangyu Duan, Wanqun Zhang, Hao Yang, Jinsong Su, Min Zhang

Interpreting Twitter User Geolocation (2020.acl-main)

Challenge:	Current fine-grained error analyses do not ground the errors to the reasons why the annotated text spans are erroneous.
Approach:	They use a bi-directional grounding scheme to ground erroneous text in two directions . if the error spans of both directions are consistent, the explanation is valid .
Outcome:	The proposed grounding process improves translation error detection significantly.

Copied to clipboard

Ting Zhong, Tianliang Wang, Fan Zhou, Goce Trajcevski, Kunpeng Zhang, Yi Yang

Z-Code++: A Pre-trained Language Model Optimized for Abstractive Summarization (2023.acl-long)

Challenge:	Existing methods for identifying user geolocation suffer from a lack of interpretability on the corresponding results.
Approach:	They adopt influence functions to interpret the behavior of GNN-based models by identifying the importance of training users when predicting locations.
Outcome:	The proposed method provides meaningful explanations on prediction results and also uncovers the so-called "black-box" GNN-based models by investigating the effect of individual nodes.

Copied to clipboard

Pengcheng He, Baolin Peng, Song Wang, Yang Liu, Ruochen Xu, Hany Hassan, Yu Shi, Chenguang Zhu, Wayne Xiong, Michael Zeng, Jianfeng Gao, Xuedong Huang

PersonaBench: Evaluating AI Models on Understanding Personal Information through Accessing (Synthetic) Private User Data (2025.findings-acl)

Challenge:	Z-Code++ is a pre-trained language model optimized for abstractive text summarization.
Approach:	They propose a pre-trained language model optimized for abstractive text summarization that uses a two-phase pre-training technique to improve model's performance.
Outcome:	The proposed model outperforms the competing models on low-resource summarization tasks in zero-shot and few-shot settings.

Copied to clipboard

Juntao Tan, Liangwei Yang, Zuxin Liu, Zhiwei Liu, Rithesh R N, Tulika Manoj Awalgaonkar, Jianguo Zhang, Weiran Yao, Ming Zhu, Shirley Kokane, Silvio Savarese, Huan Wang, Caiming Xiong, Shelby Heinecke

Out-of-Domain Detection for Low-Resource Text Classification Tasks (D19-1)

Challenge:	Existing research lacks direct access to such data, making benchmarking difficult due to privacy concerns.
Approach:	They propose a synthetic data pipeline that generates realistic user profiles and private documents and a benchmark to evaluate models' ability to understand personal information.
Outcome:	The proposed pipeline generates realistic user profiles and private documents, enabling PersonaBench, a benchmark for evaluating models’ ability to understand personal information.

Copied to clipboard

Ming Tan, Yang Yu, Haoyu Wang, Dakuo Wang, Saloni Potdar, Shiyu Chang, Mo Yu

EVM-QuestBench: An Execution-Grounded Benchmark for Natural-Language Transaction Code Generation (2026.acl-long)

Challenge:	Existing methods for OOD detection and ID classification tasks require massive amounts of ID labeled data and no OOD labeles.
Approach:	They propose to use OOD-resistant Prototypical Network to detect OOD cases with limited in-domain (ID) training data to solve this task.
Outcome:	The proposed solution outperforms state-of-the-art methods in zero-shot OOD detection task while maintaining a competitive performance on ID classification task.

Copied to clipboard

Pei Yang, Wanyi Chen, Ke Wang, Lynn Ai, Eric Yang, Tianyu Shi

Title2Event: Benchmarking Open Event Extraction with a Large-scale Chinese Title Dataset (2022.emnlp-main)

Challenge:	Existing evaluations of large language models overlook execution accuracy and safety.
Approach:	They propose an execution-grounded benchmark for natural-language transaction-script generation on EVM-compatible chains.
Outcome:	The proposed benchmark finds large performance gaps in the models with 5 independent rounds.

Copied to clipboard

Haolin Deng, Yanan Zhang, Yangfan Zhang, Wangyang Ying, Changlong Yu, Jun Gao, Wei Wang, Xiaoling Bai, Nan Yang, Jin Ma, Xiang Chen, Tianhua Zhou

Are AI-Generated Text Detectors Robust to Adversarial Perturbations? (2024.acl-long)

Challenge:	Existing EE datasets define fixed event types and design specific schemas for each of them, failing to cover diverse events emerging from the online text.
Approach:	They propose to use a sentence-level dataset to benchmark Open Event Extraction without restricting event types.
Outcome:	The proposed dataset contains more than 42,000 news titles in 34 topics collected from Chinese web pages.

Copied to clipboard

Guanhua Huang, Yuchen Zhang, Zhe Li, Yongjian You, Mingze Wang, Zhouwang Yang

Towards Unified Prompt Tuning for Few-shot Text Classification (2022.findings-emnlp)

Challenge:	Existing detectors for AI-generated text lack robustness against adversarial perturbations, with even minor changes in characters or words causing a reversal in distinguishing between human-created and AI-generated text.
Approach:	They propose a siamese calibration technique to train the model to make equally confident predictions under different noise, which improves the model’s robustness against adversarial perturbations.
Outcome:	The proposed detector outperforms baseline methods on four datasets and is more generalizable in cross-domain, cross-genre, and mixed-source scenarios.

Copied to clipboard

Jianing Wang, Chengyu Wang, Fuli Luo, Chuanqi Tan, Minghui Qiu, Fei Yang, Qiuhui Shi, Songfang Huang, Ming Gao

Prompt Space Optimizing Few-shot Reasoning Success with Large Language Models (2024.findings-naacl)

Challenge:	Prompt-based fine-tuning has boosted performance of Pre-trained Language Models (PLMs) on few-shot text classification, but PLMs are unfamiliar with prompt-style expressions during pre-training, which limits the few- shot learning performance on downstream tasks.
Approach:	They propose a framework for prompt-based fine-tuning that captures prompting semantics from non-target NLP datasets and propose 'Prompt-Options-Verbalizer' for joint prompt learning across different NLP tasks.
Outcome:	Experiments show that the proposed framework outperforms state-of-the-art prompt-based fine-tuning frameworks on few-shot text classification tasks.

Copied to clipboard

Fobo Shi, Peijun Qing, Dong Yang, Nan Wang, Youbo Lei, Haonan Lu, Xiaodong Lin, Duantengchuan Li

Retrieval Augmented Fact Verification by Synthesizing Contrastive Arguments (2024.acl-long)

Challenge:	Prompt engineering is an essential technique for enhancing the abilities of large language models (LLMs) by providing explicit and specific instructions.
Approach:	They propose a new approach that uses text embeddings to obtain basis vectors by matrix decomposition and constructs a space for representing all prompts.
Outcome:	The proposed approach significantly outperforms state-of-the-art prompt paradigms on ten public reasoning benchmarks.

Copied to clipboard

Zhenrui Yue, Huimin Zeng, Lanyu Shang, Yifan Liu, Yang Zhang, Dong Wang

Hephaestus: Improving Fundamental Agent Capabilities of Large Language Models through Continual Pre-Training (2025.naacl-long)

Challenge:	Existing methods to verify claim credibility rely on embedded knowledge or unreliable context.
Approach:	They propose retrieval augmented fact verification through the synthesis of contrasting arguments (RAFTS) they use an embedding model to identify informative demonstrations and in-context prompts to generate the prediction and explanation.
Outcome:	The proposed method outperforms existing methods with smaller LLMs or unreliable contexts.

Copied to clipboard

Yuchen Zhuang, Jingfeng Yang, Haoming Jiang, Xin Liu, Kewei Cheng, Sanket Lokegaonkar, Yifan Gao, Qing Ping, Tianyi Liu, Binxuan Huang, Zheng Li, Zhengyang Wang, Pei Chen, Ruijie Wang, Rongzhi Zhang, Nasser Zalmout, Priyanka Nigam, Bing Yin, Chao Zhang

Incomplete In-context Learning (2026.acl-long)

Challenge:	Existing LLMs often rely on complex prompting or extensive fine-tuning to introduce new capabilities while preserving strong generalizability.
Approach:	They propose a large-scale pre-training corpus to enhance LLM agents' capabilities . they use 103B agent-specific data encompassing 76,537 APIs .
Outcome:	The proposed training corpus outperforms open-source LLMs and commercial LLM agents on three agent benchmarks.

Copied to clipboard

Wenqiang Wang, Wen Yujia, Yan Xiao, Zhifeng Chen, Yangshijie Zhang, Peng Chen, Mingbo Yang, Xiaochun Cao

ConKI: Contrastive Knowledge Injection for Multimodal Sentiment Analysis (2023.findings-acl)

Challenge:	Existing in-context learning assumes the retrieval dataset contains demonstrations for all output label spaces.
Approach:	They propose a framework with train-free and train-based variants to address IICL . they propose to integrate a dataset with labeled demonstrations for each output space .
Outcome:	The proposed framework outperforms existing methods under incomplete retrieval datasets and even outperformed ICL with complete labels.

Copied to clipboard

Yakun Yu, Mingjun Zhao, Shi-ang Qi, Feiran Sun, Baoxun Wang, Weidong Guo, Xiaoli Wang, Lei Yang, Di Niu

Analyzing Chain-of-thought Prompting in Black-Box Large Language Models via Estimated V-information (2024.lrec-main)

Challenge:	Existing methods for multimodal sentiment analysis focus on general knowledge, which is inadequate to identify specific sentiments across modalities.
Approach:	They propose a method where specific-knowledge representations for each modality can be learned together with general knowledge representations via knowledge injection based on an adapter architecture.
Outcome:	The proposed method outperforms all prior methods on three popular benchmarks on multimodal sentiment analysis metrics.

Copied to clipboard

Zecheng Wang, Chunshan Li, Zhao Yang, Qingbin Liu, Yanchao Hao, Xi Chen, Dianhui Chu, Dianbo Sui

Modeling Temporal-Modal Entity Graph for Procedural Multimodal Machine Comprehension (2022.acl-long)

Challenge:	Chain-of-Thought (CoT) prompting and large language models (LLMs) have shown great potential in improving performance on challenging reasoning tasks.
Approach:	They propose a new metric which extends the concept of pointwise V-information to black-box models and quantifies label-relevant new information introduced by CoT prompting.
Outcome:	The proposed metric extends the concept of pointwise V-information to black-box models, quantifying label-relevant new information introduced by CoT prompting beyond pre-existing label information.

Copied to clipboard

Huibin Zhang, Zhengkun Zhang, Yao Zhang, Jun Wang, Yufan Li, Ning Jiang, Xin Wei, Zhenglu Yang

FineCops-Ref: A new Dataset and Task for Fine-Grained Compositional Referring Expression Comprehension (2024.emnlp-main)

Challenge:	Procedural Multimodal Documents organize textual instructions and corresponding images step by step.
Approach:	They propose a novel temporal-modal entity Graph for comprehending PMDs . they propose encoding and reasoning modules to capture textual and visual entities .
Outcome:	The proposed model can capture textual and visual entities and trace their temporal-modal evolution.

Copied to clipboard

Junzhuo Liu, Xuzheng Yang, Weiwei Li, Peng Wang

CreativeBench: Benchmarking and Enhancing Machine Creativity via Self-Evolving Challenges (2026.findings-acl)

Challenge:	Referring Expression Comprehension (REC) is a cross-modal task that objectively evaluates the capabilities of language understanding, image comprehension, and language-to-image grounding.
Approach:	They propose to use a new reference expression comprehension (REC) dataset to evaluate the capabilities of language understanding, image comprehension, and language-to-image grounding.
Outcome:	The proposed model is able to reject scenarios where the target object is not visible in the image, a key aspect often overlooked in existing models and approaches.

Copied to clipboard

Zihan Wang, Lam Nguyen, Zhengyang Zhao, Mengyue Yang, Chengwei Qin, Yujiu Yang, Linyi Yang

Challenge:	Increasing saturation of web data limits further scaling of model intelligence.
Approach:	They propose a benchmark to evaluate machine creativity in code generation that combines combinatorial and exploratory creativity through reverse engineering and self-play.
Outcome:	The proposed benchmark targets combinatorial and exploratory creativity through reverse engineering and self-play.

When Inverse Data Outperforms: Exploring the Pitfalls of Mixed Data in Multi-Stage Fine-Tuning (2025.findings-emnlp)

Copied to clipboard

Mengyi Deng, Xin Li, Tingyu Zhu, Zhicheng Yang, Zhijiang Guo, Wei Wang

Learning a Multi-Domain Curriculum for Neural Machine Translation (2020.acl-main)

Challenge:	Existing methods for o1-level performance focus on unidirectional supervised fine-tuning (SFT), overlooking the intricate interplay between diverse reasoning patterns.
Approach:	They construct a reverse reasoning dataset and examine how it is supervised . they find that naively mixing forward and reverse data during SFT weakens the directional distinction .
Outcome:	The proposed model improves accuracy by 1.6%–6.8% over a standard model.

Copied to clipboard

Wei Wang, Ye Tian, Jiquan Ngiam, Yinfei Yang, Isaac Caswell, Zarana Parekh

AgenticEval: Toward Agentic and Self-Evolving Safety Evaluation of Large Language Models (2026.findings-acl)

Challenge:	Existing data selection methods do not work well for multiple domains . multiple aspects need to be considered for training a multi-domain model .
Approach:	They propose a dynamic data selection method to multi-domain NMT that incorporates instance-level domain-relevance features and a curriculum to gradually focus on multi- domain relevant data batches.
Outcome:	The proposed model outperforms no-curriculum training on multiple domains and reaches or outperformed individual performance.

Copied to clipboard

Yixu Wang, Xin Wang, Yang Yao, Xinyuan Li, Xibang Yang, Yan Teng, Xingjun Ma, Yingchun Wang

RealChart2Code: Bridging the Gap in Real-World Chart-to-Code Generation via Multi-Task Evaluation (2026.acl-long)

Challenge:	Existing static safety evaluation methods are ill-equipped to address dynamic nature of AI risks and evolving regulations, creating a critical safety gap.
Approach:	They propose a new paradigm of agentic safety evaluation reframing evaluation as a continuous and self-evolving process rather than a one-time audit.
Outcome:	The proposed framework shows a consistent decline in model safety as the evaluation hardens.

Copied to clipboard

Jiajun Zhang, Yuying Li, Zhixun Li, Xingyu Guo, Jingzhuo Wu, Leqi Zheng, Yiran Yang, Jianke Zhang, Qingbin Li, Shannan Yan, Changguo Jia, Junfei Wu, Zilei Wang, Qiang Liu, Liang Wang

EHRAgent: Code Empowers Large Language Models for Few-shot Complex Tabular Reasoning on Electronic Health Records (2024.emnlp-main)

Challenge:	Vision-Language Models (VLMs) have demonstrated impressive capabilities in code generation across various domains, but their ability to replicate complex, multi-panel visualizations remains largely unassessed.
Approach:	They propose a large-scale benchmark to evaluate chart generation from large- scale raw data and assess iterative code refinement in a multi-turn conversational setting.
Outcome:	The new benchmark evaluates 14 leading VLMs on real-world data and shows they struggle with complex plot structures and authentic data.

Copied to clipboard

Wenqi Shi, Ran Xu, Yuchen Zhuang, Yue Yu, Jieyu Zhang, Hang Wu, Yuanda Zhu, Joyce Ho, Carl Yang, May Dongmei Wang

CPL: Counterfactual Prompt Learning for Vision and Language Models (2022.emnlp-main)

Challenge:	EHRAgent enables clinicians to interact with EHRs using natural language . reliance on rule-based conversion systems often necessitates additional training or effort from data engineers.
Approach:	They propose a large language model agent that generates and executes code in natural language to facilitate clinicians in directly interacting with EHRs.
Outcome:	The proposed agent outperforms the strongest baseline by up to 29.6% in success rate on three real-world EHR datasets.

Copied to clipboard

Xuehai He, Diji Yang, Weixi Feng, Tsu-Jui Fu, Arjun Akula, Varun Jampani, Pradyumna Narayana, Sugato Basu, William Yang Wang, Xin Wang

Exploiting Emotion-Semantic Correlations for Empathetic Response Generation (2023.findings-emnlp)

Challenge:	Existing prompt tuning methods tend to learn spurious or entangled representations, leading to poor generalization to unseen concepts.
Approach:	They propose a prompt tuning technique that tunes the learnable prompt for pre-trained vision and language models.
Outcome:	The proposed method improves few-shot performance on vision and language tasks over existing prompt tuning methods.

Copied to clipboard

Zhou Yang, Zhaochun Ren, Wang Yufeng, Xiaofei Zhu, Zhihao Chen, Tiecheng Cai, Wu Yunbing, Yisong Su, Sibo Ju, Xiangwen Liao

Muffin or Chihuahua? Challenging Multimodal Large Language Models with Multipanel VQA (2024.acl-long)

Challenge:	Empathetic response generation aims to generate empathetic responses by understanding the speaker’s emotional feelings from the language of dialogue.
Approach:	They propose a dynamical Emotion-Semantic Correlation Model (ESCM) which constructs dynamic emotion-semantics through the interaction of context and emotions.
Outcome:	The proposed model understands emotions more accurately and expresses fluent and informative empathetic responses.

Copied to clipboard

Yue Fan, Jing Gu, Kaiwen Zhou, Qianqi Yan, Shan Jiang, Ching-Chen Kuo, Yang Zhao, Xinze Guan, Xin Wang

Modeling Recurrence for Transformer (N19-1)

Challenge:	Multipanel images are a common form of visual representations, and humans can achieve approximately 99% accuracy on these questions.
Approach:	They propose a benchmark that tests multipanel visual reasoning models with 6,600 triplets of questions, answers, and multipanel images.
Outcome:	The proposed benchmark features 6,600 triplets of questions, answers, and multipanel images that challenge state-of-the-art Multimodal Large Language Models (MLLMs) human users can attain approximately 99% accuracy on these questions, compared with previous benchmarks.

Copied to clipboard

Jie Hao, Xing Wang, Baosong Yang, Longyue Wang, Jinfeng Zhang, Zhaopeng Tu

Texar: A Modularized, Versatile, and Extensible Toolkit for Text Generation (P19-3)

Challenge:	Existing studies show that the lack of recurrence modeling hinders the development of a translation model.
Approach:	They propose to model recurrence for Transformer with an additional recurrent encoder.
Outcome:	The proposed model outperforms the deep model on EnglishGerman and ChineseEnglish translation tasks.

Copied to clipboard

Zhiting Hu, Haoran Shi, Bowen Tan, Wentao Wang, Zichao Yang, Tiancheng Zhao, Junxian He, Lianhui Qin, Di Wang, Xuezhe Ma, Zhengzhong Liu, Xiaodan Liang, Wanrong Zhu, Devendra Sachan, Eric Xing

Curriculum Pre-training for End-to-End Speech Translation (2020.acl-main)

Challenge:	Texar is an open-source text generation toolkit that supports a broad set of text generation tasks.
Approach:	They introduce Texar, an open-source text generation toolkit that supports text generation tasks.
Outcome:	Texar supports machine translation, summarization, dialog, content manipulation, and more.

Copied to clipboard

Chengyi Wang, Yu Wu, Shujie Liu, Ming Zhou, Zhenglu Yang

Modeling Adversarial Attack on Pre-trained Language Models as Sequential Decision Making (2023.findings-acl)

Challenge:	End-to-end speech translation requires a powerful encoder to transcribe, understand and learn cross-lingual semantics simultaneously.
Approach:	They propose a curriculum pre-training method that includes an elementary course for transcription learning and two advanced courses for understanding the utterance and mapping words in two languages.
Outcome:	The proposed method improves on En-De and En-Fr speech translation benchmarks.

Copied to clipboard

Xuanjie Fang, Sijie Cheng, Yang Liu, Wei Wang

Consolidation or Adaptation? PRISM: Disentangling SFT and RL Data via Gradient Concentration (2026.acl-long)

Challenge:	Pre-trained language models (PLMs) have shown strong potential in various downstream tasks.
Approach:	They propose to model adversarial attack task as a sequential decision-making problem where the whole attack process is sequential with two decision- making problems, i.e., word finder and word substitution.
Outcome:	The proposed approach achieves the highest attack success rate with a comparable modification rate and semantic similarity to attack fine-tuned BERT.

Copied to clipboard

Yang Zhao, Yangou Ouyang, Xiao Ding, Hepeng Wang, Bibo Cai, Kai Xiong, Jinglong Gao, Zhouhao Sun, Li Du, Bing Qin, Ting Liu

ImPart: Importance-Aware Delta-Sparsification for Improved Model Compression and Merging in LLMs (2025.acl-long)

Challenge:	Existing data arbitration strategies for large language model training rely on surface-level heuristics that fail to diagnose intrinsic learning needs.
Approach:	They propose a framework that arbitrates data based on its degree of cognitive conflict with the model's existing knowledge.
Outcome:	Extensive experiments on WebShop and ALFWorld show that PRISM outperforms state-of-the-art hybrid methods while reducing computational costs by up to 3.22 .

Copied to clipboard

Yan Yang, Yixia Li, Hongru Wang, Xuetao Wei, James Jianqiao Yu, Yun Chen, Guanhua Chen

Improving Knowledge Graph Embedding Using Affine Transformations of Entities Corresponding to Each Relation (2021.findings-emnlp)

Challenge:	Recent approaches to reduce resource requirements for task-specific large language models have been developed.
Approach:	They propose a delta compression approach that optimizes for importance of a model . they use SVD to dynamically adjust the sparsity ratios of different vectors based on their importance .
Outcome:	The proposed approach achieves state-of-the-art in retaining task-specific knowledge even at high sparsity ratios.

Copied to clipboard

Jinfa Yang, Yongjie Shi, Xin Tong, Robin Wang, Taiyan Chen, Xianghua Ying

Representation Potentials of Foundation Models for Multimodal Alignment: A Survey (2025.emnlp-main)

Challenge:	Existing knowledge graph embedding methods use k-dimensional vectors to represent each entity in a knowledge graph.
Approach:	They propose to use affine transformations to embed knowledge graphs using previous methods . they propose to add k additional variables to the existing methods to perform embedding .
Outcome:	The proposed method outperforms RotatE, Distmult and ComplEx on various data sets.

Copied to clipboard

Jianglin Lu, Hailing Wang, Yi Xu, Yizhou Wang, Kuo Yang, Yun Fu

Improving Back-Translation with Uncertainty-based Confidence Estimation (D19-1)

Challenge:	foundation models learn highly transferable representations through large-scale pretraining on diverse data.
Approach:	They examine the representation potentials of foundation models by examining their latent capacity to capture task-specific information within a single modality while providing a transferable basis for alignment and unification across modalities.
Outcome:	The foundation models exhibit remarkable similarities across architectures and modalities, the authors show . the models can capture task-specific information within a single modality while providing a transferable basis for alignment and unification across modality.

Copied to clipboard

Shuo Wang, Yang Liu, Chao Wang, Huanbo Luan, Maosong Sun

Rethinking Multi-Modal Alignment in Multi-Choice VideoQA from Feature and Sample Perspectives (2022.emnlp-main)

Challenge:	Despite the success of low-resource neural machine translation, there is a data scarcity problem in many languages . large-scale, high-quality, and widecoverage bilingual corpora do not exist for most language pairs .
Approach:	They propose to quantify confidence of NMT models based on model uncertainty . they propose to use uncertainty-based confidence measures to improve back-translation .
Outcome:	The proposed model outperforms conventional statistical machine translation (SMT) on Chinese-English and English-German translation tasks.

Copied to clipboard

Shaoning Xiao, Long Chen, Kaifeng Gao, Zhao Wang, Yi Yang, Zhimeng Zhang, Jun Xiao

Bayesian Example Selection Improves In-Context Learning for Speech, Text and Visual Modalities (2024.emnlp-main)

Challenge:	Existing approaches to VideoQA focus on utilizing frame- or object-level visual representations, but they neglect visual-language interactions.
Approach:	They propose to break down video into trajectories and first leverage trajectory feature in VideoQA to enhance alignment between two modalities.
Outcome:	The proposed method outperforms all the state-of-the-art models on the NExT-QA benchmark.

Copied to clipboard

Siyin Wang, Chao-Han Yang, Ji Wu, Chao Zhang

Sentence-Level Agreement for Neural Machine Translation (P19-1)

Challenge:	Large language models (LLMs) can adapt to new tasks easily and efficiently in a training-free manner.
Approach:	They propose to use eBayesian in-context example selection method to extend the inference probability conditioned on in-constitut examples based on Bayes’ theorem to select in-strategy examples . Experimental results show the efficacy and robustness of their method on various models, tasks and modalities.
Outcome:	The proposed method is based on the eBayesian in-context example selection approach.

Copied to clipboard

Mingming Yang, Rui Wang, Kehai Chen, Masao Utiyama, Eiichiro Sumita, Min Zhang, Tiejun Zhao

Direct Value Optimization: Improving Chain-of-Thought Reasoning in LLMs with Refined Values (2025.emnlp-main)

Challenge:	Empirical results show that a sentence-level agreement module can significantly improve the performance of neural machine translation (NMT)
Approach:	They propose a sentence-level agreement module to minimize the difference between the representation of source and target sentences.
Outcome:	Empirical results show the proposed agreement module significantly improves translation performance.

Copied to clipboard

Hongbo Zhang, Han Cui, Guangsheng Bao, Linyi Yang, Jun Wang, Yue Zhang

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM𝛥 Integration into Upcycled MoE (2026.acl-long)

Challenge:	Existing offline preference optimization methods rely on preference labels to optimize large language models.
Approach:	They propose an offline method for enhancing large language models in reasoning tasks that utilizes value signals at individual reasoning steps.
Outcome:	The proposed framework outperforms offline preference optimization techniques by 4% to 6% on math reasoning, commonsense reasoning, and coding tasks.

Copied to clipboard

Hao Zhou, Tianhao Li, Zhijun Wang, Shuaijie She, Linjuan Wu, Hao-Ran Wei, Baosong Yang, Jiajun Chen, Shujian Huang

E-ConvRec: A Large-Scale Conversational Recommendation Dataset for E-Commerce Customer Service (2022.lrec-1)

Challenge:	Large Language Models (LLMs) are expensive and require extensive Continued Pre-Training and data-intensive alignment to expand.
Approach:	They propose a method which upcycles a dense model into a Mixture-of-Experts architecture, allocating different experts to different languages.
Outcome:	Experiments show that the proposed model upcycles a dense model into a Mixture-of-Experts(MoE) architecture, allocating different experts to different languages.

Copied to clipboard

Meihuizi Jia, Ruixue Liu, Peiying Wang, Yang Song, Zexi Xi, Haobin Li, Xin Shen, Meng Chen, Jinhui Pang, Xiaodong He

A Multi-persona Framework for Argument Quality Assessment (2025.acl-long)

Challenge:	Recent research has focused on developing conversational recommendation system (CRS), which provides valuable recommendations to users through conversations.
Approach:	They construct an authentic Chinese dialogue dataset consisting of over 25k dialogues and 770k utterances, which contains user profile, product knowledge base, and multiple sequential real conversations between users and recommenders.
Outcome:	The proposed dataset contains user profile, product knowledge base, and multiple sequential real conversations between users and recommenders.

Copied to clipboard

Bojun Jin, Jianzhu Bao, Yufang Hou, Yang Sun, Yice Zhang, Huajie Wang, Bin Liang, Ruifeng Xu

Challenge:	Existing methods for argument quality assessment do not consider multi-perspective evaluation due to subjective nature of arguments.
Approach:	They propose a multi-persona framework for argument quality assessment that simulates diverse evaluator perspectives through large language models.
Outcome:	The proposed framework outperforms baselines while providing comprehensive multi-perspective rationales on IBM-Rank-30k and IBM-ArgQ-5.3kArgs datasets.

Knowledge Distillation based Contextual Relevance Matching for E-commerce Product Search (2022.emnlp-industry)

Copied to clipboard

Ziyang Liu, Chaokun Wang, Hao Feng, Lingfei Wu, Liqun Yang

Non-parallel Accent Transfer based on Fine-grained Controllable Accent Modelling (2023.findings-emnlp)

Challenge:	Existing approaches to e-commerce relevance matching ignore bipartite graphs in logs . experimental results show that proposed method improves human relevance judgment .
Approach:	They propose an efficient knowledge distillation framework for e-commerce relevance matching to exploit the advantages of Transformer-style and classical relevance matching models.
Outcome:	The proposed method significantly improves human relevance judgment on large-scale real-world data.

Copied to clipboard

Linqin Wang, Zhengtao Yu, Yuanzhang Yang, Shengxiang Gao, Cunli Mao, Yuxin Huang

Just Like a Human Would, Direct Access to Sarcasm Augmented with Potential Result and Reaction (2023.acl-long)

Challenge:	Existing accent transfer methods rely on parallel data or speech recognition models.
Approach:	They propose to use mutual information learning to disentangle accent features and control the accent of the generated speech during the inference time.
Outcome:	The proposed framework achieves superior performance to baseline models in accentedness and audio quality.

Copied to clipboard

Changrong Min, Ximing Li, Liang Yang, Zhilin Wang, Bo Xu, Hongfei Lin

SPPO: Sequence-Level PPO for Long-Horizon Reasoning Tasks (2026.acl-long)

Challenge:	sarcasm is a form of irony conveying mockery and contempt . social media has become increasingly popular for identifying sarcasm .
Approach:	They develop a method to detect sarcasm from social media using augmented potentials.
Outcome:	The proposed method outperforms baselines on benchmark datasets.

Copied to clipboard

Tianyi Wang, Yixia Li, Long Li, Yibiao Chen, Shaohan Huang, Yun Chen, Peng Li, Yang Liu, Guanhua Chen

Eliciting Implicit Acoustic Styles from Open-domain Instructions to Facilitate Fine-grained Controllable Generation of Speech (2025.emnlp-main)

Challenge:	Proximal Policy Optimization (PPO) is central to aligning Large Language Models with verifiable rewards.
Approach:	They propose a scalable algorithm that harmonizes sample efficiency with stability of outcome-based updates.
Outcome:	The proposed algorithm outperforms standard PPO and matches the performance of computation-heavy group-based methods.

Copied to clipboard

Jianxing Yu, Gou Zihao, Chen Li, Zhisheng Wang, Peiji Yang, Wenqing Chen, Jian Yin

Public Sentiment Drift Analysis Based on Hierarchical Variational Auto-encoder (2020.emnlp-main)

Challenge:	Current work relies on pre-defined rules or templates to control the style of speech.
Approach:	They propose to use open-domain instructions to generate speech with the acoustic style that meets users’ needs based on their instructions.
Outcome:	The proposed model can be used to generate speech with the acoustic style that meets users’ needs based on open-domain instructions.

Copied to clipboard

Wenyue Zhang, Xiaoli Li, Yang Li, Suge Wang, Deyu Li, Jian Liao, Jianxing Zheng

Do VLMs Have a Moral Backbone? A Study on the Fragile Morality of Vision-Language Models (2026.findings-acl)

Challenge:	Existing methods for detecting public sentiment drift are not designed for sentiment drift detection.
Approach:	They propose a Hierarchical Variational Auto-Encoder model to learn better distribution representation and a new drift measure to directly evaluate distribution changes between historical and new data.
Outcome:	The proposed model performs better than three existing state-of-the-art methods.

Copied to clipboard

Zhining Liu, Tianyi Wang, Xiao Lin, Penghao Ouyang, Gaotang Li, Ze Yang, Hui Liu, Sumit Keswani, Vishwa Pardeshi, Huijun Zhao, Wei Fan, Hanghang Tong

DAEA: Enhancing Entity Alignment in Real-World Knowledge Graphs Through Multi-Source Domain Adaptation (2025.coling-main)

Challenge:	Vision-Language Models (VLMs) have advanced multimodal learning, driving progress in cross-modal reasoning.
Approach:	They propose to examine moral robustness of vision-language models by analyzing their moral stances under multimodal perturbations.
Outcome:	The proposed model-agnostic multimodal perturbations expose VLMs to a variety of moral vulnerabilities, including a sycophancy trade-off where stronger instruction-following models are more susceptible to persuasion.

Copied to clipboard

Linyan Yang, Shiqiao Zhou, Jingwei Cheng, Fu Zhang, Jizheng Wan, Shuo Wang, Mark Lee

Revealing the Seen, Imagining the Beyond: A Survey of Image-Grounded Chain-of-Thought Reasoning in Multimodal LLMs (2026.acl-long)

Challenge:	Entity Alignment (EA) is a critical task in Knowledge Graph (KG) integration.
Approach:	They propose a novel approach that leverages the data characteristics of synthetic benchmarks to improve performance in real-world datasets.
Outcome:	The proposed approach outperforms state-of-the-art models on real-world datasets and achieves a 29.94% improvement in Hits@1 on DOREMUS and 5.64% improvement on AGROLD.

Copied to clipboard

Qihua Dong, Yitian Zhang, Huimin Zeng, Yizhou Wang, Jianglin Lu, Kuo Yang, Yun Fu

Towards Fine-Grained and Multi-Granular Contrastive Language-Speech Pre-training (2026.acl-long)

Challenge:	Recent advances in Multimodal Large Language Models (MLLMs) have shifted visual reasoning from tool-calling to end-to-end perceptionreasoning.
Approach:	They synthesize the emerging paradigm of Image-Grounded Chain-of-Thought (IG-CoT) they propose a method-centric taxonomy covering prompting, supervised fine-tuning, and reinforcement learning .
Outcome:	The proposed model is based on a method-centric taxonomy and benchmarks.

Copied to clipboard

Yifan Yang, Bing Han, Hui Wang, Wei Wang, Ziyang Ma, Long Zhou, Zengrui Jin, Guanrou Yang, Tianrui Wang, Xu Tan, Xie Chen

Enhancing Lexical Relation Mining with Structured Sememe Knowledge (2026.acl-long)

Challenge:	Existing models for fine-grained speaking styles are limited in terms of accuracy, coverage, and naturalness.
Approach:	They propose a model that pre-trains with coarse captions and annotates with a pipeline that grounds captions in audio.
Outcome:	The proposed model outperforms existing models with fine-grained style annotations . it integrates global and fine-granular supervision, enabling unified representations based on the proposed model .

Copied to clipboard

Hansi Wang, Qiliang Liang, Yue Wang, Yang Liu

Toward Better Loanword Identification in Uyghur Using Cross-lingual Word Embeddings (C18-1)

Challenge:	Existing top-performing methods for Lexical Relation Mining rely on pre-trained language models yet fail to distinguish nuanced lexical relations.
Approach:	They propose a framework to leverage structured sememe knowledge to enhance LRC and LE.
Outcome:	The proposed method outperforms existing methods on benchmarks and outperformed the LLMs.

Copied to clipboard

Chenggang Mi, Yating Yang, Lei Wang, Xi Zhou, Tonghai Jiang

MAssistant: A Personal Knowledge Assistant for MOOC Learners (D19-3)

Challenge:	Almost every natural language processing task suffers from data sparseness.
Approach:	They propose a method which identify loanwords in monolingual corpora by using cross-lingual word embeddings as core feature and a log-linear model which combines several shallow features to predict the final results.
Outcome:	The proposed method outperforms baseline models significantly on loanword identification and translation in four languages and eight translation directions.

Copied to clipboard

Lan Jiang, Shuhan Hu, Mingyu Huang, Zhichun Wang, Jinjian Yang, Xiaoju Ye, Wei Zheng

Z-LaVI: Zero-Shot Language Solver Fueled by Visual Imagination (2022.emnlp-main)

Challenge:	Massive Open Online Courses (MOOCs) have experienced a rapid development since 2012 . many MOOC platforms have been launched, including Coursera1 , edX2 , and Udacity3 etc.
Approach:	They present a personal knowledge assistant system called MAssistant for MOOC learners . MAsistants has a large-scale concept graph built from open data . it also provides a browser extension which interacts with users during video lectures .
Outcome:	The proposed system helps users trace the concepts they have learned in MOOCs, and to build their own concept graphs.

Copied to clipboard

Yue Yang, Wenlin Yao, Hongming Zhang, Xiaoyang Wang, Dong Yu, Jianshu Chen

A Sequence-to-Sequence Approach to Dialogue State Tracking (2021.acl-long)

Challenge:	Large-scale pretrained language models suffer from reporting bias, describing the lack of explicit commonsense knowledge in written text.
Approach:	They propose to endow language models with visual imagination capabilities by recalling existing images and synthesizing nonexistent images via text-to-image generation.
Outcome:	The proposed model improves the performance of existing language models across a diverse set of language tasks.

Copied to clipboard

Yue Feng, Yang Wang, Hang Li

FinMaster: A Holistic Benchmark for Full-Pipeline Financial Management with Large Language Models (2026.findings-acl)

Challenge:	Existing methods for dialogue state tracking are still challenging, but they are improving . a new approach to dialogue state monitoring is proposed, called Seq2Seq-DU .
Approach:	They propose a new dialogue state tracking module that formalizes DST as a sequence-to-sequence problem.
Outcome:	The proposed method outperforms existing methods on benchmark datasets in different settings.

Copied to clipboard

Junzhe Jiang, Chang Yang, Aixin Cui, Sihan Jin, Yujing Zhang, Yilin Xiao, Ruiyu Wang, Bo Li, Xiao Huang, Danny Dongning Sun, Xinrun Wang

PERM: Psychology-grounded Empathetic Reward Modeling for Large Language Models (2026.findings-acl)

Challenge:	Existing benchmarks lack domain-specific data, realistic workflow-level task design, and standardized workflow- level evaluation.
Approach:	a new benchmark evaluates large language models on financial management workflows . the global financial services market is projected to grow to $37 trillion by 2027 .
Outcome:	a new benchmark for large language models on financial management workflows reveals critical capability gaps . accuracy drops from 90% on basic tasks to 40% on complex scenarios requiring multi-step reasoning . the global financial services market reached $25.8 trillion in 2022 and is projected to grow to $37 trillion by 2027 .

Copied to clipboard

Chengbing Wang, Wuqiang Zheng, Yang Zhang, Fengbin Zhu, Junyi Cheng, Yi Xie, Wenjie Wang, Fuli Feng

Interactive Learning for LLM Reasoning (2026.findings-acl)

Challenge:	Existing reward models evaluate empathy from a single perspective, overlooking bidirectional interaction nature of empathy.
Approach:	They propose a reward model that evaluates empathy from a single perspective . they propose PERM to integrate a bystander perspective to monitor overall interaction quality .
Outcome:	a new reward model outperforms state-of-the-art models on an emotional intelligence benchmark and an industrial daily conversation dataset.

Copied to clipboard

Hehai Lin, Shilei Cao, Sudong Wang, Haotian Wu, Minzhi Li, Linyi Yang, Juepeng Zheng, Chengwei Qin

Understanding How Value Neurons Shape the Generation of Specified Values in LLMs (2025.findings-emnlp)

Challenge:	Existing multi-agent learning approaches foster collaboration among Large Language Models (LLMs) yet they still rely on re-executing the MAS during inference.
Approach:	They propose a co-learning framework that integrates Dynamic Interaction and Perception Calibration to enhance LLMs' independent problem-solving ability.
Outcome:	The proposed framework integrates Dynamic Interaction and Perception Calibration to improve LLMs' independent problem-solving ability.

Copied to clipboard

Yi Su, Jiayi Zhang, Shu Yang, Xinhai Wang, Lijie Hu, Di Wang

SciAssess: Benchmarking LLM Proficiency in Scientific Literature Analysis (2025.findings-naacl)

Challenge:	Current approaches to interpret value representations are limited by superficial judgments over mechanistic analysis.
Approach:	They propose a mechanistic interpretability framework that uses the Schwartz Values Survey to interpret value . they use a dataset that operationalizes four dimensions of universal value through behavioral contexts .
Outcome:	The proposed method bridges psychological value frameworks with neuron analysis in large language models.

Copied to clipboard

Hengxing Cai, Xiaochen Cai, Junhan Chang, Sihang Li, Lin Yao, Wang Changxin, Zhifeng Gao, Hongshuai Wang, Li Yongge, Mujie Lin, Shuwen Yang, Jiankun Wang, Mingjun Xu, Jin Huang, Xi Fang, Jiaxi Zhuang, Yuqi Yin, Yaqi Li, Changhong Chen, Zheng Cheng, Zifeng Zhao, Linfeng Zhang, Guolin Ke

Challenge:	Existing benchmarks fail to adequately evaluate the proficiency of Large Language Models (LLMs) Existing standards do not cover the skills needed to evaluate LLMs in scientific literature analysis.
Approach:	They propose a benchmark to evaluate the proficiency of large language models in scientific literature analysis.
Outcome:	SciAssess evaluates 11 LLMs on multiple tasks across scientific fields.

Copied to clipboard

Yang Zhao, Li Du, Xiao Ding, Yangou Ouyang, Hepeng Wang, Kai Xiong, Jinglong Gao, Zhouhao Sun, Dongliang Xu, Qing Yang, Dongchen Li, Bing Qin, Ting Liu

Self-Distillation Bridges Distribution Gap in Language Model Fine-Tuning (2024.acl-long)

Challenge:	Existing methods for selecting training data from general datasets fail to account for the joint distribution of instructions, resulting in inefficient learning and suboptimal knowledge transfer.
Approach:	They propose a method that constructs a mixed gradient-based instruction graph to capture the joint distribution and interdependencies among instructions.
Outcome:	The proposed method outperforms existing methods on domain adaptation tasks and in complex, data-scarce scenarios.

Copied to clipboard

Zhaorui Yang, Tianyu Pang, Haozhe Feng, Han Wang, Wei Chen, Minfeng Zhu, Qian Liu

DictLLM: Harnessing Key-Value Data Structures with Large Language Models for Enhanced Medical Diagnostics (2024.findings-acl)

Challenge:	Experimental results show that fine-tuning of large language models for specific tasks can be challenging . distribution shift during fine-timing can lead to performance degradation in general task capabilities .
Approach:	They propose a new approach that bridges the distribution gap between task datasets and LLMs by guiding fine-tuning with a distilled dataset generated by the model itself.
Outcome:	The proposed approach achieves comparable or superior performance on downstream tasks compared to the vanilla approach.

Copied to clipboard

YiQiu Guo, Yuchen Yang, Ya Zhang, Yu Wang, Yanfeng Wang

MMEvol: Empowering Multimodal Large Language Models with Evol-Instruct (2025.findings-acl)

Challenge:	Structured data processing is a complex and complex process.
Approach:	They propose a framework that captures heterogeneity of structured data using large language models . they propose group positional encoding, hierarchical attention bias and optimal transport alignment layer .
Outcome:	The proposed framework outperforms baseline methods and few-shot GPT-4 on a medical lab report dataset.

Copied to clipboard

Run Luo, Haonan Zhang, Longze Chen, Ting-En Lin, Xiong Liu, Yuchuan Wu, Min Yang, Yongbin Li, Minzheng Wang, Pengpeng Zeng, Lianli Gao, Heng Tao Shen, Yunshui Li, Hamid Alinejad-Rokny, Xiaobo Xia, Jingkuan Song, Fei Huang

VLFeedback: A Large-Scale AI Feedback Dataset for Large Vision-Language Models Alignment (2024.emnlp-main)

Challenge:	a new framework for image-text instruction data evolution improves MLLM performance . lack of high-quality instruction data remains a major bottleneck in ML modeling .
Approach:	They propose a multimodal instruction data evolution framework that iteratively enhances data quality through fine-grained perception, cognitive reasoning, and interaction evolution.
Outcome:	The proposed approach improves MLLM performance in nine vision-language tasks while using significantly less data.

Copied to clipboard

Lei Li, Zhihui Xie, Mukai Li, Shunian Chen, Peiyi Wang, Liang Chen, Yazheng Yang, Benyou Wang, Lingpeng Kong, Qi Liu

Putting Captions to the Test: Evaluating Video Caption Quality through Multiple-Choice Question Answering (2026.acl-long)

Challenge:	Large vision-language models (LVLMs) are evolving rapidly and require data with human supervision to achieve better alignment.
Approach:	They introduce VLFeedback, the first large-scale vision-language feedback dataset . they train Silkie, an LVLM fine-tuned via direct preference optimization .
Outcome:	The proposed model outperforms its base model in helpfulness, visual faithfulness, and safety metrics and exhibits enhanced resilience against red-teaming attacks.

Copied to clipboard

Zizhen Wang, Bo Feng, Zhengfeng Lai, Shiyu Li, Yang Lu, Meng Cao, Ping Huang, Xiaoming Simon Wang

Unveiling Internal Reasoning Modes in LLMs: A Deep Dive into Latent Reasoning vs. Factual Shortcuts with Attribute Rate Ratio (2025.emnlp-main)

Challenge:	Existing metrics for video captioning are based on text-based comparisons with ground-truth references.
Approach:	They propose a reference-free benchmark that assesses video captions based on their utility . they will release the benchmark to facilitate reproducible research .
Outcome:	The proposed benchmark improves on human-verified, fine-grained questions . it correlates significantly better with human judgments than existing metrics .

Copied to clipboard

Yiran Yang, Haifeng Sun, Jingyu Wang, Qi Qi, Zirui Zhuang, Huazheng Wang, Pengfei Ren, Jing Wang, Jianxin Liao

AnnaAgent: Dynamic Evolution Agent System with Multi-Session Memory for Realistic Seeker Simulation (2025.findings-acl)

Challenge:	Existing research in multi-hop questions has identified two reasoning modes, but has not investigated how these modes differ during inference.
Approach:	They propose a classification metric that compares latent reasoning and factual shortcuts in multi-hop questions.
Outcome:	The proposed metric achieves 90% accuracy on the proposed datasets and demonstrates effectiveness in RAG conflict scenarios.

Copied to clipboard

Ming Wang, Peidong Wang, Lin Wu, Xiaocui Yang, Daling Wang, Shi Feng, Yuxin Chen, Bixuan Wang, Yifei Zhang

CR-GIS: Improving Conversational Recommendation via Goal-aware Interest Sequence Modeling (2022.coling-1)

Challenge:	Existing models of seeker simulations are limited by the cost and ethical concerns of involving real seekers in mental health research.
Approach:	They propose an emotional and cognitive dynamic agent system equipped with tertiary memory to enable dynamic control of the simulator's configurations.
Outcome:	The proposed system achieves more realistic seeker simulation compared to baselines.

Copied to clipboard

Jinfeng Zhou, Bo Wang, Zhitong Yang, Dongming Zhao, Kun Huang, Ruifang He, Yuexian Hou

Browse and Concentrate: Comprehending Multimodal Content via Prior-LLM Context Fusion (2024.acl-long)

Challenge:	Existing methods to determine a goal item by sequentially tracking users’ interests ignore the rich goal-aware implicit interest sequence patterns in a dialog.
Approach:	They propose to model goal-aware implicit user interest sequence patterns in a dialog and a hierarchical Star Transformer to guide multi-turn utterances generation.
Outcome:	The proposed framework achieves more accurate recommendations with more fluent and coherent dialog utterances.

Copied to clipboard

Ziyue Wang, Chi Chen, Yiqi Zhu, Fuwen Luo, Peng Li, Ming Yan, Ji Zhang, Fei Huang, Maosong Sun, Yang Liu

Rethinking Depression Prediction from a Fine-Grained Subscore Modeling Perspective via Multi-Task Learning (2026.acl-long)

Challenge:	Multimodal Large Language Models (MLLMs) lack understanding of multi-image and interleaved inputs due to the visual features encoded by frozen encoders before being fed into the LLM backbone.
Approach:	They propose a two phase paradigm to enable in-depth multimodal context fusion prior to feeding the features into LLMs.
Outcome:	The proposed paradigm boosts the performance on 7 multi-image scenarios, contributing to increments on average accuracy by 2.13% and 7.60% against strong MLLMs baselines with 3B and 11B LLMs, respectively.

Copied to clipboard

Zhenguang Wang, Bo Li, Wenhui Tan, Peng Cao, Yang Wang, Jia Duan, Fei Wang, Osmar Zaiane

Asking Clarification Questions in Knowledge-Based Question Answering (D19-1)

Challenge:	Existing methods for depression assessment rely on standardized ratings, but they are time-consuming and subject to inter-rater variability.
Approach:	They propose a fine-grained model for subscore prediction via multi-task learning that can be used to predict depression severity using multiple tasks.
Outcome:	The proposed model outperforms baselines and Qwen3-14B direct scoring on the public E-DAIC dataset and to a large-scale private clinical dataset.

Copied to clipboard

Jingjing Xu, Yuechen Wang, Duyu Tang, Nan Duan, Pengcheng Yang, Qi Zeng, Ming Zhou, Xu Sun

PFDial: A Structured Dialogue Instruction Fine-tuning Method Based on UML Flowcharts (2025.findings-acl)

Challenge:	Existing clarification datasets with limited annotated examples do not address ambiguous phenomena.
Approach:	They propose a dataset that allows users to ask clarification questions using open-domain examples.
Outcome:	The proposed model achieves better performance than strong baselines and provides new challenges.

Copied to clipboard

Ming Zhang, Yuhui Wang, Yujiong Shen, Tingyi Yang, Changhao Jiang, Yilong Wu, Shihan Dou, Qinhao Chen, Zhiheng Xi, Zhihao Zhang, Yi Dong, Zhen Wang, Zhihui Fei, Mingyang Wan, Tao Liang, Guojun Ma, Qi Zhang, Tao Gui, Xuanjing Huang

Meta-Reasoning: Semantics-Symbol Deconstruction for Large Language Models (2024.findings-acl)

Challenge:	Large Language Models (LLMs) have shown remarkable progress in dialogue and reasoning, but they struggle to solve strictly constrained dialogue tasks.
Approach:	They construct a dataset that contains 12,705 high-quality Chinese dialogue instructions from 440 flowcharts containing 5,055 process nodes.
Outcome:	The proposed model outperforms GPT-4o models on backward transitions and outperformed GPT-42 models on the same dataset.

Copied to clipboard

Yiming Wang, Zhuosheng Zhang, Pei Zhang, Baosong Yang, Rui Wang

Interpretable Math Word Problem Solution Generation via Step-by-step Planning (2023.acl-long)

Challenge:	Existing methods rely on syntactically mapping natural languages to complete formal languages like Python and SQL.
Approach:	They propose to deconstruct reasoning-independent semantic information into generic symbolic representations, thereby efficiently capturing more generalized reasoning knowledge.
Outcome:	The proposed method improves in-context reasoning accuracy, learning efficiency, out-of-domain generalization, and output stability compared to the Chain-of thought technique.

Copied to clipboard

Mengxue Zhang, Zichao Wang, Zhichao Yang, Weiqi Feng, Andrew Lan

ChildMandarin: A Comprehensive Mandarin Speech Dataset for Young Children Aged 3-5 (2025.acl-long)

Challenge:	Existing approaches to solving math word problems focus on obtaining the correct answer.
Approach:	They propose a step-by-step planning approach for intermediate solution generation that strategically plans the generation of the next solution step based on the MWP and the previous solution steps.
Outcome:	The proposed approach improves the accuracy and interpretability of the solution on automatic metrics and human evaluation.

Copied to clipboard

Jiaming Zhou, Shiyao Wang, Shiwan Zhao, Jiabei He, Haoqin Sun, Hui Wang, Cheng Liu, Aobo Kong, Yujie Guo, Xi Yang, Yequan Wang, Yonghua Lin, Yong Qin

ETR: Entropy Trend Reward for Efficient Chain-of-Thought Reasoning (2026.acl-long)

Challenge:	Automatic speech recognition systems have advanced significantly with models like Whisper, Conformer, and self-supervised frameworks such as Wav2vec 2.0.
Approach:	They propose to use Mandarin speech datasets to analyze pronunciation and tone of children aged 3 to 5 and evaluate their models on speaker verification (SV) They find that the datasets are more robust than those used by adult speech recognition systems and are open-source and available for all academic purposes.
Outcome:	The proposed dataset includes 41.25 hours of speech with carefully crafted manual transcriptions, collected from 397 speakers across various provinces in China, with balanced gender representation.

Copied to clipboard

Xuan Xiong, Huan Liu, Li Gu, Zhixiang Chi, Yue Qiu, Yuanhao YU, Yang Wang

Med-SRAF: A Multi-Agent Framework for Medical Reasoning via Semantic Routing and Agentic Fusion (2026.findings-acl)

Challenge:	Existing methods to shorten CoTs use length penalties or global entropy reduction . Existing approaches to CoT reasoning have significant practical drawbacks .
Approach:	They propose a method that shortens CoTs by length penalties or global entropy reduction . they integrate ETR into Group Relative Policy Optimization and evaluate it .
Outcome:	The proposed objective improves accuracy–efficiency trade-off by +9.9% while reducing CoT length by 67% across four benchmarks.

Copied to clipboard

Xiao Li, Zhuo Chen, Jun Xia, Hongxin Xiang, Chao Wang, Wenjie Du, Yang Wang

Hello Again! LLM-powered Personalized Agent for Long-term Dialogue (2025.naacl-long)

Challenge:	Existing RAG methods suffer from a two-part problem: semantic drift and concatenation fallacy . et al.: rapid development of Large Language Models has led to a paradigm shift in artificial intelligence .
Approach:	They propose a multi-agent retrieval augmentation framework guided by medical domain knowledge to address these challenges.
Outcome:	The proposed framework outperforms existing general RAG baselines on five widely used medical benchmarks.

Copied to clipboard

Hao Li, Chenghao Yang, An Zhang, Yang Deng, Xiang Wang, Tat-Seng Chua

LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification (2026.acl-long)

Challenge:	Existing dialogue systems focus on brief single-session interactions, neglecting real-world needs for long-term companionship and personalized interactions.
Approach:	They propose a model-agnostic framework for long-term dialogue agents . they use event summary and persona management to enable reasoning .
Outcome:	The proposed framework incorporates three independently tunable modules dedicated to event perception, persona extraction, and response generation.

Copied to clipboard

Penghui Yang, Cunxiao Du, Fengzhuo Zhang, Haonan Wang, Tianyu Pang, Chao Du, Bo An

Harmonizing the Past, Present, and Future: A Null-Space Constrained Region-Specific Method for Continual Learning in LLMs (2026.acl-long)

Challenge:	Large Language Models (LLMs) can process extremely long contexts, requiring efficient inference over extended inputs.
Approach:	They propose a model that uses a constant-sized key-value cache to train long-context models.
Outcome:	Experimental results show that LongSpec achieves 3.26x speedup over strong Flash Attention baselines and 2.34x wall clock time on four math reasoning tasks.

Copied to clipboard

Jinhui Chen, Shizhu He, Xingchang Yang, Huanxuan Liao, Yequan Wang, Xiangwen Liao, Wenhao Teng, Kang Liu, Jun Zhao

DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Models (2023.acl-long)

Challenge:	Existing continual learning paradigms prioritize instant performance through dense updates, leading to catastrophic forgetting and rapid exhaustion of model capacity.
Approach:	They propose a method that preserves previously acquired knowledge and acquires new task-specific skills while preserving sufficient parameter capacity for subsequent adaptation.
Outcome:	The proposed method is based on the brain's functional partitioning and can be used to map tasks between specialized and generalist neurons.

Copied to clipboard

Zijie J. Wang, Evan Montoya, David Munechika, Haoyang Yang, Benjamin Hoover, Duen Horng Chau

CBT-Bench: Evaluating Large Language Models on Assisting Cognitive Behavior Therapy (2025.naacl-long)

Challenge:	Recent advances in diffusion models have enabled high-quality image generation . generating images with desired details requires proper prompts .
Approach:	They analyze syntactic and semantic characteristics of diffusion models and their prompts . they pinpoint specific hyperparameter values and prompt styles that can lead to model errors .
Outcome:	The first large-scale text-to-image prompt dataset totals 6.5TB . it contains 14 million images generated by Stable Diffusion, 1.8 million unique prompts, and hyperparameters specified by real users.

Copied to clipboard

Mian Zhang, Xianjun Yang, Xinlu Zhang, Travis Labrum, Jamie C. Chiu, Shaun M. Eack, Fei Fang, William Yang Wang, Zhiyu Chen

Empowering Language Models with Knowledge Graph Reasoning for Open-Domain Question Answering (2022.emnlp-main)

Challenge:	Existing research has explored mental health condition classifications, empathetic conversations, and chatbots designed for simple discourse structures.
Approach:	They propose a benchmark for systematic evaluation of cognitive behavioral therapy assistance using Large Language Models (LLMs).
Outcome:	The proposed benchmark includes three levels of tasks covering key aspects of cognitive behavioral therapy that could be enhanced through AI assistance.

Copied to clipboard

Ziniu Hu, Yichong Xu, Wenhao Yu, Shuohang Wang, Ziyi Yang, Chenguang Zhu, Kai-Wei Chang, Yizhou Sun

Fantastic Questions and Where to Find Them: FairytaleQA – An Authentic Dataset for Narrative Comprehension (2022.acl-long)

Challenge:	Existing Language Models lack the power to store all required knowledge, resulting in a lack of ability to infer out-of-context knowledge.
Approach:	They propose a Knowledge Interaction Layer that can be flexibly plugged into existing Transformer-based LMs to interact with a differentiable Knowledge Graph Reasoning module collaboratively.
Outcome:	The proposed model can be plugged into existing Transformer-based LMs to interact with a differentiable Knowledge Graph Reasoning module collaboratively.

Copied to clipboard

Ying Xu, Dakuo Wang, Mo Yu, Daniel Ritchie, Bingsheng Yao, Tongshuang Wu, Zheng Zhang, Toby Li, Nora Bradford, Branda Sun, Tran Hoang, Yisi Sang, Yufang Hou, Xiaojuan Ma, Diyi Yang, Nanyun Peng, Zhou Yu, Mark Warschauer

Question Answering

Challenge:	Existing QA datasets rarely distinguish fine-grained reading skills, such as the understanding of varying narrative elements.
Approach:	They propose to use FairytaleQA to generate 10,580 questions based on 278 children-friendly stories to assess model's fine-grained learning skills.
Outcome:	The proposed dataset consists of 10,580 questions derived from 278 children-friendly stories, covering seven types of narrative elements or relations.

RLKGF: Reinforcement Learning from Knowledge Graph Feedback Without Human Annotations (2025.findings-acl)

Copied to clipboard

Lian Yan, Chen Tang, Yi Guan, Haotian Wang, Songyuan Wang, Haifeng Liu, Yang Yang, Jingchi Jiang

NormBank: A Knowledge Bank of Situational Social Norms (2023.acl-long)

Challenge:	Lack of human preference labels remains a significant bottleneck when applying RLHF to a downstream domain.
Approach:	They propose a method that leverages human priors encoded in Knowledge Graphs (KGs) to derive RL rewards in the absence of manual annotations.
Outcome:	Experiments on three public and one private medical dialogue datasets show that the proposed method outperforms the competitive RLAIF in improving LLM diagnostic accuracy.

Copied to clipboard

Caleb Ziems, Jane Dwivedi-Yu, Yi-Chia Wang, Alon Halevy, Diyi Yang

Challenge:	NormBank is a knowledge bank of 155k situational norms that can be used to ground flexible normative reasoning for interactive, assistive, and collaborative AI systems.
Approach:	They propose a new scheme for hierarchically organizing the seemingly unbounded social norms within a multivalent sociocultural frame.
Outcome:	The proposed framework can be used to ground flexible reasoning for interactive, assistive, and collaborative AI systems.

Visual Self-Fulfilling Alignment: Shaping Safety-Oriented Personas via Threat-Related Images (2026.acl-long)

Copied to clipboard

Qishun Yang, Shu Yang, Lijie Hu, Di Wang

YATO: Yet Another deep learning based Text analysis Open toolkit (2023.emnlp-demo)

Challenge:	Existing methods require explicit safety labels or contrastive data, yet visual inputs enable harmful outputs.
Approach:	They propose a visual self-fulfilling alignment mechanism that fine-tunes vision-language models on neutral VQA tasks without any safety labels.
Outcome:	The proposed approach reduces attack success rate, improves response quality, and mitigates over-refusal while preserving general capabilities.

Copied to clipboard

Zeqiang Wang, Yile Wang, Jiageng Wu, Zhiyang Teng, Jie Yang

Temporal Consistency for LLM Reasoning Process Error Identification (2025.findings-emnlp)

Challenge:	YATO is an open-source toolkit for text analysis with deep learning . it supports free combinations of three types of widely used features .
Approach:	They introduce YATO, an open-source toolkit for text analysis with deep learning.
Outcome:	YATO is an open-source toolkit for text analysis with deep learning . the toolkit supports free combinations of three types of widely used features .

Copied to clipboard

Jiacheng Guo, Yue Wu, Jiahao Qiu, Kaixuan Huang, Xinzhe Juan, Ling Yang, Mengdi Wang

ToM: Leveraging Tree-oriented MapReduce for Long-Context Reasoning in Large Language Models (2025.emnlp-main)

Challenge:	Empirical evaluations show consistent performance improvements over baseline methods . 7B/8B distilled models outperform all 70B/72B models and GPT-4o on ProcessBench .
Approach:	They propose a temporal consistency method that leverages consistency in a sequence of self-reflection actions to improve verification accuracy.
Outcome:	The proposed method outperforms existing methods on three benchmarks . it leverages consistency in a sequence of self-reflection actions to improve accuracy .

Copied to clipboard

Jiani Guo, Zuchao Li, Jie Wu, Qianren Wang, Yun Li, Lefei Zhang, Hai Zhao, Yujiu Yang

IDOL: Indicator-oriented Logic Pre-training for Logical Reasoning (2023.findings-acl)

Challenge:	Experimental results show ToM outperforms existing divide-and-conquer frameworks . RAG relies on similarity-based rankings to retrieve and reason over chunks based on logical coherence .
Approach:	They propose a Tree-oriented MapReduce framework for long-context reasoning . it leverages the hierarchical structure of long documents by constructing a DocTree .
Outcome:	Experimental results show that ToM outperforms existing divide-and-conquer frameworks and RAGs . the proposed framework improves logical coherence and long-context reasoning on 70B+ LLMs compared to existing approaches .

Copied to clipboard

Zihang Xu, Ziqing Yang, Yiming Cui, Shijin Wang

Offline Reinforcement Learning for LLM Multi-step Reasoning (2025.findings-acl)

Challenge:	Existing systems for logical reasoning have surpassed the average performance of humans in many tasks like SQuAD but there is still a long way to go when it comes to logical reasoning.
Approach:	They propose an InDicator-Oriented Logic Pre-training task which logically strengthens pre-trained models with the help of 6 types of logical indicators and a logicalally rich dataset.
Outcome:	The proposed task achieves state-of-the-art on ReClor and LogiQA, the two most representative benchmarks in logical reasoning MRC.

Copied to clipboard

Huaijie Wang, Shibo Hao, Hanze Dong, Shenao Zhang, Yilin Bao, Ziran Yang, Yi Wu

AgentCPM-GUI: Building Mobile-Use Agents with Reinforcement Fine-Tuning (2025.emnlp-demos)

Challenge:	Large language models (LLMs) are increasingly applied to complex tasks requiring multi-step reasoning.
Approach:	They propose an offline method for enhancing multi-step reasoning by optimizing the soft Bellman Equation by combining a policy model and a value function.
Outcome:	The proposed method surpasses existing methods on multi-step reasoning benchmarks and can be extended to multi-iteration frameworks when additional resources are available.

Copied to clipboard

Zhong Zhang, Yaxi Lu, Yikun Fu, Yupeng Huo, Shenzhi Yang, Yesai Wu, Han Si, Xin Cong, Haotian Chen, Yankai Lin, Xie Xie, Wei Zhou, Wang Xu, Zhou Su, Zhongwu Zhai, Xiaoming Liu, null Meiyudong, Jianming Xu, Hongyan Tian, Chongyi Wang, Chi Chen, Yuan Yao, Zhiyuan Liu, Maosong Sun

DeepMed: Building a Medical DeepResearch Agent via Multi-hop Med-Search Data and Turn-Controlled Agentic Training & Inference (2026.findings-acl)

Challenge:	Large language model agents have enabled GUI-based automation, but their deployment is limited by noisy data, poor generalization, and lack of support for non-English GUIs.
Approach:	They propose an 8B-parameter GUI agent built for robust and efficient on-device GUI interaction.
Outcome:	The proposed GUI agent achieves promising performance on five public benchmarks and proposed Chinese benchmark CAGUI.

Copied to clipboard

Zihan Wang, Hao Wang, Shi Feng, Xiaocui Yang, Daling Wang, Yiqun Zhang, Jinghao Lin, Xiaozhong Ji, Haihua Yang

Out-of-Distribution Generalization in Natural Language Processing: Past, Present, and Future (2023.emnlp-main)

Challenge:	Medical reasoning models are constrained by parametric knowledge and can induce hallucinations and spurious attributions.
Approach:	They propose a model that uses a multi-hop med-search QA synthesis method to apply the DR paradigm in medical contexts.
Outcome:	The proposed model outperforms larger medical reasoning models on medical benchmarks.

Copied to clipboard

Linyi Yang, Yaoxian Song, Xuan Ren, Chenyang Lyu, Yidong Wang, Jingming Zhuo, Lingqiao Liu, Jindong Wang, Jennifer Foster, Yue Zhang

PGPO: Enhancing Agent Reasoning via Pseudocode-style Planning Guided Preference Optimization (2025.findings-acl)

Challenge:	Existing literature on the generalization of machine learning models to out-of-distribution data is lacking.
Approach:	They propose to present the first comprehensive review of recent progress, methods, and evaluations on the generalization challenge from an OOD perspective in natural language understanding.
Outcome:	The proposed survey provides the first comprehensive review of recent progress, methods, and evaluations on the generalization challenge from an OOD perspective in natural language understanding.

Copied to clipboard

Zouying Cao, Runze Wang, Yifei Yang, Xinbei Ma, Xiaoyong Zhu, Bo Zheng, Hai Zhao

PITA: Prompting Task Interaction for Argumentation Mining (2024.acl-long)

Challenge:	Existing LLM agents generate verbose and inefficient natural language plans to guide reasoning, which restricts agents’ ability to generalize across similar tasks.
Approach:	They propose a pseudocode-style planning guide optimization method that captures the structural logic of reasoning and uses two planning-oriented rewards to enhance agent learning.
Outcome:	The proposed method outperforms existing LLM agents on representative agent benchmarks and outperformed the current leading baselines.

Copied to clipboard

Yang Sun, Muyi Wang, Jianzhu Bao, Bin Liang, Xiaoyan Zhao, Caihua Yang, Min Yang, Ruifeng Xu

Text Classification

Challenge:	Argumentation mining (AM) aims to detect arguments and their inherent relations from textual compositions.
Approach:	They propose a method to model the inter-relationships among three subtasks within a generative framework.
Outcome:	The proposed method achieves state-of-the-art performance on two AM benchmarks.

Query-Efficient Agentic Graph Extraction Attacks on GraphRAG Systems (2026.acl-long)

Copied to clipboard

Shuhua Yang, Jiahao Zhang, Yilong Wang, Dongwon Lee, Suhang Wang

Learning to Refine: Self-Refinement of Parallel Reasoning in LLMs (2026.findings-acl)

Challenge:	Existing attacks exploit leakage of retrieved subgraphs, leaving the security implications of structured knowledge representations unexplored.
Approach:	They propose a framework that leverages a novelty-guided exploration–exploitation strategy and external graph memory modules to extract a latent entity–relation graph.
Outcome:	The proposed framework outperforms baselines on medical, agriculture, and literary datasets under identical query budgets while maintaining high precision.

Copied to clipboard

Qibin Wang, Pu Zhao, Shaohan Huang, Fangkai Yang, Lu Wang, Furu Wei, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang

AgentGym: Evaluating and Training Large Language Model-based Agents across Diverse Environments (2025.acl-long)

Challenge:	Existing approaches to test-time scaling are limited due to the quality of candidate responses.
Approach:	They propose a new metric to quantify the relative improvement of self-refinement beyond majority voting.
Outcome:	The proposed method achieves state-of-the-art performance across five benchmarks over other methods.

Copied to clipboard

Zhiheng Xi, Yiwen Ding, Wenxiang Chen, Boyang Hong, Honglin Guo, Junzhe Wang, Xin Guo, Dingwen Yang, Chenyang Liao, Wei He, Songyang Gao, Lu Chen, Rui Zheng, Yicheng Zou, Tao Gui, Qi Zhang, Xipeng Qiu, Xuanjing Huang, Zuxuan Wu, Yu-Gang Jiang

The Shifted and The Overlooked: A Task-oriented Investigation of User-GPT Interactions (2023.emnlp-main)

Challenge:	Large language models (LLMs) are promising foundations to build generally-capable agents . however, the community lacks a unified interactive framework that covers diverse environments for comprehensive evaluation of agents.
Approach:	They propose a framework that features 7 real-world scenarios, 14 environments, and 89 tasks for unified, real-time, and concurrent agent interaction.
Outcome:	The proposed framework features 7 real-world scenarios, 14 environments, and 89 tasks for unified, real-time, and concurrent agent interaction.

Copied to clipboard

Siru Ouyang, Shuohang Wang, Yang Liu, Ming Zhong, Yizhu Jiao, Dan Iter, Reid Pryzant, Chenguang Zhu, Heng Ji, Jiawei Han

EvolvR: Self-Evolving Pairwise Reasoning for Story Evaluation to Enhance Generation (2026.acl-long)

Challenge:	Recent advances in large language models (LLMs) have produced models that exhibit remarkable performance across a variety of NLP tasks.
Approach:	They analyze a large-scale collection of user-GPT conversations to identify a significant gap between academic research in NLP and the needs of real-world NLP applications.
Outcome:	The proposed model outperforms existing models in a large-scale collection of user-GPT conversations and identifies a significant gap between the tasks that users frequently request from LLMs and the tasks commonly studied in academic research.

Copied to clipboard

Xinda Wang, Zhengxu Hou, Yangshijie Zhang, null Yanbingren, Jialin Liu, ChenZhuo Zhao, Zhibo Yang, Bin-Bin Yang, Feng Xiao

Exploring Quality and Diversity in Synthetic Data Generation for Argument Mining (2025.emnlp-main)

Challenge:	Existing methods for story evaluation lack reasoning capabilities for open-source models . evolvR framework provides high-fidelity evaluators for story generation tasks .
Approach:	They propose a framework that self-synthesizes chain-of-thought data via a multi-persona strategy . they propose evolvR to provide a reward model for story generation .
Outcome:	The proposed framework achieves state-of-the-art performance on three evaluation benchmarks . it also enhances the quality of generated stories, validating the superiority of the framework .

Copied to clipboard

Jianzhu Bao, Yuqi Huang, Yang Sun, Wenya Wang, Yice Zhang, Bojun Jin, Ruifeng Xu

A Semi-Supervised Stable Variational Network for Promoting Replier-Consistency in Dialogue Generation (D19-1)

Challenge:	Argument Mining (AM) is hindered by the scarcity of structure-annotated datasets, which are expensive to create manually.
Approach:	They propose to use quality-oriented synthesis and diversity-oriented approach to generate argumentative texts with diverse topics and argument structures.
Outcome:	The proposed approach significantly improves existing models in full-data and low-resource settings.

Copied to clipboard

Jinxin Chang, Ruifang He, Longbiao Wang, Xiangyu Zhao, Ting Yang, Ruifang Wang

Revisiting Interpolation Augmentation for Speech-to-Text Generation (2024.findings-acl)

Challenge:	Existing methods favor uninformative and non replier-specific responses due to lack of relevant information guidance.
Approach:	They propose to use a semi-supervised variable network to generate replier-specific responses . they use vMF as latent space to obtain stable KL performance .
Outcome:	The proposed model outperforms baseline models on two large conversation datasets and generates diverse and replier-specific responses.

Copied to clipboard

Chen Xu, Jie Wang, Xiaoqian Liu, Qian Dong, Chunliang Zhang, Tong Xiao, JingBo Zhu, Dapeng Man, Wu Yang

MathSight: A Benchmark Exploring Have Vision-Language Models Really Seen in University-Level Mathematical Reasoning? (2026.acl-long)

Challenge:	Existing approaches to speech-to-text generation tasks are limited by the lack of extensive labeled datasets.
Approach:	They propose to use interpolation augmentation to construct virtual training samples by transforming inputs and labels to enhance generalization in other domains.
Outcome:	The proposed approach significantly improves performance across diverse tasks, architectures, and data scales, offering a promising avenue for more robust S2T systems in resource-constrained settings.

Copied to clipboard

Yuandong Wang, Yao Cui, Yuxin Zhao, Zhen Yang, Yangfu Zhu, Zhenzhou Shao

Multi-Programming Language Sandbox for LLMs (2025.acl-demo)

Challenge:	Existing benchmarks rarely isolate how much visual information contributes to reasoning . a growing collection of benchmarks has catalyzed rapid progress in multimodal reasoning - but how much it contributes remains unclear .
Approach:	They propose a university-level multimodal mathematical reasoning benchmark to quantify the effect of visual input.
Outcome:	The proposed benchmark disentangles and quantifies the effect of visual input on multimodal reasoning models.

Copied to clipboard

Shihan Dou, Jiazheng Zhang, Jianxiang Zang, Yunbo Tao, Weikang Zhou, Haoxiang Jia, Shichun Liu, Yuming Yang, Shenxi Wu, Zhiheng Xi, Muling Wu, Rui Zheng, Changze Lv, Limao Xiong, Shaoqing Zhang, Lin Zhang, Wenyu Zhan, Rongxiang Weng, Jingang Wang, Xunliang Cai, Yueming Wu, Ming Wen, Yixin Cao, Tao Gui, Xipeng Qiu, Qi Zhang, Xuanjing Huang

Why Do More Experts Fail? A Theoretical Analysis of Model Merging (2026.acl-long)

Challenge:	MPLSandbox is an out-of-the-box multi-programming language sandbox designed to provide unified and comprehensive feedback from compiler and analysis tools for Large Language Models (LLMs).
Approach:	They propose a multi-programming language sandbox that provides unified feedback from compilers and analysis tools for Large Language Models.
Outcome:	The proposed multi-language sandbox can provide comprehensive feedback from compilers and analysis tools for large language models (LLMs).

Copied to clipboard

Zijing Wang, Xingle Xu, YongKang Liu, Yiqun Zhang, Peiqin Lin, Shi Feng, Daling Wang, Xiaocui Yang, Hinrich Schuetze

Challenge:	Existing methods for model merging struggle to maintain performance gains as the number of merged models increases.
Approach:	They propose a Reparameterized Heavy-Tailed method to extend the merged model’s coverage and enhance performance.
Outcome:	The proposed method extends the merged model’s coverage and enhances performance on 19 benchmarks, including knowledge-intensive and general-purpose tasks.

CQIL: Inference Latency Optimization with Concurrent Computation of Quasi-Independent Layers (2024.acl-long)

Copied to clipboard

Longwei Zou, Qingyang Wang, Han Zhao, Jiangangkong Jiangangkong, Yi Yang, Yangdong Deng

The Moral Integrity Corpus: A Benchmark for Ethical Dialogue Systems (2022.acl-long)

Challenge:	Existing methods to improve inference efficiency target to reduce per-layer latency, but ignore cumulative latency due to number of layers.
Approach:	They propose to identify quasi-independent layers that can be concurrently computed to significantly decrease inference latency.
Outcome:	Empirical results show that the proposed method reduces latency by 48.3% on LLaMA-33B while maintaining close level of performance.

Copied to clipboard

Caleb Ziems, Jane Yu, Yi-Chia Wang, Alon Halevy, Diyi Yang

LLM-Enhanced Self-Evolving Reinforcement Learning for Multi-Step E-Commerce Payment Fraud Risk Detection (2025.acl-industry)

Challenge:	Moral integrity corpus captures the moral assumptions of 38k prompt-reply pairs, using 99k distinct Rules of Thumb (RoTs).
Approach:	They propose a resource that captures the moral assumptions of 38k prompt-reply pairs, using 99k distinct Rules of Thumb (RoTs).
Outcome:	The proposed resource captures the moral assumptions of 38k prompt-reply pairs, using 99k distinct Rules of Thumb (RoTs).

Copied to clipboard

Bo Qu, Zhurong Wang, Daisuke Yagi, Zach Xu, Yang Zhao, Yinan Shan, Frank Zahradnik

SEMGraph: Incorporating Sentiment Knowledge and Eye Movement into Graph Model for Sentiment Analysis (2022.emnlp-main)

Challenge:	e-commerce payment fraud detection is a new area for reinforcement learning (RL) and Large Language Models (LLMs).
Approach:	They propose to integrate reinforcement learning (RL) with Large Language Models (LLMs) by framing transaction risk as a multi-step Markov Decision Process (MDP), RL optimizes risk detection across multiple payment stages.
Outcome:	The proposed approach improves fraud detection accuracy and demonstrates zero-shot capability.

Copied to clipboard

Bingbing Wang, Bin Liang, Jiachen Du, Min Yang, Ruifeng Xu

NOAHQA: Numerical Reasoning with Interpretable Graph Question Answering Dataset (2021.findings-emnlp)

Challenge:	Existing research on sentiment analysis based on eye movement signals has been attributed importance.
Approach:	They propose a linguistic probing eye movement paradigm to extract eye movement features based on the relationship between linguistic features and human reading behavior.
Outcome:	The proposed graph architecture achieves state-of-the-art performance on two sentiment analysis datasets with eye movement signals and three sentiment analysis data without eye movement signal.

Copied to clipboard

Qiyuan Zhang, Lei Wang, Sicheng Yu, Shuohang Wang, Yang Wang, Jing Jiang, Ee-Peng Lim

Multi-Agent Collaboration via Cross-Team Orchestration (2025.findings-acl)

Challenge:	Existing question answering datasets lack numerical reasoning and reasoning processes . current research on numerical reasoning focuses on simple calculations .
Approach:	They propose a conversational and bilingual question answering dataset with numerical reasoning with compound mathematical expressions.
Outcome:	The proposed model achieves 55.5 exact match scores while human performance is 89.7.

Copied to clipboard

Zhuoyun Du, Chen Qian, Wei Liu, Zihao Xie, YiFei Wang, Rennai Qiu, Yufan Dang, Weize Chen, Cheng Yang, Ye Tian, Xuantang Xiong, Lei Han

Challenge:	Large Language Models (LLMs) have significantly impacted various domains, especially through organized LLM-driven autonomous agents.
Approach:	They propose a framework that enables orchestrated teams to jointly propose various task-oriented solutions and interact with their insights in a self-independence while cross-team collaboration environment for superior solutions generation.
Outcome:	Experiments show that the framework can generate better software quality compared to state-of-the-art frameworks.

LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety (2026.acl-long)

Copied to clipboard

Junxiao Yang, Haoran Liu, Jinzhe Tu, Jiale Cheng, Zhexin Zhang, Shiyao Cui, Jiaqi Weng, Jialing Tao, Hui Xue, Hongning Wang, Han Qiu, Minlie Huang

Challenge:	Large language models (LLMs) have demonstrated better safety performance in high-resource languages than in low-resourced languages.
Approach:	They propose language-agnostic semantic alignment (LASA) which anchors safety alignment directly in semantic bottlenecks.
Outcome:	The proposed approach significantly improves safety across all languages: average attack success rate drops from 24.7% to 2.8% on LLaMA-3.1-8B-Instruct and remains within 3–4% across Qwen2.5 and Qwend3 Instruct models (7B–32B).

Inspecting Unification of Encoding and Matching with Transformer: A Case Study of Machine Reading Comprehension (D19-58)

Copied to clipboard

Hangbo Bao, Li Dong, Furu Wei, Wenhui Wang, Nan Yang, Lei Cui, Songhao Piao, Ming Zhou

Towards Database-Free Text-to-SQL Evaluation: A Graph-Based Metric for Functional Correctness (2025.coling-main)

Challenge:	Experimental results show that unified model outperforms other models that treat encoding and matching separately.
Approach:	They evaluate a unified model with Transformer layers for machine reading comprehension . they find that the model learns different modeling strategies compared with previous models .
Outcome:	The unified model outperforms models with Transformer layers on the machine reading comprehension task.

Copied to clipboard

Yi Zhan, Longjie Cui, Han Weng, Guifeng Wang, Yu Tian, Boyi Liu, Yingxiang Yang, Xiaoming Yin, Jiajun Xie, Yang Sun

Efficient Prior-Guided Reasoning for Robust Retrieval-Augmented Generation under Conflicts (2026.acl-long)

Challenge:	Existing metrics for evaluating functional correctness of SQL queries are prone to false positives due to inadequately prepared test databases.
Approach:	They propose a graph-based metric that uses a relational operator tree to extract rich semantic information from the logical execution plan of SQL queries and embed it into a diagram.
Outcome:	The proposed method eliminates the need for extensive test database preparation and performs graph matching on unseen SQL queries.

Copied to clipboard

Xiaowei Yuan, Ziyang Huang, Zhao Yang, Yequan Wang, Jun Zhao, Kang Liu

Adversarial Training for Machine Reading Comprehension with Virtual Embeddings (2021.starsem-1)

Challenge:	Retrieval-Augmented Generation (RAG) has become a standard paradigm for grounding Large Language Models (LLMs) however, performance degrades substantially when faced with noisy, outdated, or conflicting retrieved information.
Approach:	They propose a framework that explicitly elicits the model’s parametric knowledge as prior information to guide reasoning on retrieved documents.
Outcome:	The proposed framework achieves robust performance across varying degrees of external inconsistency and noise.

Copied to clipboard

Ziqing Yang, Yiming Cui, Chenglei Si, Wanxiang Che, Ting Liu, Shijin Wang, Guoping Hu

Negation Triplet Extraction with Syntactic Dependency and Semantic Consistency (2024.lrec-main)

Challenge:	Neural networks are vulnerable to adversarial examples that have been mixed with certain perturbations.
Approach:	They propose a novel adversarial training method that perturbs the embedding matrix instead of word vectors to differentiate the roles of passages and questions.
Outcome:	The proposed method is effective universally and further improves the performance of MRC tasks.

Copied to clipboard

Yuchen Shi, Deqing Yang, Jingping Liu, Yanghua Xiao, Zongyu Wang, Huimin Xu

HIRAG: Hierarchical-Thought Instruction-Tuning Retrieval-Augmented Generation (2025.findings-emnlp)

Challenge:	Negation understanding is crucial to many downstream tasks such as sentiment analysis, question answering, Web search and natural language inference.
Approach:	They propose a novel negation triplet extraction task which aims to extract negation subject along with negation cue and scope.
Outcome:	The proposed model is based on a generative pretrained language model with a multi-task learning framework and achieves the best performance compared to baselines.

Copied to clipboard

Yihan Jiao, Zhehao Tan, Dan Yang, Duolin Sun, Jie Feng, Yue Shen, Jian Wang, Peng Wei

Hierarchical Enhancement Framework for Aspect-based Argument Mining (2023.findings-emnlp)

Challenge:	In-depth research on the specific capabilities needed by the RAG generation model is lacking, leading to inconsistent document quality and retrieval system imperfections.
Approach:	They propose that RAG models should possess three progressively hierarchical abilities: (1) Filtering: the ability to select relevant information; (2) Combination: the capability to combine semantic information across paragraphs; (3) RAG-specific reasoning: the capacity to further process external knowledge using internal knowledge.
Outcome:	Experiments show that the proposed method significantly improves the model’s open-book examination capability on datasets such as RGB, PopQA, MuSiQue, HotpotQA, and PubmedQA.

Copied to clipboard

Yujie Fu, Yang Li, Suge Wang, Xiaoli Li, Deyu Li, Jian Liao, JianXing Zheng

Logical Consistency as a Bridge: Improving LLM Hallucination Detection via Label Constraint Modeling between Responses and Self-Judgments (2026.acl-long)

Challenge:	Existing methods have primarily treated ABAM as a nested named entity recognition problem, overlooking the need for tailored strategies to effectively address the specific challenges of ABA M tasks.
Approach:	They propose a layer-based Hierarchical Enhancement Framework (HEF) for Aspect-Based Argument Mining and introduce three new components to improve the performance and accuracy.
Outcome:	Experiments on multiple datasets and tasks verify the effectiveness of the proposed framework and components.

Copied to clipboard

Hao Mi, Qiang Sheng, Shaofei Wang, Beizhe Hu, Yifan Sun, Zhengjia Wang, Hengqi Zeng, Yang Li, Danding Wang, Juan Cao

Private Language Models via Truncated Laplacian Mechanism (2024.emnlp-main)

Challenge:	Existing methods for hallucination detection focus on implicit neural uncertainty or explicit symbolic reasoning, ignoring factual hallucinosities.
Approach:	They propose a framework that bridges neural features and symbolic judgments for hallucination detection by leveraging a "meta-judgment" process to map symbolic labels back into the feature space.
Outcome:	Extensive experiments on 4 public datasets, across 4 LLMs, against 8 baselines demonstrate the superiority of LaaB.

Copied to clipboard

Tianhao Huang, Tao Yang, Ivan Habernal, Lijie Hu, Di Wang

Is LLM an Overconfident Judge? Unveiling the Capabilities of LLMs in Detecting Offensive Language with Annotation Disagreement (2025.findings-acl)

Challenge:	Existing methods for word embedding are prone to privacy leakage, resulting in weaker relaxations of DP that are inferior to the canonical DP in terms of privacy strength.
Approach:	They propose a method for private word embedding that uses a non-trivial extension of the truncated Laplacian mechanism and propose to test its effectiveness.
Outcome:	The proposed method has lower variance compared to the previous methods.

Copied to clipboard

Junyu Lu, Kai Ma, Kaichun Wang, Kelaiti Xiao, Roy Ka-Wei Lee, Bo Xu, Liang Yang, Hongfei Lin

GEAR: Graph-based Evidence Aggregating and Reasoning for Fact Verification (P19-1)

Challenge:	Existing studies focus on evaluating large language models' ability to handle disagreement cases.
Approach:	They evaluate the performance of large language models in detecting offensive language at varying levels of agreement.
Outcome:	The proposed model improves detection accuracy and model alignment with human judgment by using disagreement samples in training.

Copied to clipboard

Jie Zhou, Xu Han, Cheng Yang, Zhiyuan Liu, Lifeng Wang, Changcheng Li, Maosong Sun

MentalGLM Series: Explainable Large Language Models for Mental Health Analysis on Chinese Social Media (2025.emnlp-main)

Challenge:	Existing methods to extract information from evidence are unable to grasp relational and logical information among the evidence.
Approach:	They propose a graph-based evidence aggregating and reasoning framework to integrate evidence from multiple pieces of evidence.
Outcome:	The proposed framework achieves significant performance improvements on a large-scale benchmark dataset.

Copied to clipboard

Wei Zhai, Nan Bai, Qing Zhao, Jianqiang Li, Fan Wang, Hongzhi Qi, Meng Jiang, Xiaoqin Wang, Bing Xiang Yang, Guanghui Fu

MolTC: Towards Molecular Relational Modeling In Language Models (2024.findings-acl)

Challenge:	Social media is a key platform for emotional expression, yet deep learning lacks flexibility and interpretability.
Approach:	They propose to use Chinese social media to train interpretable mental health instruction datasets to test models' ability to explain their decisions.
Outcome:	The proposed models outperform deep learning and LLMs on three mental health downstream tasks and demonstrate their potential for clinical applications.

Copied to clipboard

Junfeng Fang, Shuai Zhang, Chang Wu, Zhengyi Yang, Zhiyuan Liu, Sihang Li, Kun Wang, Wenjie Du, Xiang Wang

RepoGenesis: Benchmarking End-to-End Microservice Generation from Readme to Repository (2026.acl-long)

Challenge:	Molecular Relational Learning (MRL) is a promising way to understand interactions between molecular pairs.
Approach:	They propose a novel LLM-based multi-modal framework for molecular interaction modeling following Chain-of-Thought (CoT) theory which integrates graphical information of two molecules in pair.
Outcome:	The proposed framework integrates graphical information of two molecules in pair.

Copied to clipboard

Zhiyuan Peng, Xin Yin, Pu Zhao, Fangkai Yang, Lu Wang, Ran Jia, Xu Chen, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang

Challenge:	Existing benchmarks focus on isolated function/class-level generation, neglecting complete microservice repository generation.
Approach:	They propose a multilingual benchmark for repository-level end-to-end web microservice generation that reflects real-world development workflows.
Outcome:	The benchmark compared 106 repositories across 18 domains and 11 frameworks and 1,258 API endpoints and 2,335 test cases.

NUMINA: A Natural Understanding Benchmark for Multi-dimensional Intelligence and Numerical Reasoning Abilities (2025.findings-emnlp)

Copied to clipboard

Changyu Zeng, Yifan Wang, Zimu Wang, Wei Wang, Zhengni Yang, Muyi Bao, Jimin Xiao, Anh Nguyen, Yutao Yue

In-Context Demonstration Selection with Cross Entropy Difference (2023.findings-emnlp)

Challenge:	Existing 3D benchmarks lack fine-grained numerical reasoning task annotations, limiting MLLMs’ ability to perform precise spatial measurements and complex numerical reasoning.
Approach:	They propose a 3D-based benchmark to enhance indoor perceptual understanding by using multi-scale annotations and question-answer pairs.
Outcome:	The proposed benchmark improves indoor perceptual understanding by incorporating multi-scale annotations and question-answer pairs.

Copied to clipboard

Dan Iter, Reid Pryzant, Ruochen Xu, Shuohang Wang, Yang Liu, Yichong Xu, Chenguang Zhu

RTADev: Intention Aligned Multi-Agent Framework for Software Development (2025.findings-acl)

Challenge:	Large language models (LLMs) can use in-context demonstrations to improve performance on zero-shot tasks.
Approach:	They propose a cross-entropy difference method for selecting in-context demonstrations that uses parameter efficient finetuning to train small models on training data.
Outcome:	The proposed method outperforms baseline selection methods on a mix-domain dataset and shows that the effectiveness of in-context demonstrations negatively correlates with the perplexity of the test example.

Copied to clipboard

Jie Liu, Guohua Wang, Ronghui Yang, Jiajie Zeng, Mengchen Zhao, Yi Cai

SafeMCP: Proactive Power Regulation for LLM Agent Defense via Environment-Grounded Look-Ahead Reasoning (2026.acl-long)

Challenge:	Large Language Models (LLMs) are efficient assistants to humans in software development tasks, but they can cause errors during the development process.
Approach:	They propose an intention aligned multi-agent framework that ensures that all agents work based on a consensus.
Outcome:	The proposed framework reduces errors and improves the quality of generated software code.

Copied to clipboard

Lichao Wang, ZhaoXing Ren, Tianzhuo Yang, Jiaming Ji, Chi Harold Liu, Yaodong Yang, Juntao Dai

Recontextualizing Revitalization: A Mixed Media Approach to Reviving the Nüshu Language (2025.emnlp-main)

Challenge:	Large Language Model (LLM) agents are expanding their action spaces to operate in complex environments.
Approach:	They propose a server-side defense plugin that constrains tool acquisition via predictive reasoning regarding future safety risks.
Outcome:	Experiments on PowerSeeking Bench, ToolEmu, and AgentHarm show that SafeMCP achieves a safe equilibrium, effectively mitigating risks while preserving agent utility.

Copied to clipboard

Ivory Yang, Xiaobo Guo, Yuxin Wang, Hefan Zhang, Yaning Jia, William Dinauer, Soroush Vosoughi

TALON: A Multi-Agent Framework for Long-Table Exploration and Question Answering (2025.emnlp-main)

Challenge:	Nüshu is an endangered language from Jiangyong County, Hunan, China, and the world’s only known writing system created and used exclusively by women.
Approach:	They propose to use NüshuStrokes to record all 397 Unicode Nü Shu characters in sequential handwriting by an expert calligrapher.
Outcome:	Evaluating five state-of-the-art Chinese Optical Character Recognition systems on NüshuVision lowers CER to 0.67, a modest but meaningful improvement over previous datasets.

Copied to clipboard

Ruochun Jin, Xiyue Wang, Dong Wang, Haoqi Zheng, Yunpeng Qi, Silin Yang, Meng Zhang

Mitigating Catastrophic Forgetting in Large Language Models with Self-Synthesized Rehearsal (2024.acl-long)

Challenge:	Existing approaches to query-relevant content retrieval fail to retrieve contextually relevant data.
Approach:	They propose a multi-agent framework for table question answering over long tables . TALON features a planning agent that iteratively invokes a tool agent to access tabular data .
Outcome:	The proposed framework achieves average accuracy improvements of 7.5% and 12.0% across all language models.

Copied to clipboard

Jianheng Huang, Leyang Cui, Ante Wang, Chengyi Yang, Xinting Liao, Linfeng Song, Junfeng Yao, Jinsong Su

APPSI-139: A Parallel Corpus of English Application Privacy Policy Summarization and Interpretation (2026.acl-long)

Challenge:	Existing methods to train LLMs on previous training data are not feasible in real-world applications because of catastrophic forgetting.
Approach:	They propose a framework that uses the LLM to generate synthetic instances for rehearsal and refine the instance outputs based on the synthetic inputs.
Outcome:	The proposed framework achieves superior or comparable performance compared to conventional rehearsal-based approaches while being more data-efficient.

Copied to clipboard

Pengyun Zhu, Qiheng Sun, Long Wen, Yanbo Wang, Yang Cao, Junxu Liu, Deyi Xiong, Jinfei Liu, Zhibo Wang, Kui Ren

Syntax-BERT: Improving Pre-trained Transformers with Syntax Trees (2021.eacl-main)

Challenge:	a lack of high-quality English privacy policy corpus optimized for legal clarity and readability is limiting translation of privacy policies . 139 privacy policies are often considered "incomprehensible" due to technical jargon, legal language, and convoluted grammatical structures.
Approach:	They propose a high-quality English privacy policy corpus annotated by domain experts . they propose APPSI-139 to summarize and interpret privacy policies in English .
Outcome:	The proposed framework outperforms large language models in terms of readability and accuracy.

Copied to clipboard

Jiangang Bai, Yujing Wang, Yiren Chen, Yaming Yang, Jing Bai, Jing Yu, Yunhai Tong

How Should We Enhance the Safety of Large Reasoning Models: An Empirical Study (2026.acl-long)

Challenge:	Pre-trained language models like BERT achieve superior performances in various NLP tasks without explicit consideration of syntactic information.
Approach:	They propose a plug-and-play framework that incorporates syntax trees into pre-trained Transformers.
Outcome:	The proposed framework improves on pre-trained models on natural language understanding datasets and shows that it can be used to train pre-structured neural networks.

Copied to clipboard

Zhexin Zhang, Xian Qi Loye, Victor Shea-Jay Huang, Junxiao Yang, Qi Zhu, Shiyao Cui, Fei Mi, Lifeng Shang, Yingkang Wang, Hongning Wang, Minlie Huang

Continual Sequence Generation with Adaptive Compositional Modules (2022.acl-long)

Challenge:	Large Reasoning Models have achieved remarkable success on reasoning-intensive tasks, but their enhanced reasoning capabilities do not translate to improved safety performance.
Approach:	They propose to use supervised fine tuning to enhance the safety of Large Reasoning Models.
Outcome:	The proposed method improves the safety of large reasoning models on reasoning-intensive tasks.

Copied to clipboard

Yanzhe Zhang, Xuezhi Wang, Diyi Yang

ReflectEvo: Improving Meta Introspection of Small LLMs by Learning Self-Reflection (2025.findings-acl)

Challenge:	Existing work on continual sequence generation relies on reuse of existing parameters to learn new tasks or blindly adds new parameters for each new task.
Approach:	They propose to use continual sequence generation to reuse existing parameters for new tasks . current continuous learning models often forget knowledge of dissimilar tasks if data distributions shift .
Outcome:	The proposed framework outperforms state-of-the-art models on various sequences of generation tasks.

Copied to clipboard

Jiaqi Li, Xinyi Dong, Yang Liu, Zhizhuo Yang, Quansen Wang, Xiaobo Wang, Song-Chun Zhu, Zixia Jia, Zilong Zheng

AgentAsk: Multi-Agent Systems Need to Ask (2026.acl-long)

Challenge:	ReflectEvo-460k is a large-scale, comprehensive, self-generated reflection dataset with broadened instructions and diverse multi-domain tasks.
Approach:	They propose a pipeline that iteratively generates self-reflection for self-training and a large-scale reflection dataset with broadened instructions and diverse multi-domain tasks.
Outcome:	The proposed pipeline improves Llama-3 reasoning ability by up to 71.2% and Mistral by upto 44.4%.

Copied to clipboard

Bohan Lin, Kuo Yang, Zelin Tan, Yingchuan Lai, Chen Zhang, Guibin Zhang, Xinlei Yu, Miao Yu, Xu Wang, Yudong Zhang, Yang Wang

Taxonomy-Guided Zero-Shot Recommendations with LLMs (2025.coling-main)

Challenge:	Multi-agent systems fail to consistently outperform strong single-a agent baselines due to error propagation at inter-aggent message handoffs.
Approach:	They propose an edge-level error taxonomy that identifies four main errors in multi-agent interactions as data gaps, signal corruption, referential drift and capacity gaps as primary sources of failure.
Outcome:	The proposed module outperforms existing systems on five benchmarks and is architecture-agnostic.

Copied to clipboard

Yueqing Liang, Liangwei Yang, Chen Wang, Xiongxiao Xu, Philip S. Yu, Kai Shu

CSLM: A Framework for Question Answering Dataset Generation through Collaborative Small Language Models (2024.findings-emnlp)

Challenge:	Existing approaches to deploy large language models (LLMs) into RecSys have limited prompt length, unstructured item information, and un-constrained generation of recommendations.
Approach:	They propose a taxonomy-guided recommendation framework that empowers LLMs with category information in a systematic approach.
Outcome:	The proposed framework significantly improves recommendation quality compared to zero-shot approaches.

Copied to clipboard

Yiming Wang, Yang Liu, Lingchen Wang, An Xiao

Large-Scale Multimodal Knowledge Graph about Classical Chinese Poetry: Fine-grained Method and Comprehensive Evaluation (2026.findings-acl)

Challenge:	Collecting high-quality question-answer (QA) pairs is vital for training large language models, but computational demands and associated costs often render such approaches prohibitive for the average researcher.
Approach:	They propose a small-scaled, open-source solution that generates QA pairs from documents or raw corpora using large-scale models like Llama-70B.
Outcome:	Experiments on domain-specific datasets show that the proposed model can generate high-quality QA pairs, making it accessible to a broader range of researchers.

Copied to clipboard

Shuo Wang, Qing Zhu, Yang Xiao, Minglong Lei

Reasoning-Enhanced Domain-Adaptive Pretraining of Multimodal Large Language Models for Short Video Content Governance (2025.emnlp-industry)

Challenge:	Existing studies on classical Chinese poetry are limited by modality constraints, dataset size, or the level of refinement.
Approach:	They propose to construct a large-scale and fine-grained multimodal knowledge graph of classical Chinese poetry using an informative ontology graph and a text-image alignment method.
Outcome:	The proposed method collects knowledge about classical Chinese poetry from ontology graphs and performs four tasks that demonstrate its comprehensiveness and high quality.

Copied to clipboard

Zixuan Wang, Yu Sun, Hongwei Wang, Baoyu Jing, Xiang Shen, Xin Dong, Zhuolin Hao, Hongyu Xiong, Yang Song

Understanding and Mitigating Bias Inheritance in LLM-based Data Augmentation on Downstream Tasks (2026.acl-long)

Challenge:	Existing approaches to identifying inappropriate content require extensive human-labeled data and lack cross-issue generalization.
Approach:	They propose a reasoning-enhanced multimodal large language model (MLLM) pretraining paradigm for unified inappropriate content detection.
Outcome:	The proposed model improves the MLLM's performance in both zero-shot and supervised fine-tuning settings and shows strong generalization capabilities to emergent, previously unseen issues.

Copied to clipboard

Miaomiao Li, Hao Chen, Yang Wang, Tingyuan Zhu, Weijia Zhang, Kaijie Zhu, Kam-Fai Wong, Jindong Wang

Language Scaling for Universal Suggested Replies Model (2021.naacl-industry)

Challenge:	Generating synthetic datasets via large language models (LLMs) has emerged as promising approach to improve LLM performance.
Approach:	They propose three mitigation strategies to mitigate bias inheritance in LLMs by analyzing real and LLM-augmented data.
Outcome:	The proposed methods can work differently on different tasks and biases.

Copied to clipboard

Qianlan Ying, Payal Bajaj, Budhaditya Deb, Yu Yang, Wei Wang, Bojia Lin, Milad Shokouhi, Xia Song, Yang Yang, Daxin Jiang

Confidence v.s. Critique: A Decomposition of Self-Correction Capability for LLMs (2025.acl-long)

Challenge:	We consider scaling automated suggested replies (SR) to multiple languages for a commercial email application.
Approach:	They propose a multi-lingual multi-task continual learning framework with auxiliary tasks and language adapters to train universal language representation across regions.
Outcome:	The proposed model reduces catastrophic forgetting and improves cross-lingual transfer across languages while reducing training costs.

Copied to clipboard

Zhe Yang, Yichang Zhang, Yudong Wang, Ziyao Xu, Junyang Lin, Zhifang Sui

Challenge:	Existing approaches to improve self-correction performance of Large Language Models are based on intrinsic selfcorrectione, which allows the model to check and revise its selfgenerated answers without external feedback.
Approach:	They propose to decompose the self-correction capability into confidence and critique capabilities and a metric for overall self-corretion capability evaluation.
Outcome:	The proposed method outperforms vanilla SFT and achieves much higher accuracy after self-correction.

Path-enhanced Pre-trained Language Model for Knowledge Graph Completion (2025.findings-emnlp)

Copied to clipboard

Hao Wang, Dandan Song, Zhijing Wu, Yuhang Tian, Pan Yang

Beyond Single Frames: Can LMMs Comprehend Implicit Narratives in Comic Strip? (2025.findings-emnlp)

Challenge:	Pre-trained language models have achieved remarkable knowledge graph completion (KGC) success.
Approach:	They propose a path-enhanced pre-trained language model-based knowledge graph completion method which uses multi-view generation to infer missing facts in triple-level and path-level simultaneously.
Outcome:	The proposed method significantly improves the performance of the knowledge graph completion task.

Copied to clipboard

Xiaochen Wang, Heming Xia, Jialin Song, Longyu Guan, Qingxiu Dong, Rui Li, Yixin Yang, Yifan Pu, Weiyao Luo, Yiru Wang, Xiangdi Meng, Wenjie Li, Zhifang Sui

AutoMonitor-Bench: Evaluating the Reliability of LLM-Based Misbehavior Monitor (2026.findings-acl)

Challenge:	Large Multimodal Models have demonstrated strong performance on vision-language benchmarks, yet current evaluations focus on single-image reasoning.
Approach:	STRIPCIPHER is a benchmark designed to evaluate model ability on understanding implicit narratives in silent comics.
Outcome:	STRIPCIPHER is a high-quality, human-annotated dataset featuring fine-grained annotations and comprehensive coverage of varying difficulty levels.

Copied to clipboard

Shu Yang, Jingyu Hu, Tong Li, Hanqi Yan, Wenxuan Wang, Di Wang

Challenge:	AutoMonitor-Bench evaluates the reliability of LLM-based misbehavior monitors across diverse tasks and failure modes.
Approach:	They introduce AutoMonitor-Bench, a benchmark designed to evaluate misbehavior monitors across diverse tasks and failure modes.
Outcome:	The new benchmark evaluates the reliability of LLM-based misbehavior monitors across tasks and failure modes.

Decode with Template: Content Preserving Sentiment Transfer (2020.lrec-1)

Copied to clipboard

Zhiyuan Wen, Jiannong Cao, Ruosong Yang, Senzhang Wang

Towards Hierarchical Multi-Step Reward Models for Enhanced Reasoning in Large Language Models (2026.findings-acl)

Challenge:	Existing methods to transfer sentiments for text use only explicit sentiments and templates to remove them from input sentences.
Approach:	They propose a method to transfer sentiments from input sentences to output sentences using templates.
Outcome:	The proposed model significantly outperforms state-of-the-art models in content preservation.

Copied to clipboard

Teng Wang, Jiang Zhangyi, Zhenqi He, Hailei Gong, Shenyang Tong, Wenhan Yang, Zeyu Li, Yanan Zheng, Zifan He, Zewen Ye, Shengjie Ma, Jianping Zhang

Multimodal Fusion with Co-Attention Networks for Fake News Detection (2021.findings-acl)

Challenge:	Existing Process Reward Models (PRMs) are vulnerable to reward hacking and require expensive, large-scale annotation of reasoning steps.
Approach:	They propose a reward model approach which evaluates both individual and consecutive reasoning steps from fine-grained and coarse-grounded level.
Outcome:	Empirical results show that the proposed model performs better than existing PRMs and is more robust than existing models.

Copied to clipboard

Yang Wu, Pengwei Zhan, Yunjian Zhang, Liming Wang, Zhen Xu

ReasoningGuard: Safeguarding Large Reasoning Models with Inference-time Safety Aha Moments (2026.acl-long)

Challenge:	Existing methods to detect fake news with textual and visual contents are ineffective because they concatenate unimodal features without considering inter-modality relations.
Approach:	They propose to fuse textual and visual features for fake news detection using multimodal co-attention networks to learn inter-dependencies between multimodal features.
Outcome:	Extensive experiments on two realworld datasets show that the proposed network outperforms state-of-the-art methods and learns inter-dependencies among multimodal features.

Copied to clipboard

Yuquan Wang, Mi Zhang, Yining Wang, Geng Hong, Mi Wen, Xiaoyu You, Min Yang

Large Language Models as Source Planner for Personalized Knowledge-grounded Dialogues (2023.findings-emnlp)

Challenge:	Existing defenses for Large Reasoning Models (LRMs) depend on costly fine-tuning and additional expert knowledge, which limits their scalability.
Approach:	They propose an inference-time safeguard for Large Reasoning Models that injects safety aha moments into the reasoning process to guide the model towards harmless yet helpful reasoning.
Outcome:	The proposed safeguard outperforms nine existing safeguards while avoiding common exaggerated safety issues.

Copied to clipboard

Hongru Wang, Minda Hu, Yang Deng, Rui Wang, Fei Mi, Weichao Wang, Yasheng Wang, Wai-Chung Kwan, Irwin King, Kam-Fai Wong

Examining False Positives under Inference Scaling for Mathematical Reasoning (2025.emnlp-main)

Challenge:	Existing knowledge-grounded dialogue systems focus on a single knowledge source or ignore the dependency between multiple knowledge sources.
Approach:	They propose a framework that integrates multiple knowledge sources and dependencies between them.
Outcome:	The proposed framework can produce persona-consistent and knowledge-enhanced responses on a knowledge-grounded dialogue dataset.

Copied to clipboard

Yu Wang, Nan Yang, Liang Wang, Furu Wei, Fuli Feng

Guiding not Forcing: Enhancing the Transferability of Jailbreaking Attacks on LLMs via Removing Superfluous Constraints (2025.acl-long)

Challenge:	Recent advances in language models have led to significant improvements in mathematical reasoning across benchmarks.
Approach:	They analyze the prevalence of false positives in language models by using heuristic evaluation methods . they find that false positive models produce correct final answers but with flawed deduction paths .
Outcome:	The proposed model performance improvements are based on the proposed model and its evaluation metrics.

Copied to clipboard

Junxiao Yang, Zhexin Zhang, Shiyao Cui, Hongning Wang, Minlie Huang

Evaluating Memory Capability in Continuous Lifelog Scenario (2026.findings-acl)

Challenge:	Jailbreaking attacks can effectively induce unsafe behaviors in Large Language Models (LLMs).
Approach:	They propose a conceptual framework to elucidate transferability of gradient-based jailbreaking methods . they identify superfluous constraints as significant barriers to improved transferability .
Outcome:	The proposed method increases the overall transfer attack success rate (T-ASR) across target and source models with varying safety levels from 18.4% to 50.3% while improving stability and controllability of jailbreak behaviors.

Copied to clipboard

Jianjie Zheng, Zhichen Liu, Zhanyu Shen, Jingxiang Qu, Guanhua Chen, Yile Wang, Yang Xu, Yang Liu, Sijie Cheng

Challenge:	Existing benchmarks focus on online one-on-one chatting or human-AI interactions, neglecting real-world scenarios.
Approach:	They propose a framework to curate a lifelog benchmark that combines two subsets of audio data to address temporal leakage in offline settings.
Outcome:	The proposed framework outperforms existing benchmarks on live chats and AI interactions.

Instance-Guided Prompt Learning for Few-Shot Text Matching (2022.findings-emnlp)

Copied to clipboard

Jia Du, Xuanyu Zhang, Siyi Wang, Kai Wang, Yanquan Zhou, Lei Li, Qing Yang, Dongliang Xu

WR-One2Set: Towards Well-Calibrated Keyphrase Generation (2022.emnlp-main)

Challenge:	Few-shot text matching is a more practical technique to determine whether two texts are semantically identical.
Approach:	They propose a pluggable prompt learning method for few-shot text matching . they use the semantics of instances to regulate the effects of the gate on the prompt tokens .
Outcome:	The proposed method outperforms baselines on MRPC and QQP.

Copied to clipboard

Binbin Xie, Xiangpeng Wei, Baosong Yang, Huan Lin, Jun Xie, Xiaoli Wang, Min Zhang, Jinsong Su

Towards a Better Understanding of Label Smoothing in Neural Machine Translation (2020.aacl-main)

Challenge:	Experimental results show that keyphrase generation has serious calibration errors . ONE2SET generates short phrases summarizing an input document .
Approach:	They propose a paradigm for keyphrase generation that generates short phrases summarizing an input document.
Outcome:	The proposed model over-estimates tokens and makes it well-calibrated on common datasets.

Copied to clipboard

Yingbo Gao, Weiyue Wang, Christian Herold, Zijian Yang, Hermann Ney

GenPT: Beyond Self-Report for Reliable LLM Psychometrics via Generative Projective Testing (2026.acl-long)

Challenge:	In recent years, Neural Network (NN) models bring steady and concrete improvements on the task of Machine Translation (MT).
Approach:	They propose to penalize over-confident outputs and regularize the model so that its outputs do not diverge too much from some prior distribution.
Outcome:	The proposed method is well-motivated and can improve the performance of strong neural machine translation systems.

Copied to clipboard

Ming Wang, Shuang Wu, Bixuan Wang, Lu Lin, Yuxin Chen, Xiaocui Yang, Daling Wang, Shi Feng, Yifei Zhang, Yufan Sun

Challenge:	Large language models (LLMs) inherit contamination from training corpora, directional bias under social-desirability framing, and limited responsiveness to context beyond the item text.
Approach:	They propose a paradigm that reformulates TAT, Rorschach, and SCT with newly generated stimuli and organises assessment as a three-stage pipeline.
Outcome:	The proposed paradigm reformulates TAT, Rorschach, and SCT with newly generated stimuli and organises assessment as a three-stage pipeline.

SPIDE: Serial and Parallel Intertwined Speculative Decoding (2026.findings-acl)

Copied to clipboard

Wenru Xu, Peixuan Xu, Ziqi Yang, Ming Hu, Zihui Wang, Jianzhong Qi, Rongshan Yu, Xiaoliang Fan, Cheng Wang

Predicting and Using Target Length in Neural Machine Translation (2020.aacl-main)

Challenge:	Speculative decoding (SD) is a training-free SD framework that orchestrates dynamic alternation combining serial dynamic drafting with parallel draft verification.
Approach:	They propose a serial and parallel intertwined speculative DEcoding framework that orchestrates dynamic alternation combining serial dynamic drafting and parallel draft verification.
Outcome:	The proposed framework accelerates inference while reducing the LLM usage costs.

Copied to clipboard

Zijian Yang, Yingbo Gao, Weiyue Wang, Hermann Ney

SDA: Semantic Discrepancy Alignment for Text-conditioned Image Retrieval (2024.findings-acl)

Challenge:	Current NMT systems do not model the length of the output explicitly . length normalization is a common technique used in the beam search of NMT to enable a fair comparison of partial hypotheses with different lengths.
Approach:	They propose to use length prediction as an auxiliary task to obtain length information from the encoder.
Outcome:	The proposed sub-network improves over the baseline system and the predicted length can be used as an alternative to length normalization during decoding.

Copied to clipboard

Yuchen Yang, Yu Wang, Yanfeng Wang

Token-Aware Editing of Internal Activations for Large Language Model Alignment (2025.emnlp-main)

Challenge:	Existing methods for textconditioned image retrieval are limited due to the scale of training and the complexity of attributes in modification texts.
Approach:	They propose a general boosting framework to address these issues by employing semantic discrepancy alignment by formulating distance consistency and neighbor consistency between the image and text domains.
Outcome:	The proposed framework improves retrieval performance on three prominent datasets with state-of-the-art results.

Copied to clipboard

Tianbo Wang, Yuqing Ma, Kewei Liao, Chengzhao Yang, Zhange Zhang, Jiakai Wang, Xianglong Liu

On Safety Risks in Experience-Driven Self-Evolving Agents (2026.findings-acl)

Challenge:	Existing methods to optimize the behavior of large language models neglect misalignment discrepancies among tokens, resulting in deviant alignment direction and inflexible editing strength.
Approach:	They propose a token-aware editing approach to exploit the misalignment discrepancy among tokens to enhance activation probing and facilitate intervention.
Outcome:	Extensive experiments on three alignment capabilities demonstrate the efficacy of the proposed approach surpassing baseline by 25.8% on the primary metric of truthfulness with minimal cost.

Copied to clipboard

Weixiang Zhao, Yichen Zhang, Yingshuo Wang, Yang Deng, Yanyan Zhao, Xuda Zhi, Yongbo Huang, Hao He, Wanxiang Che, Bing Qin, Ting Liu

Challenge:	Experience-driven self-evolution has emerged as a promising paradigm for improving the autonomy of large language model agents, yet its reliance on self-curated experience introduces underexplored safety risks.
Approach:	They investigate how experience accumulation and utilization in self-evolving agents affect safety performance across web-based and embodied environments.
Outcome:	The findings expose inherent limitations of current self-evolving agents and call for more principled strategies to ensure safe and reliable adaptation.

The Role of Visual Modality in Multimodal Mathematical Reasoning: Challenges and Insights (2025.acl-long)

Copied to clipboard

Yufang Liu, Yao Du, Tao Ji, Jianing Wang, Yang Liu, Yuanbin Wu, Aimin Zhou, Mengdi Zhang, Xunliang Cai

Time-RA: Towards Time Series Reasoning for Anomaly Diagnosis with LLM Feedback (2026.findings-acl)

Challenge:	Existing models that leverage visual information do not improve math reasoning performance . authors suggest that visual information is important for multimodal reasoning .
Approach:	They propose a dataset to require image reliance for problem-solving and challenge models with similar, yet distinct, images that change the correct answer.
Outcome:	The proposed model performance is unaffected by changes to or removal of images in the dataset.

Copied to clipboard

Yiyuan Yang, Zichuan Liu, Lei Song, Kai Ying, Stephen Wang, Joshua Thomas Bamford, Svitlana Vyetrenko, Jiang Bian, Qingsong Wen

Enhancing the Transferability of Jailbreak Attacks on Large Language Models via Exploiting Reparameterization Invariance (2026.acl-long)

Challenge:	Time series anomaly detection (TSAD) has traditionally focused on binary classification and lacks the fine-grained categorization and explanatory reasoning required for transparent decision-making.
Approach:	They propose a time-series reasoning task that reformulates TSAD from discriminative to reasoning-intensive paradigm.
Outcome:	The proposed task reformulates TSAD from discriminative to reasoning-intensive paradigm.

Copied to clipboard

Ao Wang, Xinghao Yang, Yongshun Gong, Wei Liu, Bao-di Liu, Weifeng Liu

Can Language Models Follow Multiple Turns of Entangled Instructions? (2025.findings-emnlp)

Challenge:	Existing token-level attacks have shown efficacy on open-source models but suffer from poor cross-model transferability.
Approach:	They propose a framework to improve cross-model transferability by modifying model parameters and generating update directions according to differences in output distributions rather than parameter-space distances.
Outcome:	The proposed framework improves cross-model transferability and success rates on open-source models.

Copied to clipboard

Chi Han, Xin Liu, Haodong Wang, Shiyang Li, Jingfeng Yang, Haoming Jiang, Zhengyang Wang, Qingyu Yin, Liang Qiu, Changlong Yu, Yifan Gao, Zheng Li, Bing Yin, Jingbo Shang, Heng Ji

ChangJuan: A Comprehensive Benchmark for Book-Length Chinese Story Evaluation (2026.findings-acl)

Challenge:	Despite of significant achievements in improving instruction-following capabilities of large language models, the ability to process multiple potentially entangled or conflicting instructions remains a considerable challenge.
Approach:	They construct multi-turn instruction with 1.1K high-quality multi-turned conversations using the human-in-the-loop approach and examine their capabilities.
Outcome:	The proposed model shows that it is difficult to integrate multiple turns and balance competing objectives when instructions intersect or conflict.

Copied to clipboard

Dingyi Yang, Mingshuo Wang, Qin Jin

GLUE-X: Evaluating Natural Language Understanding Models from an Out-of-Distribution Generalization Perspective (2023.findings-acl)

Challenge:	Recent advances in Large Language Models (LLMs) have significantly enhanced the capacity of Automatic Story Evaluation.
Approach:	They propose a method to distill raw reviews into generally agreed viewpoints across key evaluation aspects such as plot and character.
Outcome:	The proposed model outperforms open-source baselines and raises Qwen3’s Kendall’s tau correlation with human judgments from 24.8 to 34.1.

Copied to clipboard

Linyi Yang, Shuibai Zhang, Libo Qin, Yafu Li, Yidong Wang, Hanmeng Liu, Jindong Wang, Xing Xie, Yue Zhang

LogicAsker: Evaluating and Improving the Logical Reasoning Ability of Large Language Models (2024.emnlp-main)

Challenge:	Pre-trained language models (PLMs) have improved generalization performance but the out-of-distribution (OOD) generalization problem remains a challenge in many NLP tasks.
Approach:	They propose to create a benchmark for evaluating out-of-distribution (OOD) generalization in NLP models.
Outcome:	The proposed benchmarks highlight the importance of OOD robustness and provide insights on how to measure it and improve it.

Copied to clipboard

Yuxuan Wan, Wenxuan Wang, Yiliu Yang, Youliang Yuan, Jen-tse Huang, Pinjia He, Wenxiang Jiao, Michael Lyu

V-RoLoRA: RLVR-Driven MoE Routing for Steerable Pluralistic Alignment (2026.findings-acl)

Challenge:	LogicAsker examines and improves the reasoning abilities of large language models such as ChatGPT and GPT-4.
Approach:	They propose a set of atomic reasoning skills grounded in propositional and predicate logic to examine and improve the reasoning abilities of large language models such as ChatGPT and GPT-4.
Outcome:	The proposed approach improves reasoning abilities in large language models such as ChatGPT and GPT-4 by up to 5%.

Copied to clipboard

Jing Wang, Yaomin Wu, Yinglin Wang, Yitong Yang

LoRA-drop: Efficient LoRA Parameter Pruning based on Output Evaluation (2025.coling-main)

Challenge:	Current methods for steering large language models rely on prompt engineering or reasoning-time guidance.
Approach:	They propose a value-controllable pluralistic alignment framework enhanced with conditioned gating that dynamically directs the flow among multiple experts based on an input value or moral vector.
Outcome:	The proposed method outperforms prompt-based steering and multi-task PEFT benchmarks on two 8-billion-parameter backbones.

Copied to clipboard

Hongyun Zhou, Xiangyu Lu, Wang Xu, Conghui Zhu, Tiejun Zhao, Muyun Yang

Drivel-ology: Challenging LLMs with Interpreting Nonsense with Depth (2025.emnlp-main)

Challenge:	Low-Rank Adaptation (LoRA) is currently the most commonly used PEFT method for fine-tuning models with billions of parameters.
Approach:	They propose to use low-rank Adaptation to evaluate LoRA parameter features and then retain LoRA for important layers and the other layers share the same LoRA.
Outcome:	The proposed method achieves comparable performance to full fine-tuning and LoRA while retaining 50% of the LoRA parameters on average.

Copied to clipboard

Yang Wang, Chenghao Xiao, Chia-Yi Hsiao, Zi Yan Chang, Chi-Li Chen, Tyler Loakman, Chenghua Lin

Multi-Level Cross-Modal Alignment for Speech Relation Extraction (2024.emnlp-main)

Challenge:	Despite excelling at many natural language processing tasks, large language models fail to grasp the layered semantics of Drivelological text.
Approach:	They construct a benchmark dataset of over 1,200+ carefully curated and diverse examples across English, Mandarin, Spanish, French, Japanese, and Korean to examine their Drivelological characteristics.
Outcome:	The proposed models lack conceptual understanding and lack conceptual and semantic accuracy.

Copied to clipboard

Liang Zhang, Zhen Yang, Biao Fu, Ziyao Lu, Liangying Shao, Shiyu Liu, Fandong Meng, Jie Zhou, Xiaoli Wang, Jinsong Su

C-ICL: Contrastive In-context Learning for Information Extraction (2024.findings-emnlp)

Challenge:	Existing studies use synthetic speech to train and evaluate SpeechRE models, hindering their development . modality gap issue limits performance of existing models, limiting future researches .
Approach:	They propose to use speech data to train and evaluate SpeechRE models by using real speech . they propose to train a cross-modal alignment model to bridge the modality gap .
Outcome:	The proposed model can train to bridge the modality gap between speech encoder and text decoder . the proposed model is based on two real SpeechRE datasets .

Copied to clipboard

Ying Mo, Jiahao Liu, Jian Yang, Qifan Wang, Shun Zhang, Jingang Wang, Zhoujun Li

STAD: Self-Training with Ambiguous Data for Low-Resource Relation Extraction (2022.coling-1)

Challenge:	Existing methods for in-context learning with large language models focus on using correct or negative examples, ignoring the potential value of incorrect or negative samples.
Approach:	They propose a few-shot technique that leverages both correct and incorrect sample constructions to create in-context learning demonstrations.
Outcome:	The proposed technique outperforms previous few-shot in-context learning methods on a broad spectrum of related tasks.

Copied to clipboard

Junjie Yu, Xing Wang, Jiangjiang Zhao, Chunjie Yang, Wenliang Chen

AgentThink: A Unified Framework for Tool-Augmented Chain-of-Thought Reasoning in Vision-Language Models for Autonomous Driving (2025.findings-emnlp)

Challenge:	Existing approaches for low-resource relation extraction use only confident instances and uncertain instances.
Approach:	They propose a self-training approach for low-resource relation extraction using auto-annotated instances.
Outcome:	The proposed method improves on two widely used datasets with low-resource settings.

Copied to clipboard

Kangan Qian, Sicong Jiang, Yang Zhong, Ziang Luo, Zilin Huang, Tianze Zhu, Kun Jiang, Mengmeng Yang, Zheng Fu, Jinyu Miao, Yining Shi, He Zhe Lim, Li Liu, Tianbao Zhou, Hongyi Wang, Huang Yu, Yifei Hu, Guang Li, Guang Chen, Hao Ye, Lijun Sun, Diange Yang

Knowledge Graph Embedding by Adaptive Limit Scoring Loss Using Dynamic Weighting Strategy (2022.findings-acl)

Challenge:	Vision-Language Models struggle with hallucinations, inefficient reasoning, and limited real-world validation hinders accurate perception and robust step-by-step reasoning.
Approach:	AgentThink integrates Chain-of-Thought reasoning with dynamic, agent-style tool invocation for autonomous driving tasks.
Outcome:	Experiments on the DriveLMM-o1 benchmark show AgentThink significantly boosts overall reasoning scores by 53.91% and enhances answer accuracy by 33.54% .

Copied to clipboard

Jinfa Yang, Xianghua Ying, Yongjie Shi, Xin Tong, Ruibin Wang, Taiyan Chen, Bowei Xing

LoraRetriever: Input-Aware LoRA Retrieval and Composition for Mixed Tasks in the Wild (2024.findings-acl)

Challenge:	Existing knowledge graph embedding models use a loss framework to distinguish between correct and incorrect triplets.
Approach:	They propose a loss framework that reweights each triplet to highlight the less-optimized triplets.
Outcome:	The proposed method performs on several knowledge graph embedding models, including TransE, TransH and ComplEx.

Copied to clipboard

Ziyu Zhao, Leilei Gan, Guoyin Wang, Wangchunshu Zhou, Hongxia Yang, Kun Kuang, Fei Wu

PACE: Prefix-Protected and Difficulty-Aware Compression for Efficient Reasoning (2026.findings-acl)

Challenge:	Low-Rank Adaptation (LoRA) is an effective yet efficient solution for fine-tuning large language models.
Approach:	They propose a low-rank Adaptation framework that retrieves and composes multiple LoRAs according to input prompts.
Outcome:	Experimental results show that LoraRetriever outperforms baselines in terms of performance and versatility.

Copied to clipboard

Ruixiang Feng, Yuntao Wen, Silin Zhou, Ke Shi, Yifan Wang, Ran Le, Zhenwei An, Zongchao Chen, Chen Yang, Guangyue Peng, Yiming Jia, Dongsheng Wang, Tao Zhang, Lisi Chen, Yang Song, Shen Gao, Shuo Shang

Pengwei Zhan, Jing Yang, He Wang, Chao Zheng, Xiao Huang, Liming Wang

Challenge:	Existing LRMs often suffer from "overthinking" and excessively long reasoning traces . a dual-level framework for length compression of LRM is proposed .
Approach:	They propose a framework for prefix-protected and difficulty-aware compression under hierarchical supervision.
Outcome:	The proposed framework reduces token usage while improving accuracy on math benchmarks.

Copied to clipboard

A Framework of Knowledge Graph-Enhanced Large Language Model Based on Question Decomposition and Atomic Retrieval (2024.findings-emnlp)

Challenge:	Neural language models are vulnerable to word-level adversarial text attacks . previous word-based search methods assume important words influence prediction .
Approach:	They propose a method for similarizing the influence of words with contrast learning that encourages model to learn sentence representations in which words of varying importance have a more uniform influence on prediction.
Outcome:	The proposed method is compatible with various training methods and improves model robustness against various adversarial attacks.

Copied to clipboard

Yading Li, Dandan Song, Changzhi Zhou, Yuhang Tian, Hao Wang, Ziyi Yang, Shuhao Zhang

Assessing the Ability of Self-Attention Networks to Learn Word Order (P19-1)

Challenge:	Existing methods to enhance LLMs with knowledge graphs have limited results . knowledge graph question answering (KGQA) provides interpretable reasoning for large language models .
Approach:	They propose a framework for KG-enhanced LLM based on question decomposition and atomic retrieval . they propose question decomposing tree as framework for LLM reasoning .
Outcome:	The proposed framework outperforms existing reasoning-based baselines on KGQA datasets.

Copied to clipboard

Baosong Yang, Longyue Wang, Derek F. Wong, Lidia S. Chao, Zhaopeng Tu

RECALL: REpresentation-aligned Catastrophic-forgetting ALLeviation via Hierarchical Model Merging (2025.emnlp-main)

Challenge:	Existing studies have attributed SAN to being weak at learning positional information for sequence modeling due to lack of recurrence structure.
Approach:	They propose a word reordering detection task to quantify how well word order information is learned by SAN and RNN.
Outcome:	The proposed task quantifies how well word order information learned by SAN and RNN is learned.

Copied to clipboard

Bowen Wang, Haiyuan Wan, Liwen Shi, Chen Yang, Peng He, Yue Ma, Haochen Han, Wenhao Li, Tiao Tan, Yongjian Li, Fangming Liu, Gong Yifan, Sheng Zhang

Step-by-Step: Controlling Arbitrary Style in Text with Large Language Models (2024.lrec-main)

Challenge:	Existing models that require task labels or performance trade-offs are susceptible to catastrophic forgetting.
Approach:	They propose a representation-aware model merging framework for continual learning without access to historical data.
Outcome:	The proposed framework outperforms baselines in knowledge retention and generalization across five NLP tasks and multiple continual learning scenarios.

Copied to clipboard

Pusheng Liu, Lianwei Wu, Linyong Wang, Sensen Guo, Yang Liu

LongLeader: A Comprehensive Leaderboard for Large Language Models in Long-context Scenarios (2025.naacl-long)

Challenge:	Existing methods for autoregressive text generation have low controllability and accumulating errors.
Approach:	They propose a three-stage prompt-based approach to express autoregressive text in a specific region editing task using a word frequency-based strategy.
Outcome:	Experiments on publicly competitive datasets confirm that the proposed approach achieves state-of-the-art performance.

Copied to clipboard

Pei Chen, Hongye Jin, Cheng-Che Lee, Rulin Shao, Jingfeng Yang, Mingyu Zhao, Zhaoyu Zhang, Qin Lu, Kaiwen Men, Ning Xie, Huasheng Li, Bing Yin, Han Li, Lingyun Wang

SyntaxSQLNet: Syntax Tree Networks for Complex and Cross-Domain Text-to-SQL Task (D18-1)

Challenge:	LongLeader aims to assess different LLMs' long-context comprehension abilities . long-constext comprehension is a key bottleneck for many use cases .
Approach:	They propose a leaderboard to assess different LLMs' long-context comprehension abilities . they offer open-source access to the benchmarks and maintain a dedicated website .
Outcome:	The proposed model assesses different LLMs on selected benchmarks and provides open-source access to the benchmarks.

Copied to clipboard

Tao Yu, Michihiro Yasunaga, Kai Yang, Rui Zhang, Dongxu Wang, Zifan Li, Dragomir Radev

Model Surgery: Modulating LLM’s Behavior Via Simple Parameter Editing (2025.naacl-long)

Challenge:	Existing studies in text-to-SQL do not require generating complex SQL queries with multiple clauses or sub-queries.
Approach:	They propose a syntax tree network to address the complex text-to-SQL generation task.
Outcome:	The proposed model outperforms the current state-of-the-art model by 9.5% on a large text-to-SQL corpus.

Copied to clipboard

Huanqian Wang, Yang Yue, Rui Lu, Jingxin Shi, Andrew Zhao, Shenzhi Wang, Shiji Song, Gao Huang

Challenge:	Current approaches for detoxification or preventing jailbreaking involve fine-tuning billions of parameters through gradient descent with substantial computational cost.
Approach:	They propose to use supervised fine-tuning and Reinforcement Learning from human feedback to modify LLMs' behavior by directly editing a small subset of parameters.
Outcome:	Experiments show that editing a small subset of parameters can modulate specific behaviors of LLMs, such as detoxification and resistance to jailbreak, with only inference-level computational resources.

Improving Pacing in Long-Form Story Planning (2023.findings-emnlp)

Copied to clipboard

Yichen Wang, Kevin Yang, Xiaoming Liu, Dan Klein

Challenge:	Existing systems for writing long-form stories suffer from unnatural pacing, whether glossing over important events or over-elaborating on insignificant details.
Approach:	They propose a system that uses a concreteness evaluator to judge which of two events is more concrete.
Outcome:	The proposed system improves pacing when automatically generating story outlines.

SERM: Self-Evolving Relevance Model with Agent-Driven Learning from Massive Query Streams (2026.findings-acl)

Copied to clipboard

Chenglong Wang, Canjia Li, Xingzhao Zhu, Yifu Huo, Huiyu Wang, Weixiong Lin, Yun Yang, Qiaozhi He, Tian Hua Zhou, null Changxiaojia, JingBo Zhu, Tong Xiao

Challenge:	Existing approaches to generate relevance judgments are limited due to dynamic nature of query distributions.
Approach:	They propose a self-evolving relevance model approach to generalize queries to practical search scenarios . they use a multi-agent sample miner and a relevance annotator to generate reliable labels .
Outcome:	The proposed approach can achieve significant performance gains on a large-scale industrial platform, validated by offline multilingual evaluations and online testing.

Clustering-Aware Negative Sampling for Unsupervised Sentence Representation (2023.findings-acl)

Copied to clipboard

Jinghao Deng, Fanqi Wan, Tao Yang, Xiaojun Quan, Rui Wang

Detoxifying Large Language Models via Knowledge Editing (2024.acl-long)

Challenge:	Using clustering-aware learning, in-batch negatives are often ignored in sentence representation learning.
Approach:	They propose a method that integrates cluster information into contrastive learning for unsupervised sentence representation learning.
Outcome:	The proposed method compares favorably with baselines on semantic textual similarity tasks.

Copied to clipboard

Mengru Wang, Ningyu Zhang, Ziwen Xu, Zekun Xi, Shumin Deng, Yunzhi Yao, Qishen Zhang, Linyi Yang, Jindong Wang, Huajun Chen

Agentic Episodic Control (2026.findings-acl)

Challenge:	Existing methods to detoxify Large Language Models (LLMs) are limiting, but knowledge editing can be effective.
Approach:	They propose a baseline method to detoxify Large Language Models (LLMs) they propose supervised fine-tuning and reinforcement learning from human feedback (RLHF)
Outcome:	The proposed method reduces toxicity of large language models with one instance of tuning . it reduces the toxicity, while minimizing the toxins, the authors show .

Copied to clipboard

Xidong Yang, Wenhao Li, Junjie Sheng, Yun Hua, Haosheng Chen, Chuyun Shen, Xiangfeng Wang

LogicPro: Improving Complex Logical Reasoning via Program-Guided Learning (2025.acl-long)

Challenge:	Existing methods for reinforcement learning (RL) are limited by poor data efficiency and weak generalization.
Approach:	They propose a novel architecture that integrates large language models into episodic RL.
Outcome:	The proposed architecture achieves 2–6 higher data efficiency than baselines and is the only method to solve complex tasks like UnlockLocal with over 90% success.

Copied to clipboard

Jin Jiang, Yuchen Yan, Yang Liu, Jianing Wang, Shuai Peng, Xunliang Cai, Yixin Cao, Mengdi Zhang, Liangcai Gao

Cue-CoT: Chain-of-thought Prompting for Responding to In-depth Dialogue Questions with LLMs (2023.findings-emnlp)

Challenge:	LogicPro is a data synthesis method that uses LeetCode-style algorithm problems and their corresponding Program solutions to generate complex logic data.
Approach:	They propose a new method which leverages LeetCode-style algorithm Problems and their corresponding Program solutions to synthesize complex logic data in text format.
Outcome:	The proposed method outperforms existing models for BBH27, LogicBench, DROP, AR-LSAT, and GSM8K, and a wide range of reasoning datasets.

Copied to clipboard

Hongru Wang, Rui Wang, Fei Mi, Yang Deng, Zezhong Wang, Bin Liang, Ruifeng Xu, Kam-Fai Wong

Mulan: A Multi-Level Alignment Model for Video Question Answering (2023.findings-emnlp)

Challenge:	Existing LLMs generate responses based on the dialogue context, overlooking the underlying linguistic cues about the user status exhibited in the context.
Approach:	They propose a linguistic cue-based chain-of-thoughts method which enhances the LLMs inference with an intermediate reasoning step to find cues exhibited in the dialogue.
Outcome:	The proposed method outperforms standard prompting methods on in-depth dialogue questions and linguistic cues exhibited in the context.

Copied to clipboard

Yu Fu, Cong Cao, Yuling Yang, Yuhai Lu, Fangfang Yuan, Dakui Wang, Yanbing Liu

DEEM: Dynamic Experienced Expert Modeling for Stance Detection (2024.lrec-main)

Challenge:	Existing methods focus on visual-language alignment at the video level, but they do not account for fine-grained semantic interaction between video and text.
Approach:	They propose a multi-level Alignment Model for Video Question Answering that establishes alignment between visual and textual modalities at the object-level, frame-level and video-level.
Outcome:	The proposed model outperforms state-of-the-art methods even with a small amount of extra visual-language pre-training data and a reduced number of trainable parameters.

Copied to clipboard

Xiaolong Wang, Yile Wang, Sijie Cheng, Peng Li, Yang Liu

ProLongVid: A Simple but Strong Baseline for Long-context Video Instruction Tuning (2025.emnlp-main)

Challenge:	Existing work on stance detection tasks using large language models shows promising results, but it may not be able to provide detailed background knowledge.
Approach:	They propose a method which leverages the generated experienced experts and lets LLMs reason in a semi-parametric way.
Outcome:	The proposed method outperforms methods with self-consistency reasoning and reduces bias.

Copied to clipboard

Rui Wang, Bohao Li, Xiyang Dai, Jianwei Yang, Yi-Ling Chen, Zhen Xing, Yifan Yang, Dongdong Chen, Xipeng Qiu, Zuxuan Wu, Yu-Gang Jiang

Tackling Modality Heterogeneity with Multi-View Calibration Network for Multimodal Sentiment Detection (2023.acl-long)

Challenge:	Existing approaches to adapt image-focused models for video understanding have not been successful in analyzing long video sequences.
Approach:	They propose a video instruction dataset that outperforms existing video instruction data for fine-tuning MLLMs by incrementally increasing input context length.
Outcome:	The proposed model outperforms existing models on video benchmarks and outperformed proprietary models on VideoMME even with a compact 7B model.

Copied to clipboard

Yiwei Wei, Shaozu Yuan, Ruosong Yang, Lei Shen, Zhangmeizhi Li, Longbiao Wang, Meng Chen

On the Sub-layer Functionalities of Transformer Decoder (2020.findings-emnlp)

Challenge:	Existing studies focus on fusing different features but ignore the challenge of modality heterogeneity.
Approach:	They propose a text-guided fusion module with novel Sparse-Attention to reduce the negative impacts of redundant visual elements and a sentiment-based congruity constraint task to calibrate the feature shift in the representation space.
Outcome:	The proposed model is competitive against existing methods and achieves state-of-the-art results on two public benchmark datasets.

Copied to clipboard

Yilin Yang, Longyue Wang, Shuming Shi, Prasad Tadepalli, Stefan Lee, Zhaopeng Tu

Large Language Model for Multi-Domain Translation: Benchmarking and Domain CoT Fine-tuning (2024.findings-emnlp)

Challenge:	Existing efforts to interpret the encoder of Transformer-based encoder-decoder architectures for neural machine translation have focused on assessing the encoded representations or interpreting the multi-head self-attentions.
Approach:	They propose to use Transformer-based encoder-decoder architectures to analyze how information is propagated through each module of each decoder layer.
Outcome:	The proposed model can be dropped with minimal loss of performance on three translation datasets and can be used to train and inference faster.

Copied to clipboard

Tianxiang Hu, Pei Zhang, Baosong Yang, Jun Xie, Derek Wong, Rui Wang

Compressing then Matching: An Efficient Pre-training Paradigm for Multimodal Embedding (2026.acl-long)

Challenge:	Achieving consistent high-quality machine translation across diverse domains remains a challenge due to limited and imbalanced parallel training data available in various domains.
Approach:	They propose a domain Chain of Thought technique that uses the multi-domain intelligence of LLMs to improve translation performance.
Outcome:	The proposed method achieves significant improvements in translation accuracy and domain robustness over traditional fine-tuning on a small dataset of four domains.

Copied to clipboard

Da Li, Yuxiao Luo, Keping Bi, Jiafeng Guo, Wei Yuan, Biao Yang, Yan Wang, Fan Yang, Tingting Gao, Guorui Zhou

DSVD: Dynamic Self-Verify Decoding for Faithful Generation in Large Language Models (2025.emnlp-main)

Challenge:	Recent approaches demonstrate that MLLMs can be adapted into competitive embedding models via large-scale contrastive learning.
Approach:	They propose a compressed pre-training phase which serves as a warm-up stage for contrastive learning.
Outcome:	The proposed model achieves state-of-the-art among MLLMs of comparable size on the MMEB, realizing optimization in both efficiency and effectiveness.

Copied to clipboard

YiQiu Guo, Yuchen Yang, Zhe Chen, Pingjie Wang, Yusheng Liao, Ya Zhang, Yanfeng Wang, Yu Wang

Probability-Consistent Preference Optimization for Enhanced LLM Reasoning (2025.findings-acl)

Challenge:	Existing approaches to reliability of large language models often lack self-correction or use costly post-hoc verification.
Approach:	They propose a decoding framework that enhances generation reliability through real-time hallucination detection and efficient error correction.
Outcome:	Extensive experiments across five benchmarks show the proposed framework improves truthfulness and factual accuracy.

Copied to clipboard

Yunqiao Yang, Houxing Ren, Zimu Lu, Ke Wang, Weikang Shi, Aojun Zhou, Junting Pan, Mingjie Zhan, Hongsheng Li

Joint Knowledge Base Completion and Question Answering by Combining Large Language Models and Small Language Models (2026.acl-long)

Challenge:	Recent advances in preference optimization have demonstrated significant potential for improving mathematical reasoning capabilities in large language models.
Approach:	They propose a framework that establishes two quantitative metrics for preference selection: surface-level answer correctness and intrinsic token-level probability consistency.
Outcome:	The proposed framework outperforms existing outcome-only criterion approaches across a diverse range of LLMs and benchmarks.

Copied to clipboard

Yinan Liu, Dongying Lin, Sigang Luo, Xiaochun Yang, Bin Wang

Syntactic Graph Convolutional Network for Spoken Language Understanding (2020.coling-main)

Challenge:	Existing studies rely on the small language model (SLM) to enhance them jointly, and the large language model’s strong reasoning ability is ignored.
Approach:	They propose a framework which can make knowledge base completion and knowledge base question answering enhance each other in an iterative manner by combining the strengths of the small language model and the large language model.
Outcome:	The proposed framework surpasses baselines for both KBC and KBQA tasks over two public benchmark data sets.

Copied to clipboard

Keqing He, Shuyu Lei, Yushu Yang, Huixing Jiang, Zhongyuan Wang

TOOL-ED: Enhancing Empathetic Response Generation with the Tool Calling Capability of LLM (2025.coling-main)

Challenge:	Existing work on slot filling and intent detection builds joint models without prior knowledge of linguistic knowledge.
Approach:	They propose a joint model that integrates syntactic structure for learning slot filling and intent detection jointly.
Outcome:	The proposed model outperforms existing models on two public benchmark datasets and further improves on slot filling and intent detection.

Copied to clipboard

Huiying Cao, Yiqun Zhang, Shi Feng, Xiaocui Yang, Daling Wang, Yifei Zhang

G-Safeguard: A Topology-Guided Security Lens and Treatment on LLM-based Multi-agent Systems (2025.acl-long)

Challenge:	Empathetic conversation is a crucial characteristic in daily conversations between individuals.
Approach:	They propose an Emotional Knowledge Tool Calling framework which encapsulates commonsense knowledge bases as empathetic tools, enabling LLMs to integrate external knowledge flexibly.
Outcome:	The proposed framework can generate empathetic responses effectively on the TOOL-ED dataset.

Copied to clipboard

Shilong Wang, Guibin Zhang, Miao Yu, Guancheng Wan, Fanci Meng, Chongye Guo, Kun Wang, Yang Wang

Fourier Transformer: Fast Long Range Modeling by Removing Sequence Redundancy with FFT Operator (2023.findings-acl)

Challenge:	Large Language Model (LLM)-based Multi-agent Systems (MAS) have demonstrated remarkable capabilities in various complex tasks, but their vulnerability to adversarial attacks, misinformation propagation, and unintended behaviors have raised significant concerns.
Approach:	They propose a topology-guided security lens and treatment for robust LLM-MAS that leverages graph neural networks to detect anomalies on the multi-agent utterance graph and employ topological intervention for attack remediation.
Outcome:	Experiments show that the proposed security lens recovers 40% of the performance under various attack strategies and integrates with mainstream MAS with security guarantees.

Copied to clipboard

Ziwei He, Meng Yang, Minwei Feng, Jingcheng Yin, Xinbing Wang, Jingwen Leng, Zhouhan Lin

I²B-LPO: Latent Policy Optimization via Iterative Information Bottleneck (2026.acl-long)

Challenge:	Existing transformer models are computationally demanding and prohibitively costly for long sequences due to the quadratic complexity of its selfattention module.
Approach:	They propose a transformer-based model that inherits weights from large pretrained models by removing redundancies in hidden sequences using the ready-made Fast Fourier Transform operator.
Outcome:	The proposed model outperforms the standard BART model on the long-range modeling benchmark LRA with significant improvements in speed and space.

Copied to clipboard

Huilin Deng, Hongchen Luo, Yue Zhu, Long Li, Zhuoyue Chen, Xinghao Zhao, Ming LI, Chuyang Zhao, Jihai Zhang, MengChang Wang, Yang Cao, Yu Kang

Refined Evaluation for End-to-End Grammatical Error Correction Using an Alignment-Based Approach (2025.coling-main)

Challenge:	Existing methods for large language model reasoning suffer from exploration collapse due to the semantic homogeneity of random rollouts.
Approach:	They propose to use latent policy optimization via iterative information bottleneck to optimize reasoning trajectories by diversifying reasoning .
Outcome:	Empirical results show that the proposed method achieves state-of-the-art performance with margins of up to 5.3% in accuracy and 7.4% in diversity metrics.

Copied to clipboard

Junrui Wang, Mengyang Qiu, Yang Gu, Zihao Huang, Jungyeul Park

Dangling-Aware Entity Alignment with Mixed High-Order Proximities (2022.findings-naacl)

Challenge:	errant is a new evaluation tool that can be used to evaluate end-to-end grammatical error correction systems.
Approach:	They propose a method to assess end-to-end grammatical error correction systems using alignment-based alignment methods that reproduce and improve results from existing evaluation tools.
Outcome:	The proposed method reproduces and improves results from existing evaluation tools, such as errant, even when applied to raw text input.

Copied to clipboard

Juncheng Liu, Zequn Sun, Bryan Hooi, Yiwei Wang, Dayiheng Liu, Baosong Yang, Xiaokui Xiao, Muhao Chen

SudokuFill: A Multi-Agent Progressive Filling Framework for Document-Level Scientific Information Extraction (2026.findings-acl)

Challenge:	Existing methods for dangling-aware entity alignment are underexplored but important problem.
Approach:	They propose a framework that uses high-order proximities to detect dangling entities and align matchable entities.
Outcome:	The proposed framework detects dangling entities and aligns matchable entities better than existing methods.

Copied to clipboard

Yang Li, Yajiao Wang, Yu Zhang, Yuanzhe Zhang, Maodi Hu, Mengting Zhang, Xi Sun, Hua Yue, Zhixiong Zhang

FlashAudio: Rectified Flow for Fast and High-Fidelity Text-to-Audio Generation (2025.acl-long)

Challenge:	Scientific information extraction (SciIE) is a key bottleneck for turning unstructured papers into computable knowledge bases.
Approach:	They propose a scientific information extraction framework that solves a Sudoku problem as a progressive filling problem.
Outcome:	The proposed framework outperforms the GPT-4o model on a document-level adjuvant dataset.

Copied to clipboard

Huadai Liu, Jialei Wang, Rongjie Huang, Yang Liu, Heng Lu, Zhou Zhao, Wei Xue

Adaptive Feature-based Low-Rank Compression of Large Language Models via Bayesian Optimization (2024.findings-emnlp)

Challenge:	Recent advances in latent diffusion models (LDMs) have markedly enhanced text-to-audio generation, yet their iterative sampling processes impose substantial computational demands, limiting practical deployment.
Approach:	They propose to learn straight flow for fast simulation by using flashAudio with rectified flows and immiscible flow to minimize the total distance of data-noise pairs in a batch vias assignment.
Outcome:	The proposed method can learn straight flow for fast simulations and reduce noise distribution.

Copied to clipboard

Yixin Ji, Yang Xiang, Juntao Li, Qingrong Xia, Zi Ye, Xinyu Duan, Zhefeng Wang, Kehai Chen, Min Zhang

Dual-Feedback Knowledge Retrieval for Task-Oriented Dialogue Systems (2023.emnlp-main)

Challenge:	Large language models require a balance between efficiency and performance.
Approach:	They propose a low-rank compression technique that reduces non-essential parameters by decomposing weight matrices into products of two low-ranked matrici.
Outcome:	The proposed method outperforms existing pruning and low-rank compression techniques in maintaining model performance at the same compression ratio.

Copied to clipboard

Tianyuan Shi, Liangzhi Li, Zijian Lin, Tao Yang, Xiaojun Quan, Qifan Wang

ClusterUCB: Efficient Gradient-Based Data Selection for Targeted Fine-Tuning of LLMs (2025.findings-emnlp)

Challenge:	Current approaches to task-oriented dialogue systems integrate knowledge retrieval and response generation, which poses scalability challenges when dealing with extensive knowledge bases.
Approach:	They propose a retriever-generator architecture that harnesses a retrieval and a generator to generate system responses by using feedback from the generator as pseudo-labels.
Outcome:	The proposed architecture shows superior performance on three benchmark datasets.

Copied to clipboard

Zige Wang, Qi Zhu, Fei Mi, Minghui Xu, Ruochun Jin, Wenjing Yang

Empathetic Dialogue Generation via Sensitive Emotion Recognition and Sensible Knowledge Selection (2022.findings-emnlp)

Challenge:	Gradient-based data influence approximation is not feasible in practice.
Approach:	They propose a gradient-based data selection framework with clustering and a modified Upper Confidence Bound algorithm to solve this problem.
Outcome:	The proposed framework can achieve comparable results to the original gradient-based data selection methods while reducing computational consumption.

Copied to clipboard

Lanrui Wang, Jiangnan Li, Zheng Lin, Fandong Meng, Chenxu Yang, Weiping Wang, Jie Zhou

Eye Movement Features Can Predict Human Preferences on Machine-Generated Texts (2026.acl-srw)

Challenge:	Empathy is a key trait of everyday human conversations.
Approach:	They propose a serial encoding and Emotion-Knowledge interaction method for empathetic dialogue generation which is more sensitive to emotion dynamics in conversations.
Outcome:	The proposed method outperforms baseline evaluations on the utterance-level annotated EMPATHETICDIALOGUES.

Copied to clipboard

Xiaoshan He, Xiaoqun Liu, Haodong He, Yu Wang, Yang Xu

Should We Rely on Entity Mentions for Relation Extraction? Debiasing Relation Extraction with Counterfactual Analysis (2022.naacl-main)

Challenge:	Existing studies on eye movement in text quality assessment are limited . eye-movement features are important predictors of human judgments of text quality, but are costly and inconsistent.
Approach:	They propose to capture eye-movement features during screen reading of LLM-generated text using a dataset that includes eye-motion recordings, reading-time measurements, and post-reading evaluations.
Outcome:	The proposed dataset shows that eye-movement features can significantly improve models over other probabilistic metrics, including negative log-likelihood (NLL).

Copied to clipboard

Yiwei Wang, Muhao Chen, Wenxuan Zhou, Yujun Cai, Yuxuan Liang, Dayiheng Liu, Baosong Yang, Juncheng Liu, Bryan Hooi

Self-Improvement in Multimodal Large Language Models: A Survey (2025.findings-emnlp)

Challenge:	Existing studies rely on entity information for sentence-level relation extraction (RE) but this can leak superficial and spurious clues of relations.
Approach:	They propose to use entity mentions to extract relations from textual context . they use a causal graph to model dependencies between variables in RE models .
Outcome:	The proposed method yields significant gains on both effectiveness and generalization for RE.

Copied to clipboard

Shijian Deng, Kai Wang, Tianyu Yang, Harsh Singh, Yapeng Tian

Retrieval Enhanced Model for Commonsense Generation (2021.findings-acl)

Challenge:	Using data and data, self-improvement for Large Language Models has improved model capabilities without significantly increasing costs.
Approach:	This survey provides a comprehensive overview of self-improvement for Large Language Models . it includes commonly used evaluations and downstream applications .
Outcome:	The authors provide a comprehensive overview of self-improvement in Multimodal LLMs.

Copied to clipboard

Han Wang, Yang Liu, Chenguang Zhu, Linjun Shou, Ming Gong, Yichong Xu, Michael Zeng

GNN-encoder: Learning a Dual-encoder Architecture via Graph Neural Networks for Dense Passage Retrieval (2022.findings-emnlp)

Challenge:	Existing frameworks for commonsense generation are lacking for pre-trained models.
Approach:	They propose a framework that uses concept matching to retrieve prototype sentences and trainable sentence retriever to enhance pre-training and fine-tuning.
Outcome:	The proposed framework achieves state-of-the-art on the large-scale Common-Gen benchmark.

Copied to clipboard

Jiduan Liu, Jiahao Liu, Yang Yang, Jingang Wang, Wei Wu, Dongyan Zhao, Rui Yan

RRAtention: Dynamic Block Sparse Attention via Per-Head Round-Robin Shifts for Long-Context Inference (2026.acl-long)

Challenge:	Existing approaches to perform large-scale query-passage retrieval are term-based, but they lose interaction between query-pastage pairs.
Approach:	They propose to fuse query (passage) information into query representations via graph neural networks that are constructed by queries and their top retrieved passages.
Outcome:	The proposed model outperforms existing models on MSMARCO, Natural Questions and TriviaQA datasets and achieves the new state-of-the-art on these datasets.

Copied to clipboard

Siran Liu, Guoxia Wang, Sa Wang, Jinle Zeng, Haoyang Xie, Siyu Lou, Jiabin Yang, Dianhai Yu, Haifeng Wang, Chao Yang

Separation and Fusion: A Novel Multiple Token Linking Model for Event Argument Extraction (2024.naacl-long)

Challenge:	Existing approaches to dynamic sparse attention require preprocessing, lack global evaluation, violate query independence, or incur high computational overhead.
Approach:	They propose a dynamic sparse attention method that achieves all desirable properties through a head round-robin (RR) sampling strategy.
Outcome:	Experiments on natural language understanding and multimodal video comprehension show that the proposed method achieves 2.4 speedup at 128K context length outperforming existing methods.

Copied to clipboard

Jing Xu, Dandan Song, Siu Hui, Zhijing Wu, Meihuizi Jia, Hao Wang, Yanru Zhou, Changzhi Zhou, Ziyi Yang

Augur: Modeling Covariate Causal Associations in Time Series via Large Language Models (2026.acl-long)

Challenge:	Existing methods for event argument extraction (EAE) lack cross-event information and require longer role sequences . et al. (2017): outperforms state-of-the-art methods for EE.
Approach:	They propose a separation-and-fusion paradigm to separate the acquisition of cross-event information and fuse it into the argument extraction of a target event.
Outcome:	The proposed model outperforms the state-of-the-art models on four widely used datasets.

Copied to clipboard

Zhiqing Cui, Binwu Wang, Qingxiang Liu, Yeqiang Wang, Zhengyang Zhou, Yuxuan Liang, Yang Wang

CLUE: A Chinese Language Understanding Evaluation Benchmark (2020.coling-main)

Challenge:	Large language models (LLMs) have emerged as a promising avenue for time series forecasting . existing approaches face limitations such as marginalized role in model architectures and lack of interpretability.
Approach:	They propose a framework that exploits LLM causal reasoning to discover and use directed causal associations among covariates.
Outcome:	The proposed model improves predictive accuracy while yielding transparent, traceable reasoning about variable interactions.

Copied to clipboard

Liang Xu, Hai Hu, Xuanwei Zhang, Lu Li, Chenjie Cao, Yudong Li, Yechen Xu, Kai Sun, Dian Yu, Cong Yu, Yin Tian, Qianqian Dong, Weitang Liu, Bo Shi, Yiming Cui, Junyi Li, Jun Zeng, Rongzhao Wang, Weijian Xie, Yanting Li, Yina Patterson, Zuoyu Tian, Yiwen Zhang, He Zhou, Shaoweihua Liu, Zhe Zhao, Qipeng Zhao, Cong Yue, Xinrui Zhang, Zhengliang Yang, Kyle Richardson, Zhenzhong Lan

Challenge:	Existing language evaluation benchmarks for English are limited to English . lack of such benchmarks makes it difficult to replicate success in other languages .
Approach:	They introduce a large-scale Chinese language understanding evaluation benchmark . the benchmark uses a set of current state-of-the-art pre-trained Chinese models .
Outcome:	The first large-scale Chinese Language Understanding Evaluation (CLUE) benchmark is released . the benchmark evaluates models across a wide range of tasks on original Chinese text . existing language evaluation benchmarks are mostly limited to English .

Agri-CM3: A Chinese Massive Multi-modal, Multi-level Benchmark for Agricultural Understanding and Reasoning (2025.acl-long)

Copied to clipboard

Haotian Wang, Yi Guan, Fanshu Meng, Chao Zhao, Lian Yan, Yang Yang, Jingchi Jiang

Mining Word Boundaries from Speech-Text Parallel Data for Cross-domain Chinese Word Segmentation (2025.coling-main)

Challenge:	Existing benchmarks lack comprehensive evaluations, particularly in multi-level reasoning, making it difficult to identify model limitations.
Approach:	They propose to use Agri-CM3 to assess multi-level reasoning in agricultural management by integrating multiple data modalities.
Outcome:	The Agri-CM3 benchmark includes 3,939 images and 15,901 multi-level multiple-choice questions with detailed explanations.

Copied to clipboard

Xuebin Wang, Lei Zhang, Zhenghua Li, Shilin Zhou, Chen Gong, Yang Hou

Non-Existent Relationship: Fact-Aware Multi-Level Machine-Generated Text Detection (2025.emnlp-main)

Challenge:	Recent studies on Chinese Word Segmentation (CWS) have focused on the cross-domain scenarios, but there is a high cost of manually annotating high-quality data.
Approach:	They propose to explicitly mine word boundaries from parallel speech-text data by using the Montreal Forced Aligner toolkit to perform character-level alignment on speech- text data.
Outcome:	The proposed approach is based on character-level alignment on speech-text data and a robust complete-then-train (CTT) strategy.

Copied to clipboard

Yang Wu, Ruijia Wang, Jie Wu

Inference-Time Language Model Alignment via Integrated Value Guidance (2024.findings-emnlp)

Challenge:	Existing methods for detecting LLMs lack the authenticity of the entity graph . lmgenerated text is misused, including fake news and spam .
Approach:	They propose a fact-aware model that assesses discrepancies between textual and factual entity graphs through graph comparison.
Outcome:	The proposed model outperforms state-of-the-art methods on three public datasets showing that it can capture differences in entity graphs between machine-generated and human-written texts.

Copied to clipboard

Zhixuan Liu, Zhanhui Zhou, Yuanfu Wang, Chao Yang, Yu Qiao

ASAP: A Chinese Review Dataset Towards Aspect Category Sentiment Analysis and Rating Prediction (2021.naacl-main)

Challenge:	Large language models are fine-tuned to align with human preferences, but tuning large models is computationally intensive and complex.
Approach:	They propose a method that uses implicit and explicit value functions to guide language model decoding at token and chunk-level respectively.
Outcome:	The proposed method outperforms traditional methods and circumvents the complexities of fine-tuning.

Copied to clipboard

Jiahao Bu, Lei Ren, Shuang Zheng, Yang Yang, Jingang Wang, Fuzheng Zhang, Wei Wu

MRFD: Multi-Region Fusion Decoding with Self-Consistency for Mitigating Hallucinations in LVLMs (2025.findings-emnlp)

Challenge:	Sentiment analysis is a key task in e-commerce to detect fine-to-coarse sentiment polarities.
Approach:	They propose to use a large-scale Chinese restaurant review dataset ASAP to investigate the sentiment polarities underlying user reviews.
Outcome:	The proposed model outperforms state-of-the-art models on both tasks.

Copied to clipboard

Haonan Ge, Yiwei Wang, Ming-Hsuan Yang, Yujun Cai

Zero-Shot Learners for Natural Language Understanding via a Unified Multiple Choice Perspective (2022.emnlp-main)

Challenge:	Large Vision-Language Models often produce hallucinations due to the limited ability to verify information in different regions of the image.
Approach:	a new decoding method improves factual grounding by modeling inter-region consistency . the method identifies salient regions using cross-attention and generates initial responses for each .
Outcome:	a training-free decoding method reduces hallucinations and improves response consistency . the proposed method generates initial responses for each region and weights reliability weights among responses .

Copied to clipboard

Ping Yang, Junjie Wang, Ruyi Gan, Xinyu Zhu, Lin Zhang, Ziwei Wu, Xinyu Gao, Jiaxing Zhang, Tetsuya Sakai

Measuring Bargaining Abilities of LLMs: A Benchmark and A Buyer-Enhancement Method (2024.findings-acl)

Challenge:	Existing approaches to zero-shot learning are format-agnostic and can address new learning tasks without additional training.
Approach:	They propose a new paradigm for zero-shot learning that is format agnostic and compatible with any format and applicable to a list of language tasks.
Outcome:	The proposed model shows state-of-the-art performance on several benchmarks and produces satisfactory results on tasks such as text classification and commonsense reasoning.

Copied to clipboard

Tian Xia, Zhiwei He, Tong Ren, Yibo Miao, Zhuosheng Zhang, Yang Yang, Rui Wang

Challenge:	Using a novel approach, we can evaluate an agent’s bargaining abilities as an asymmetric incomplete information game.
Approach:	They propose an approach that integrates a deterministic Offer Generator and an LLM Narrator to create natural language sentences for generated offers.
Outcome:	The proposed approach improves the buyer’s deal rates from 26.67% to 88.88% and brings a ten times multiplication of profits on all baselines, even a model that has not been aligned.

MoLAN: A Unified Modality-Aware Noise Dynamic Editing Framework for Multimodal Sentiment Analysis (2026.findings-acl)

Copied to clipboard

Xingle Xu, YongKang Liu, Dexian Cai, Shi Feng, Xiaocui Yang, Daling Wang, Yifei Zhang

Covariance Matrix-Driven Image Channel Allocation for Multimodal Fake News Detection (2026.findings-acl)

Challenge:	Existing approaches to multimodal sentiment analysis treat entire modality as an independent unit for feature enhancement or denoising, which often suppresses redundant noise at the cost of weakening critical information.
Approach:	They propose a ModaLity-aware noise dynAmic editiNg framework that performs modality-awful block partitioning by dividing features of each modality into multiple blocks.
Outcome:	Experiments on five models and four datasets show that MoLAN+ achieves the state-of-the-art performance.

Copied to clipboard

Zongliang Han, Wenyu Guo, Guoqing Jin, Yang Liu, Yan Song, Dong Yu, Wang Min

MTAG: Modal-Temporal Attention Graph for Unaligned Human Multimodal Language Sequences (2021.naacl-main)

Challenge:	Existing methods focus on designing efficient multimodal fusion frameworks to bridge the semantic gap between images and texts.
Approach:	They propose a covariance matrix-driven image channel allocation method that expands the number of original channel maps and assigns importance scores to the expanded channel maps.
Outcome:	The proposed method achieves state-of-the-art on three public multimodal fake news detection benchmark datasets.

Copied to clipboard

Jianing Yang, Yongxin Wang, Ruitao Yi, Yuying Zhu, Azaan Rehman, Amir Zadeh, Soujanya Poria, Louis-Philippe Morency

Tree-KG: An Expandable Knowledge Graph Construction Framework for Knowledge-intensive Domains (2025.acl-long)

Challenge:	a novel graph-based neural model for multimodal sequential data is proposed . fusion is the process of blending information from multiple modalities, usually preceded by alignment .
Approach:	They propose a graph-based neural model that converts unaligned data into a modal-temporal graph . they use a dynamic pruning and read-out technique to efficiently process the graph fusion operation .
Outcome:	The proposed model performs state-of-the-art on multimodal sentiment analysis and emotion recognition benchmarks while utilizing significantly fewer model parameters.

Copied to clipboard

Songjie Niu, Kaisen Yang, Rui Zhao, Yichao Liu, Zonglin Li, Hongning Wang, Wenguang Chen

Structure-Unified M-Tree Coding Solver for Math Word Problem (2022.emnlp-main)

Challenge:	Knowledge graphs are a useful tool for organizing complex data in knowledge-intensive domains.
Approach:	They propose an expandable framework that combines structured domain texts with advanced semantic techniques to create a tree-like graph from textbooks.
Outcome:	The proposed framework surpasses competing methods in the text-Annotated dataset with high scores on the Text-Annalytated data.

Copied to clipboard

Bin Wang, Jiangzhou Ju, Yang Fan, Xinyu Dai, Shujian Huang, Jiajun Chen

Numerical Reasoning

Challenge:	Existing models that take into account the binary tree structure of mathematical expressions have achieved better performance, but the output space is non-deterministic.
Approach:	They propose a Structure-Unified M-Tree Coding Solver which applies a tree with any M branches to unify the output structures.
Outcome:	The proposed model outperforms several state-of-the-art models under similar experimental conditions and performs much better under low-resource conditions.

Bit-by-Bit: Progressive QAT Strategy with Outlier Channel Splitting for Stable Low-Bit LLMs (2026.acl-long)

Copied to clipboard

Binxing Xu, Hao Gu, Lujun Li, Hao Wang, Bei Liu, Jiacheng Liu, Qiyuan Zhu, Xintong Yang, Chao Li, Sirui Han, Yike Guo

A Practical Approach for Building Production-Grade Conversational Agents with Workflow Graphs (2025.acl-industry)

Challenge:	Existing approaches to training LLMs at ultra-low precisions suffer from convergence instability and substantial training costs.
Approach:	They propose a progressive QAT framework with outlier channel splitting to address these issues . they use nested structure of integer quantization grids to enable a "train once, deploy any precision" paradigm .
Outcome:	The proposed framework outperforms baselines on both Llama2/3 and W2A16, with an 11 speedup over BF16.

Copied to clipboard

Chiwan Park, Wonjun Jang, Daeryong Kim, Aelim Ahn, Kichang Yang, Woosung Hwang, Jihyeon Roh, Hyerin Park, Hyosun Wang, Min Seok Kim, Jihoon Kang

Multimodal Invariant Sentiment Representation Learning (2025.findings-acl)

Challenge:	Large Language Models (LLMs) have led to significant improvements in various service domains, including search, recommendation, and chatbot applications.
Approach:	They propose a framework for developing scalable, controllable, and reliable AI-driven agents that can be applied to real-world applications.
Outcome:	The proposed framework bridges the gap between academic research and real-world application, and enables scalable, controllable, and reliable AI-driven agents.

Copied to clipboard

Aoqiang Zhu, Min Hu, Xiaohua Wang, Jiaoyun Yang, Yiming Tang, Ning An

JARVIS or Ultron? A Survey on the Safety and Security Threats of Computer-Using Agents (2026.acl-long)

Challenge:	Existing methods for multimodal sensing ignore significant sentiment distribution imbalances and cross-modal sentiment conflicts, hindering performance improvement.
Approach:	They propose a method to learn stable multimodal invariant sentiment representations by incorporating distributional discrepancies and sentiment conflicts into the model training.
Outcome:	The proposed method improves MSA performance and achieves new state-of-the-art.

Copied to clipboard

Ada Chen, Yongjiang Wu, Junyuan Zhang, Jingyu Xiao, Shu Yang, Jen-tse Huang, Kun Wang, Wenxuan Wang, Shuai Wang

Challenge:	Recent advances in computer-using agents have created new safety and security risks . despite the impressive capabilities of CUAs, there are still significant security risks.
Approach:	They propose a systematization of knowledge on the safety and security threats of Computer-Using Agents.
Outcome:	The proposed framework provides a framework for assessing the safety and security risks of computer-using agents.

Improving Large Language Models Function Calling and Interpretability via Guided-Structured Templates (2025.emnlp-main)

Copied to clipboard

Hy Dang, Tianyi Liu, Zhuofeng Wu, Jingfeng Yang, Haoming Jiang, Tao Yang, Pei Chen, Zhengyang Wang, Helen Wang, Huasheng Li, Bing Yin, Meng Jiang

APOLLO: A Simple Approach for Adaptive Pretraining of Language Models for Logical Reasoning (2023.acl-long)

Challenge:	Large language models (LLMs) have strong reasoning and tool-use capabilities, yet fail in real-world tool-interactions due to incorrect parameterization, poor tool selection, or misinterpretation of user intent.
Approach:	They propose a curriculum-inspired framework that leverages structured reasoning templates to guide LLMs through more deliberate step-by-step instructions for generating function calls.
Outcome:	The proposed framework reduces tool-use errors and improves interpretability and transparency of tool-using agents.

Copied to clipboard

Soumya Sanyal, Yichong Xu, Shuohang Wang, Ziyi Yang, Reid Pryzant, Wenhao Yu, Chenguang Zhu, Xiang Ren

A Bounding Box is Worth One Token - Interleaving Layout and Text in a Large Language Model for Document Understanding (2025.findings-acl)

Challenge:	Existing methods to improve logical reasoning skills require complex data processing.
Approach:	They propose an adaptive pretraining approach to improve logical reasoning over text . they use a subset of Wikipedia sentences for pretraining and a sentence-level classification loss .
Outcome:	The proposed model outperforms baselines on LogiQA and ReClor.

Copied to clipboard

Jinghui Lu, Haiyang Yu, Yanjie Wang, Yongjie Ye, Jingqun Tang, Ziwei Yang, Binghong Wu, Qi Liu, Hao Feng, Han Wang, Hao Liu, Can Huang

WarriorCoder: Learning from Expert Battles to Augment Code Large Language Models (2025.acl-long)

Challenge:	Existing methods for integrating spatial layouts with text have limitations . existing methods produce overly long text sequences or lack autoregressive traits of LLMs .
Approach:	They introduce Interleaving Layout and Text in a Large Language Model (LayTextLLM) they use OCR-derived text and spatial layouts to integrate with LLMs for document understanding .
Outcome:	The proposed model shows an increase in performance in KIE and VQA tasks.

Copied to clipboard

Huawen Feng, Pu Zhao, Qingfeng Sun, Can Xu, Fangkai Yang, Lu Wang, Qianli Ma, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang, Qi Zhang

PLAWBENCH: A Rubric-Based Benchmark for Evaluating LLMs in Real-World Legal Practice (2026.acl-long)

Challenge:	Recent code large language models have demonstrated impressive performance on code-related tasks.
Approach:	They propose a paradigm that learns from expert battles to address these limitations . they create an arena where leading LLMs challenge each other with evaluations .
Outcome:	The proposed model improves on existing models by leveraging expert battles . it achieves state-of-the-art performance even without relying on proprietary models .

Copied to clipboard

Yuzhen Shi, Huanghai Liu, Yiran HU, Song Gaojie, Xu Xinran, Yubo Ma, Tianyi Tang, Li Zhang, Qingjing Chen, Feng Di, Wenbo Lv, Weiheng Wu, Kexin Yang, Sen Yang, Wei Wang, Rongyao Shi, Qiu Yuanyang, Yuemeng Qi, Zhang Jingwen, Sui Xiaoyu, Yifan Chen, Zhang Yi, An Yang, Bowen Yu, Dayiheng Liu, Junyang Lin, Weixing Shen, Bing Zhao, Charles L. A. Clarke, HU Wei

Social Welfare Function Leaderboard: On the Emergence of LLM Agents as the Welfare Dictator (2026.findings-acl)

Challenge:	Existing benchmarks for large language models (LLMs) are coarse, single-dimensional metrics and do not explicitly assess fine-grained legal reasoning.
Approach:	They propose a Practical Law Benchmark to evaluate large language models in real-world legal practice scenarios.
Outcome:	The proposed model is based on 850 questions and 13 scenarios with expert-designed evaluation rubrics.

Copied to clipboard

Zhengliang Shi, Ruotian Ma, Jen-tse Huang, Xinbei Ma, Xingyu Chen, Mengru Wang, Qu Yang, Yue Wang, Fanghua Ye, Ziyang Chen, Shanyi Wang, Cixing LI, Wenxuan Wang, Zhaopeng Tu, Xiaolong Li, Zhaochun Ren, Liefeng Bo

CINO: A Chinese Minority Pre-trained Language Model (2022.coling-1)

Challenge:	Large language models (LLMs) are increasingly entrusted with high-stakes decisions that affect human welfare.
Approach:	They evaluate 20 state-of-the-art Large language models (LLMs) and 20 LLM dictators to create a social welfare function benchmark.
Outcome:	The proposed model creates dilemma between maximizing collective efficiency and ensuring distributive fairness.

Copied to clipboard

Ziqing Yang, Zihang Xu, Yiming Cui, Baoxin Wang, Min Lin, Dayong Wu, Zhigang Chen

MulDimIF: A Multi-Dimensional Constraint Framework for Evaluating and Improving Instruction Following in Large Language Models (2026.findings-acl)

Challenge:	Existing multilingual pre-trained language models do not perform well on some low-resource languages.
Approach:	They propose a multilingual pre-trained language model for Chinese minority languages . they collect documents from Wikipedia and construct two classification datasets .
Outcome:	The proposed model outperforms baseline models on various classification tasks.

Copied to clipboard

Junjie Ye, Caishuang Huang, Zhuohan Chen, Wenjie Fu, Chenyuan Yang, Leyi Yang, Yilong Wu, Peng Wang, Meng Zhou, Xiaolong Yang, Tao Gui, Qi Zhang, Zhongchao Shi, Jianping Fan, Xuanjing Huang

Large Language Models and Causal Inference in Collaboration: A Comprehensive Survey (2025.findings-naacl)

Challenge:	Existing research has focused on constraint categories, offering little guidance for improving instruction following abilities.
Approach:	They propose a multi-dimensional constraint framework that allows for instruction following . they construct 9,106 code-verifiable samples and evaluate 18 LLMs .
Outcome:	The proposed framework improves instruction following performance without compromising general performance.

Copied to clipboard

Xiaoyu Liu, Paiheng Xu, Junda Wu, Jiaxin Yuan, Yifan Yang, Yuhang Zhou, Fuxiao Liu, Tianrui Guan, Haoliang Wang, Tong Yu, Julian McAuley, Wei Ai, Furong Huang

CVRH: Cross-modal Variational Role Hypergraph Network via Semantic Enhancement for Multi-modal Event Argument Extraction (2026.findings-acl)

Challenge:	Large Language Models (LLMs) have shown great potential to enhance Natural Language Processing (NLP) models in areas such as predictive accuracy, fairness, robustness, and explainability.
Approach:	They evaluate or improve generative Large Language Models from a causal perspective in areas such as reasoning capacity, fairness and safety issues, explainability, and handling multimodality.
Outcome:	The proposed models can be used to perform causal relationship discovery and causal effect estimation tasks.

Copied to clipboard

Bangze Pan, Yang Li, Ruili Pu, Suge Wang, Jian Liao, JianXing Zheng, Xiaoli Li, Deyu Li

Event Extraction

Challenge:	Existing methods focus on weakly aligning uni-modal representations and generatively data augmentation techniques, but they ignore the potential impact of event role information on MEAE.
Approach:	They propose a cross-modal variational role hypergraph network via semantic enhancement to model high-order role correlations among cross-mod arguments in multi-modal documents.
Outcome:	The proposed method achieves a 6.9% improvement in F1-score on the M2E2 benchmark compared to current state-of-the-art methods.

Invisible Entropy: Towards Safe and Efficient Low-Entropy LLM Watermarking (2025.emnlp-main)

Copied to clipboard

Tianle Gu, Zongqi Wang, Kexin Huang, Yuanqi Yao, Xiangliang Zhang, Yujiu Yang, Xiuying Chen

HiMATE: A Hierarchical Multi-Agent Framework for Machine Translation Evaluation (2025.findings-emnlp)

Challenge:	Existing methods to watermark low-entropy content are expensive and risky . IE reduces parameter size by 99% while achieving performance on par with state-of-the-art methods .
Approach:	They propose a logit-based watermarking paradigm that uses entropy-based features to predict whether the next token is high or low.
Outcome:	The proposed method reduces parameter size by 99% while achieving performance on par with state-of-the-art methods.

Copied to clipboard

Shijie Zhang, Renhao Li, Songsheng Wang, Philipp Koehn, Min Yang, Derek F. Wong

Beyond Quantity: Trajectory Diversity Scaling for Code Agents (2026.findings-acl)

Challenge:	Existing LLM-based evaluation methods fail to accurately identify error spans and assess their severity.
Approach:	They propose a Hierarchical Multi-Agent Framework for Machine Translation Evaluation based on the MQM error typology and a hierarchical multi-agent system enabling granular evaluation of subtype errors.
Outcome:	The proposed framework outperforms baselines in error span detection and severity assessment.

Copied to clipboard

Guhong Chen, Chenghao Sun, Cheng Fu, Qiyao Wang, Zhihong Huang, ChaoPeng Wei, Guangxu Chen, Feiteng Fang, Ahmadreza Argha, Bing Zhao, Xander Xu, Qi Han, Hamid Alinejad-Rokny, Qiang Qu, Binhua Li, Shiwen Ni, Min Yang, HU Wei, Yongbin Li

CLaSp: In-Context Layer Skip for Self-Speculative Decoding (2025.acl-long)

Challenge:	Code large language models (LLMs) are becoming tool-interactive agents . quantity-centric scaling exhibits an early bottleneck that underutilizes trajectory data . et al.: a new approach to scale trajectory diversity improves tool-use generalization .
Approach:	They propose a Trajectory Diversity Scaling-based data synthesis framework for code agents that scales performance through diversity rather than raw volume.
Outcome:	Experiments on general tool-use benchmarks and code agent tasks show that TDScaling improves tool-user generalization and inherent coding proficiency.

Copied to clipboard

Longze Chen, Renke Shan, Huiming Wang, Lu Wang, Ziqiang Liu, Run Luo, Jiawei Wang, Hamid Alinejad-Rokny, Min Yang

Challenge:	Existing methods for drafting Large Language Models require additional modules to be trained, which can be challenging to implement and ensure compatibility across various LLMs.
Approach:	They propose an in-context layer-skipping strategy for self-speculative decoding that uses a plug-and-play mechanism to skip intermediate layers of the verify model to construct a compressed draft model.
Outcome:	The proposed method achieves a speedup of 1.3 1.7 on LLaMA3 series models without altering the original distribution of the generated text.

Prototype Tuning: A Meta-Learning Approach for Few-Shot Document-Level Relation Extraction with Large Language Models (2025.findings-naacl)

Copied to clipboard

Dinghao Pan, Yuanyuan Sun, Bo Xu, Jiru Li, Zhihao Yang, Ling Luo, Hongfei Lin, Jian Wang

Quantifying Semantic Emergence in Language Models (2025.acl-long)

Challenge:	Few-Shot Document-Level Relation Extraction (FSDLRE) aims to develop models capable of generalizing to new categories with minimal support examples.
Approach:	They propose a meta-training approach to train Large Language Models to improve their ICL capabilities . they construct simulated episodes using relation types that do not overlap with test corpus .
Outcome:	Experimental results show that the proposed approach outperforms baseline models on few-shot tasks.

Copied to clipboard

Hang Chen, Xinyu Yang, Jiaying Zhu, Wenya Wang

Attribution-Based Analysis and Optimization of Modular Agentic Workflows (2026.findings-acl)

Challenge:	Existing evaluation methods for large language models (LLMs) focus on coarse-grained text, not providing interpretations for the behavior of finergrained tokens.
Approach:	They propose a quantitative metric to measure large language models’ ability to extract semantics from input tokens.
Outcome:	The proposed metric compares the entropy reduction observed for a sequence of tokens and individual tokens.

Copied to clipboard

Yingxuan Yang, Bo Huang, Siyuan Qi, Chao Feng, Haoyi Hu, Yuxuan Zhu, Jinbo Hu, Haoran Zhao, Ziyi He, Xiao Liu, ZongYu Wang, Muning Wen, Lin Qiu, Xuezhi Cao, Xunliang Cai, Yong Yu, Weinan Zhang

Challenge:	Large Language Models (LLMs) have driven the rise of agentic workflows . yet, how can we attribute performance gains to individual upgrades and their interactions?
Approach:	They propose a game-theoretic framework that models component upgrades as players and evaluates component coalitions to compute Shapley values.
Outcome:	The proposed framework provides interaction-aware attribution and recommendation for model allocation under a fixed workflow structure.

Agent-GWO: Collaborative Agents for Dynamic Prompt Optimization in Large Language Models (2026.findings-acl)

Copied to clipboard

Xudong Wang, Chaoning Zhang, Chenghao Li, Shuxu Chen, Qigan Sun, Jiaquan Zhang, Fachrina Dewi Puspitasari, Tae-Ho Kim, Jiwei Wei, Malu Zhang, Guoqing Wang, Yang Yang, Heng Tao Shen

MIRTT: Learning Multimodal Interaction Representations from Trilinear Transformers for Visual Question Answering (2021.findings-emnlp)

Challenge:	Existing automatic prompt optimization methods fail to optimize prompts and decoding hyperparameters within a unified framework to achieve stable global improvements.
Approach:	They propose a dynamic prompt optimization framework for complex reasoning that unifies prompt templates and decodes hyperparameters as inheritable agent configurations.
Outcome:	Experiments on multiple mathematical and hybrid reasoning benchmarks show that Agent-GWO improves accuracy and stability over existing prompt optimization methods.

Copied to clipboard

Junjie Wang, Yatai Ji, Jiaqi Sun, Yujiu Yang, Tetsuya Sakai

PESCO: Prompt-enhanced Self Contrastive Learning for Zero-shot Text Classification (2023.acl-long)

Challenge:	Existing bilinear methods focus on inter-modality information between images and questions . existing models focus on the interaction between images, questions, and images .
Approach:	They propose a trilinear interaction framework that incorporates attention mechanisms for capturing inter-modality and intra-modal relationships.
Outcome:	The proposed model outperforms bilinear models on the Visual7W Telling task and VQA-1.0 Multiple Choice task and outperformed baselines on the VQA, TDIUC and GQA datasets.

Copied to clipboard

Yau-Shian Wang, Ta-Chung Chi, Ruohong Zhang, Yiming Yang

AISFG: Abundant Information Slot Filling Generator (2022.naacl-main)

Challenge:	Existing text classification frameworks require large amounts of human-labeled documents to train .
Approach:	They propose a contrastive learning framework that improves zero-shot text classification . they add prompts to enhance label retrieval and use retrieved labels to enrich training .
Outcome:	The proposed framework achieves state-of-the-art on four benchmark text classification datasets.

Copied to clipboard

Yang Yan, Junda Ye, Zhongbao Zhang, Liwen Wang

FedPETuning: When Federated Learning Meets the Parameter-Efficient Tuning Methods of Pre-trained Language Models (2023.findings-acl)

Challenge:	Existing approaches to zero/few-shot slot filling focus on slot descriptions and examples . AISFG model is based on domain-specific labels, which is not capable of transferring to new domains with little or no data.
Approach:	They propose a model with a query template that incorporates domain descriptions, slot descriptions, and examples with context.
Outcome:	Experimental results show that the proposed model outperforms state-of-the-art approaches in zero/few-shot slot filling task.

Copied to clipboard

Zhuo Zhang, Yuanhang Yang, Yong Dai, Qifan Wang, Yue Yu, Lizhen Qu, Zenglin Xu

Enhancing Neural Topic Model with Multi-Level Supervisions from Seed Words (2023.findings-acl)

Challenge:	Existing research on federated learning (FL) for pre-trained language models (PLMs) with increasing concerns about data privacy, enterprises or institutions are not allowed to collect data from end devices or local clients to a centralized server for fine-tuning PLMs.
Approach:	They investigate the parameter-efficient tuning of pre-trained language models (PLMs) and develop a federated benchmark for four representative PETuning methods .
Outcome:	The proposed method can defend against privacy attacks and maintain acceptable performance with reducing heavy resource consumption.

Copied to clipboard

Yang Lin, Xin Gao, Xu Chu, Yasha Wang, Junfeng Zhao, Chao Chen

Morpheme Sense Disambiguation: A New Task Aiming for Understanding the Language at Character Level (2024.lrec-main)

Challenge:	Existing topic seed words are difficult to incorporate into topic models due to the semantic diversity of natural language.
Approach:	They propose a neural topic model enhanced with supervisions from seed words on word and document levels.
Outcome:	The proposed model outperforms the state-of-the-art seeded topic models in terms of topic quality and classification accuracy.

Copied to clipboard

Yue Wang, Hua Zheng, Yaqi Yin, Hansi Wang, Qiliang Liang, Yang Liu

Continual Learning for Text Classification with Information Disentanglement Based Regularization (2021.naacl-main)

Challenge:	Morphemes are a strong linguistic feature to capture lexical semantics, but lack of morpheme-informed resources and the expense of manual annotations hinder morphme-enhanced methods.
Approach:	They propose a task of Morpheme Sense Disambiguation with two subtasks in-text and in-word to generalize morpheme features on more tasks.
Outcome:	The proposed tasks are based on two morpheme-annotated datasets for Chinese . the best model yields a promising precision of 77.66% on in-text and 88.19% on in word .

Copied to clipboard

Yufan Huang, Yanzhe Zhang, Jiaao Chen, Xuezhi Wang, Diyi Yang

Beyond Boundaries: Learning a Universal Entity Taxonomy across Datasets and Languages for Open Named Entity Recognition (2025.coling-main)

Challenge:	Existing continual learning methods focus on preserving knowledge from previous tasks . Continual learning is a useful tool for learning over time, but it is not always possible to generalize to new tasks.
Approach:	They propose a disentanglement-based regularization method for continual learning on text classification that disentangles text hidden spaces into generic representations and regularizes them differently to constrain knowledge required to generalize.
Outcome:	The proposed method disentangles text hidden spaces into representations that are generic to all tasks and representations specific to each individual task.

Copied to clipboard

Yuming Yang, Wantong Zhao, Caishuang Huang, Junjie Ye, Xiao Wang, Huiyuan Zheng, Yang Nan, Yuran Wang, Xueying Xu, Kaixin Huang, Yunke Zhang, Tao Gui, Qi Zhang, Xuanjing Huang

DVMap: Fine-Grained Pluralistic Value Alignment via High-Consensus Demographic-Value Mapping (2026.acl-long)

Challenge:	Current Large Language Models struggle with complex entity taxonomies in open domains and lack NER capabilities.
Approach:	They propose a dataset to guide LLMs' generalization in Open NER under a universal entity taxonomy.
Outcome:	The proposed model outperforms GPT-4 in 3 out-of-domain benchmarks across 15 datasets and 6 languages.

Copied to clipboard

Pengyun Zhu, Yuqi Ren, Zhen Wang, Lei Yang, Deyi Xiong

Challenge:	Current Large Language Models (LLMs) rely on coarse-grained national labels for pluralistic value alignment.
Approach:	They propose a framework for fine-grained pluralistic value alignment using demographic constraints.
Outcome:	The proposed framework can identify groups with predictable, high-consensus value preference . it achieves 48.6% accuracy, surpassing open-source LLM DeepSeek-v3.2 .

FaithLM: Towards Faithful Explanations for Large Language Models (2026.eacl-long)

Copied to clipboard

Yu-Neng Chuang, Guanchu Wang, Chia-Yuan Chang, Ruixiang Tang, Shaochen Zhong, Fan Yang, Andrew Wen, Mengnan Du, Xuanting Cai, Vladimir Braverman, Xia Hu

Student Guides Teacher: Weak-to-Strong Inference via Spectral Orthogonal Exploration (2026.acl-long)

Challenge:	Large language models (LLMs) produce natural language explanations, but they lack faithfulness and do not reflect the evidence the model uses to decide.
Approach:	They propose a model-agnostic framework that evaluates and improves the faithfulness of LLM explanations without token masking or task-specific heuristics.
Outcome:	The proposed framework improves faithfulness of large language models without masking or heuristics.

Copied to clipboard

Dayu Wang, Jiaye Yang, Weikang Li, Jiahui Liang, Yang Li, Deguo Xia, Jizhou Huang

A Systematic Assessment of Language Models with Linguistic Minimal Pairs in Chinese (2026.tacl-1)

Challenge:	Existing Large Language Models suffer from "Reasoning Collapse" on mathematical reasoning tasks where stochastic sampling produces lexical variations of the same erroneous logic rather than genuine semantic exploration.
Approach:	They propose a geometric inference framework that uses a spectral orthogonal probe to introduce semantically heterogeneous reasoning signals into the teacher's orthogonale complement of its dominant subspace.
Outcome:	The proposed framework improves accuracy and sampling efficiency over baseline methods on logic and code generation benchmarks.

Copied to clipboard

Yikang Liu, Yeting Shen, Hongao Zhu, Lilong Xu, Zhiheng Qian, Siyuan Song, Kejia Zhang, Jialong Tang, Pei Zhang, Baosong Yang, Rui Wang, Hai Hu

Play Guessing Game with LLM: Indirect Jailbreak Attack with Implicit Clues (2024.findings-acl)

Challenge:	Using sub-linear length normalized log-probabilities (SLLN-LP), we find unequal lengths of sentences in minimal pairs difficult for LMs even up to 32B parameters.
Approach:	They propose to use ZhoBLiMP as a linguistic minimal pair benchmark for Chinese language models to mitigate biases.
Outcome:	The proposed metric mitigates biases in Chinese language models with over 100 paradigms . Anaphor, Quantifiers, and Ellipsis are difficult for LMs even up to 32B parameters .

Copied to clipboard

Zhiyuan Chang, Mingyang Li, Yi Liu, Junjie Wang, Qing Wang, Yang Liu

SemanticCamo: Jailbreaking Large Language Models through Semantic Camouflage (2025.findings-acl)

Challenge:	Existing jailbreak attacks primarily utilize scenario camouflage techniques, however their explicit mention of malicious intent will be easily recognized and defended by LLMs.
Approach:	They propose an indirect jailbreak attack approach, Puzzler, which can bypass LLM’s defensive strategies and obtain malicious response by implicitly providing LLMs with some clues about the original malicious query.
Outcome:	The proposed approach can bypass the LLM’s defensive strategies and obtain malicious response by implicitly providing LLMs with some clues about the original malicious query.

Copied to clipboard

Jihui Yan, Xiaocui Yang, Daling Wang, Shi Feng, Yifei Zhang, Yinzhi Zhao

Both Matter: Enhancing the Emotional Intelligence of Large Language Models without Compromising the General Intelligence (2024.findings-acl)

Challenge:	Large Language Models (LLMs) have made safety issues of LLMs more prominent and critical.
Approach:	They propose a framework which attacks LLMs through semantic camouflage and replaces unsafe content with semantic features to conceal malicious intent .
Outcome:	The proposed framework outperforms existing models in over 80% of cases and is highly effective against various defenses.

Copied to clipboard

Weixiang Zhao, Zhuojun Li, Shilong Wang, Yang Wang, Yulin Hu, Yanyan Zhao, Chen Wei, Bing Qin

CAR: Empowering Agents with Dynamic Tool Synthesis and Global Trajectory Rectification (2026.findings-acl)

Challenge:	Emotional Intelligence (EI) is a key concept in the field of human intelligence.
Approach:	They propose a method to enhance EI of large language models by naive fine-tuning on EI-related tasks.
Outcome:	The proposed method improves EI of two LLM-based assistants without compromising GI.

Copied to clipboard

Kai Wang, Xu Wang, Zhiyuan Fu, Yudong Zhang, Yang Wang

Challenge:	Existing LLM agents are brittle in open-ended environments due to two limitations: 1) a closed action space; 2) myopic error recovery.
Approach:	They propose a novel architecture that augments the action space and revises global strategies by adding a reflective replanning mechanism to the system.
Outcome:	Experiments show that CAR outperforms baselines in a diagnostic benchmark with pruned toolsets to simulate tool scarcity.

ReLearn: Unlearning via Learning for Large Language Models (2025.acl-long)

Copied to clipboard

Haoming Xu, Ningyuan Zhao, Liming Yang, Sendong Zhao, Shumin Deng, Mengru Wang, Bryan Hooi, Nay Oo, Huajun Chen, Ningyu Zhang

Too Good to be Bad: On the Failure of LLMs to Role-Play Villains (2026.findings-acl)

Challenge:	Existing methods for unlearning large language models often rely on reverse optimization to reduce target token probabilities.
Approach:	They propose a data augmentation and fine-tuning pipeline for effective unlearning . they propose augmentation, evaluation frameworks to measure contextual forgetting .
Outcome:	The proposed framework achieves targeted forgetting while preserving high-quality outputs.

Copied to clipboard

Zihao Yi, Qingxuan Jiang, Ruotian Ma, Xingyu Chen, Qu Yang, Mengru Wang, Fanghua Ye, Ying Shen, Zhaopeng Tu, Xiaolong Li, Liefeng Bo

Challenge:	Large Language Models (LLMs) are increasingly tasked with creative generation, but their ability to portray non-prosocial, antagonistic personas remains largely unexamined.
Approach:	They propose a moral alignment benchmark to test the safety of large language models . they find that models struggle with traits directly antithetical to safety principles .
Outcome:	The proposed model fails to accurately portray morally ambiguous or villainous characters . the model fails most with traits directly antithetical to safety principles .

Towards IP Intelligence: Benchmarking Large Language Models on Intellectual Property Knowledge and Practice (2026.findings-acl)

Copied to clipboard

Qiyao Wang, Guhong Chen, Hongbo Wang, Huaren Liu, Minghui Zhu, Zhifei Qin, Li Linwei, Yilin Yue, Shiqiang Wang, Jiayan Li, Wu Yihang, Ziqiang Liu, Longze Chen, Run Luo, Liyang Fan, Jiaming Li, Lei Zhang, Kan Xu, Hamid Alinejad-Rokny, Chengming Li, Shiwen Ni, Yuan Lin, Min Yang

KeFVP: Knowledge-enhanced Financial Volatility Prediction (2023.findings-emnlp)

Challenge:	Existing datasets and benchmarks focus only on patents or cover limited aspects of the IP field, lacking alignment with real-world scenarios.
Approach:	They propose a bilingual IP task taxonomy and a large-scale bilingual benchmark to evaluate LLMs in real-world IP practice.
Outcome:	The proposed model achieves only 75.8% accuracy, indicating room for improvement . open-source IP and law-oriented models lag behind closed-source general-purpose models .

Copied to clipboard

Hao Niu, Yun Xiong, Xiaosu Wang, Wenjing Yu, Yao Zhang, Weizu Yang

RealHiTBench: A Comprehensive Realistic Hierarchical Table Benchmark for Evaluating LLM-Based Table Analysis (2025.findings-acl)

Challenge:	Current studies ignore the role of financial metrics knowledge in earnings calls and little consideration is given to integrating text and price information.
Approach:	They propose to integrate financial metrics knowledge into text comprehension by knowledge-enhanced adaptive pre-training and effectively incorporating text and price information by introducing a conditional time series prediction module.
Outcome:	The proposed method outperforms state-of-the-art methods on three real-world datasets and is effective and reliable.

Copied to clipboard

Pengzuo Wu, Yuhang Yang, Guangcheng Zhu, Chao Ye, Hong Gu, Xu Lu, Ruixuan Xiao, Bowen Bao, Yijing He, Liangyu Zha, Wentao Ye, Junbo Zhao, Haobo Wang

MAESTRO: Meta-learning Adaptive Estimation of Scalarization Trade-offs for Reward Optimization (2026.acl-long)

Challenge:	Existing benchmarks for large language models focus on simple, flat table structures.
Approach:	They propose a benchmark to evaluate the performance of both Large Language Models and Multimodal LLMs across a variety of input formats for complex tabular data, including LaTeX, HTML, and PNG.
Outcome:	The proposed benchmark evaluates the performance of LLMs and Multimodal LLM models across a variety of input formats for complex tabular data, including LaTeX, HTML, and PNG.

Copied to clipboard

Yang Zhao, Hepeng Wang, Xiao Ding, Yangou Ouyang, Bibo Cai, Kai Xiong, Jinglong Gao, Zhouhao Sun, Li Du, Bing Qin, Ting Liu

MUSE: A Multimodal Conversational Recommendation Dataset with Scenario-Grounded User Profiles (2025.findings-acl)

Challenge:	Group-Relative Policy Optimization (GRPO) has emerged as an efficient paradigm for aligning Large Language Models (LLMs), but its efficacy is confined to domains with verifiable ground truths.
Approach:	They propose a meta-cognitive orchestration layer that treats reward scalarization as a dynamic latent policy, leveraging the model’s terminal hidden states as 'a semantic bottleneck' . Across seven benchmarks, MAESTRO consistently outperforms single-reward and static multi-objective baselines while preserving the efficiency advantages of GRPO.
Outcome:	The proposed model outperforms single-reward and static multi-objective baselines while preserving efficiency advantages.

Copied to clipboard

Zihan Wang, Xiaocui Yang, YongKang Liu, Shi Feng, Daling Wang, Yifei Zhang

Measuring Data Diversity for Instruction Tuning: A Systematic Analysis and A Reliable Metric (2025.acl-long)

Challenge:	Existing research focuses solely on text, leaving a gap with practical applications.
Approach:	They propose to synthesize a multimodal conversational recommendation dataset using multimodal large language models to automatically synthesized data from 7,000 conversations in the Clothing domain.
Outcome:	The proposed dataset contains 83,148 utterances from 7,000 conversations centered around the Clothing domain.

Copied to clipboard

Yuming Yang, Yang Nan, Junjie Ye, Shihan Dou, Xiao Wang, Shuo Li, Huijie Lv, Tao Gui, Qi Zhang, Xuanjing Huang

PsychEval: A Multi-Session and Multi-Therapy Benchmark for High-Realism AI Psychological Counselor (2026.findings-acl)

Challenge:	Existing studies have explored various diversity-aware data selection methods to construct high-quality datasets and enhance model performance.
Approach:	They propose to use data diversity to measure instruction tuning of large language models.
Outcome:	The proposed diversity metric outperforms existing methods on simulated and real-world data and shows that it captures diversity variations and achieves a 0.97 correlation with instruction tuning.

Copied to clipboard

Qianjun Pan, Junyi Wang, Jie Zhou, Yutao Yang, Junsong Li, Kaiyin Xu, Yougen Zhou, Yihan Li, JingYuan Zhao, Qin Chen, Ningning Zhou, Kai Chen, Liang He

Challenge:	Existing models focus on a single therapy, but complex cases require flexible strategies among various therapies.
Approach:	They propose a multi-session, multi-therapy, and highly realistic benchmark . it is designed to address three key challenges: 1) can we train a highly realistic AI counselor? 2) How to systematically evaluate an AI counselor?"
Outcome:	The proposed benchmark is annotated with extensive professional skills and includes over 677 meta-skills and 4577 atomic skills.

Training Language Model to Critique for Better Refinement (2025.findings-acl)

Copied to clipboard

Tianshu Yu, Chao Xiang, Mingchuan Yang, Pei Ke, Bosi Wen, Cunxiang Wang, Jiale Cheng, Li Zhang, Xinyu Mu, Chuxiong Sun, Minlie Huang

Benchmarking LLMs on Authentic Cases from Medical Journals (2026.findings-acl)

Challenge:	Large language models (LLMs) have remarkable evaluation and critique capabilities, providing insightful feedback and identifying flaws in various tasks.
Approach:	They propose a framework to train critic models using refinement signals to generate feedback loops where critiques guide the model in refining its responses.
Outcome:	The proposed framework outperforms traditional methods and open-source models in terms of critique quality and refinement outcomes.

Copied to clipboard

Wanlong Liu, Junying Chen, Yunjin Yang, Prayag Tiwari, Wenyu Chen, Benyou Wang

Challenge:	Existing medical benchmarks suffer from performance saturation due to medical exam questions.
Approach:	They evaluate the performance of over 20 open-source and proprietary large language models and benchmark them against human medical experts.
Outcome:	The new benchmark is based on authentic clinical cases sourced from medical journals and implements rigorous human review process to ensure the quality and reliability of the benchmark.

M2C: Towards Automatic Multimodal Manga Complement (2023.findings-emnlp)

Copied to clipboard

Hongcheng Guo, Boyang Wang, Jiaqi Bai, Jiaheng Liu, Jian Yang, Zhoujun Li

Exploring Multimodal Challenges in Toxic Chinese Detection: Taxonomy, Benchmark, and Findings (2025.findings-acl)

Challenge:	Multimodal manga analysis focuses on enhancing manga understanding with visual and textual features.
Approach:	They propose a task to enhance manga understanding with visual and textual features by providing a shared semantic space for vision and language understanding.
Outcome:	The proposed task provides a shared semantic space for vision and language understanding.

Copied to clipboard

Shujian Yang, Shiyao Cui, Chuanrui Hu, Haicheng Wang, Tianwei Zhang, Minlie Huang, Jialiang Lu, Han Qiu

From Observation to Understanding: Front-Door Adjustments with Uncertainty Calibration for Enhancing Egocentric Reasoning in LVLMs (2025.findings-acl)

Challenge:	Recent studies show that character substitutions in toxic Chinese text can confuse state-of-the-art LLMs.
Approach:	They propose a taxonomy of 3 perturbation strategies and 8 specific approaches in Chinese text to assess if they can detect perturbed Chinese toxic contents.
Outcome:	The proposed model can detect perturbed Chinese text with 8 different approaches . the proposed model is compared with 9 other LLMs from the US and China .

Copied to clipboard

Shenshen Li, Wenxin Meng, Lei Wang, Hao Yang, Chong Peng, Peng Yan, Fumin Shen, Jingkuan Song, Heng Tao Shen, Xing Xu

Internalizing Multi-Agent Reasoning for Accurate and Efficient LLM-based Recommendation (2026.findings-acl)

Challenge:	Existing methods that adapt LVLMs to egocentric tasks overlook critical agent-environment interactions, limiting their ability to perform egoic reasoning.
Approach:	They propose a zero-shot paradigm to enhance egocentric reasoning by simulating human causal reasoning by formalizing ego-centric reasoning using a structural causal model.
Outcome:	The proposed method improves egocentric reasoning abilities on six tasks.

Copied to clipboard

Yang Wu, Haoze Wang, Qian Li, Jun Zhang, Huan Yu, Jie Jiang

Double-Edged Sword or Sharp Tool? Designing and Evaluating Triadic LLM-Teacher Collaboration for K-12 Writing at Scale (2026.findings-acl)

Challenge:	Large Language Models (LLMs) are reshaping recommender systems by leveraging extensive world knowledge and semantic reasoning to interpret user intent.
Approach:	They propose a single-agent Trajectory-Aligned Recommender to integrate reasoning capabilities into a model by a multi-agend teacher system.
Outcome:	The proposed model surpasses its teacher by 8.7% to 39.5% while eliminating iterative latency.

Copied to clipboard

Canran Wang, Yuwen Yang, Zhen Wang, Ming MA, Ding Yu, Chentai Wang, Keman Huang, Xiaoyong Du

MSIA: Adaptive Medical Multimodal Multi-turn Semantic Jailbreak (2026.findings-acl)

Challenge:	a large-scale empirical dataset involving 57,954 essays from 10,195 students across 120 schools over two years is presented in this paper.
Approach:	They propose a triadic collaboration system that supports K-12 writing learning . they propose linguistic expansion as a pedagogical gatekeeper and bridge .
Outcome:	The proposed system improves writing quality through a strategic labor division . authors find that excessive linguistic expansion yields diminishing marginal utility .

Copied to clipboard

Zhiheng Han, Yao Zhang, Jun Wang, Zhenglu Yang

Adaptive Immune-based Sound-Shape Code Substitution for Adversarial Chinese Text Attacks (2024.emnlp-main)

Challenge:	Medical large language models exhibit high domain specificity and condensed semantics, making them vulnerable to diagnostic errors in real-world clinical settings.
Approach:	They propose a framework for modeling and inducing multi-turn medical semantic jailbreaks in clinical dialogues.
Outcome:	Experiments on chest X-ray-based multimodal medical dialogues show that MSIA outperforms existing jailbreak methods with an average success rate of 76.67%.

Copied to clipboard

Ao Wang, Xinghao Yang, Chen Li, Bao-di Liu, Weifeng Liu

Speech-to-Speech Translation for a Real-world Unwritten Language (2023.findings-acl)

Challenge:	Existing text attack methods are designed for English text, but robust implementation of Chinese text is understudied.
Approach:	They propose an adaptive immune-based sound-shape code algorithm for Chinese text attacks . they leverage the Sound-Shape Code to generate natural substitutions .
Outcome:	The proposed algorithm produces high-quality Chinese adversarial examples . it can reduce duplication of population and improve search ability .

Copied to clipboard

Peng-Jen Chen, Kevin Tran, Yilin Yang, Jingfei Du, Justine Kao, Yu-An Chung, Paden Tomasello, Paul-Ambroise Duquenne, Holger Schwenk, Hongyu Gong, Hirofumi Inaguma, Sravya Popuri, Changhan Wang, Juan Pino, Wei-Ning Hsu, Ann Lee

Empathy in Diversity: Personalized Depression and Anxiety Therapy via Dialogue State Tracking and Patient-Aware Planning (2026.acl-long)

Challenge:	a new study examines speech-to-speech translation (S2ST) that translates speech from one language into another . the research area for unwritten languages remains a research area with little exploration due to the lack of training data.
Approach:	They propose a system that translates speech from one language into another . they use Taiwanese Hokkien as an example of an unwritten language .
Outcome:	The proposed system can be used to train models in languages without standard writing systems.

Copied to clipboard

Xinwei Yang, Junyi Fan, Yuqing Liu, Jiaxuan Wang, Jiashuai Zhang, Hongru Liang, Wenqiang Lei, Yao Song

TopKG: Target-oriented Dialog via Global Planning on Knowledge Graph (2022.coling-1)

Challenge:	Recent efforts have turned to large language models (LLMs) as therapeutic agents for psychological therapy tasks, yet robustness across diverse patients remains underexplored.
Approach:	They propose a realistic role-play protocol for evaluating therapeutic dialogue agents and a de-identified, expert-annotated corpus of therapist–patient dialogues.
Outcome:	The proposed framework outperforms baselines on therapeutic outcomes and dialogue quality while improving conversational efficiency.

Copied to clipboard

Zhitong Yang, Bo Wang, Jinfeng Zhou, Yue Tan, Dongming Zhao, Kun Huang, Ruifang He, Yuexian Hou

Probing Audio-Visual Reasoning in Multimodal Language Models through the Lens of Audio (2026.acl-long)

Challenge:	Existing target-oriented dialogs take a local and greedy strategy for response generation, where global planning is absent.
Approach:	They propose a global planning method for target-oriented dialog on a commonsense knowledge graph to adjust local response generation towards the global target.
Outcome:	The proposed method can reach the target with a higher success rate, fewer turns, and more coherent responses.

Copied to clipboard

Kaixiong Gong, Kaituo Feng, Bohao Li, Yibing Wang, Mofan Cheng, Shijia Yang, Jiaming Han, Benyou Wang, Yutong Bai, Zhuoran Yang, Xiangyu Yue

Can Large Language Models Effectively Support Decision-Making in Sudden Emergencies? (2026.findings-acl)

Challenge:	Recent multimodal large language models lack robust audio-visual integration ability and performance on DeafTest is highly correlated with AV-Odyssey accuracy.
Approach:	They propose a benchmarking tool that integrates audio-visual reasoning with audio-video cues to infer solutions.
Outcome:	The proposed model performs well on DeafTest, but lacks audio perception in simple audio tasks.

Copied to clipboard

Mengna Zhu, Jibing Wu, Lihua Liu, Yuran Gong, Yang Hao, Fu Yachao, Mao Wang, Lei Hou, Juanzi Li

Developing multilingual speech synthesis system for Ojibwe, Mi’kmaq, and Maliseet (2025.naacl-short)

Challenge:	Existing research has focused on the earlier stages of emergency response . lack of suitable datasets for reliable and compliance-aware decision-oriented modeling and evaluation is limiting current research .
Approach:	They propose a first real-world emergency decision-making dataset EDM-Bench . they propose 'rule-enhanced reasoning framework' that integrates external regulatory knowledge with constrained inference mechanisms to improve both decision safety and interpretability.
Outcome:	The proposed framework improves decision safety and interpretability by integrating regulatory knowledge with constrained inference mechanisms.

Copied to clipboard

Shenran Wang, Changbing Yang, Michael l Parkhill, Chad Quinn, Christopher Hammerly, Jian Zhu

Document-Level Event Extraction via Information Interaction Based on Event Relation and Argument Correlation (2024.lrec-main)

Challenge:	In general, speech synthesis for Indigenous languages is underdeveloped compared to the majority of languages.
Approach:	They propose to train a multilingual model on three typologically similar languages to improve performance over monolingual models.
Outcome:	The proposed model can train on three similar languages with high performance and is highly competitive with self-attention architectures with higher memory efficiency.

Copied to clipboard

Bangze Pan, Yang Li, Suge Wang, Xiaoli Li, Deyu Li, Jian Liao, Jianxing Zheng

From Curated Data to Scalable Models: Continual Pre-training of Dense and MoE Large Language Models for Tibetan (2026.acl-long)

Challenge:	Document-level Event Extraction (DEE) is a vital task in NLP . current approaches overlook intricate relationships among events and subtle correlations among arguments within a document .
Approach:	They propose a document-level event extraction tool that integrates event relationships and argument correlation graphs to model the relationship among events.
Outcome:	The proposed network outperforms existing models and large language models in terms of F1-score across two benchmark datasets.

Copied to clipboard

Lei Yang, Leiyu Pan, Bojian Xiong, Renren Jin, Shaowei Zhang, Yue Chen, Ling Shi, Jiang Zhou, Junru Wu, Zhen Wang, Jianxiang Peng, Juesi Xiao, Tianyu Dong, Zhuowen Han, Zhuo Chen, Yuqi Ren, Deyi Xiong

Probing the Safety Robustness of LLMs in Latent Space (2026.acl-long)

Challenge:	Large language models have achieved remarkable success across a wide range of tasks, yet their performance remains heavily biased toward high-resource languages.
Approach:	They propose a pipeline for advancing Tibetan language modeling through multilingual continual pre-training with Tibetan, Chinese, and English.
Outcome:	The proposed model outperforms open-source and Tibetan-focused models on diverse tasks.

Copied to clipboard

Tianle Gu, Kexin Huang, Zongqi Wang, Yixu Wang, Jie Li, Xin Wang, Yang Yao, Yujiu Yang, Yan Teng, Yingchun Wang

Capture Human Disagreement Distributions by Calibrated Networks for Natural Language Inference (2022.findings-acl)

Challenge:	Despite substantial progress in safety alignment techniques, aligned large language models can still produce unsafe responses under minor internal perturbations.
Approach:	They introduce Activation Steering Attack (ASA) and leverage the Negative Log-Likelihood (NLL) as a diagnostic signal to probe the local sensitivity of safety behaviors in latent space.
Outcome:	The proposed method is model-agnostic and supervision-free, enabling a general and reproducible diagnostic metric for analyzing safety robustness.

Copied to clipboard

Yuxia Wang, Minghan Wang, Yimeng Chen, Shimin Tao, Jiaxin Guo, Chang Su, Min Zhang, Hao Yang

Synchronized Video Storytelling: Generating Video Narrations with Structured Storyline (2024.acl-long)

Challenge:	Previously, it's common to disregard it as noise or as a sign of poor-quality data, as their annotations are heavily based on personal experience and opinions.
Approach:	They propose to capture the human disagreement distribution from the perspective of model calibration.
Outcome:	The proposed model can achieve competitive performance when well-calibrated, on divergence scores between predictive probability and the true human opinion distribution, and the accuracy.

Copied to clipboard

Dingyi Yang, Chunru Zhan, Ziheng Wang, Biao Wang, Tiezheng Ge, Bo Zheng, Qin Jin

Speech-Text Pre-training for Spoken Dialog Understanding with Explicit Cross-Modal Alignment (2023.acl-long)

Challenge:	Existing studies on dense video captioning and video story generation have made some progress, but in practical applications, we typically require synchronized narrations for ongoing visual scenes.
Approach:	They propose a task of Synchronized Video Storytelling to generate synchronized narrations for videos using a benchmark dataset with rich annotations.
Outcome:	The proposed framework can generate narrations with the guidance of the generated or predefined storyline and human evaluations validate the effectiveness.

Copied to clipboard

Tianshu Yu, Haoyu Gao, Ting-En Lin, Min Yang, Yuchuan Wu, Wentao Ma, Chao Wang, Fei Huang, Yongbin Li

“Mistakes Help Us Grow”: Facilitating and Evaluating Growth Mindset Supportive Language in Classrooms (2023.emnlp-main)

Challenge:	Existing speech-text pre-training methods are limited to one or two specific tasks, despite their success in speech-language processing tasks.
Approach:	They propose a temporal position prediction task to capture the speech-text alignment . they use a textual dialog pre-training task to generalize a response selection task .
Outcome:	The proposed model is superior in learning speech-text alignment and multi-turn dialog context.

Copied to clipboard

Kunal Handa, Margarett Clapper, Jessica Boyle, Rose Wang, Diyi Yang, David Yeager, Dorottya Demszky

START: Self-taught Reasoner with Tools (2025.emnlp-main)

Challenge:	GMSL has been shown to significantly reduce disparities in academic achievement and enhance students’ learning outcomes.
Approach:	They develop a coaching tool to reframe unsupportive utterances to GMSL using large language models.
Outcome:	The proposed model outperforms the GMSL-trained teachers in fostering a growth mindset and promoting challenge-seeking behavior.

Copied to clipboard

Chengpeng Li, Mingfeng Xue, Zhenru Zhang, Jiaxi Yang, Beichen Zhang, Bowen Yu, Binyuan Hui, Junyang Lin, Xiang Wang, Dayiheng Liu

CF-TCIR: A Compositor-Free Framework for Hierarchical Text-Conditioned Image Retrieval (2024.findings-acl)

Challenge:	Large Reasoning Models (LRMs) have demonstrated remarkable capabilities in complex reasoning through long chain-of-thought, yet they struggle with precise computations and algorithmic operations.
Approach:	They propose a training-free approach that activates LRMs’ latent tool-use capabilities through artificial hints and a framework that enables models to learn effective tool utilization through diverse hint patterns and rejection-based data synthesis.
Outcome:	Experiments show that START significantly improves state-of-the-art LRMs across challenging benchmarks, including competition-level mathematics (AMC23: 95.0%, AIME24: 75.6%) and graduate-level science questions (GPQA: 64.6%).

Copied to clipboard

Yuchen Yang, Yu Wang, Yanfeng Wang

MoDULA: Mixture of Domain-Specific and Universal LoRA for Multi-Task Learning (2024.emnlp-main)

Challenge:	Existing approaches to text-conditioned image retrieval use attention-driven compositors . instead, we reformulate the retrieval process as a cross-modal interaction between a synthesized image feature and its corresponding text descriptor.
Approach:	They propose a compositor-free framework for text-conditioned image retrieval . they propose combining a reference image and modification text to form a query tuple .
Outcome:	The proposed framework offers advantages in terms of computational efficiency, scalability, and performance.

Copied to clipboard

Yufei Ma, Zihan Liang, Huangyu Dai, Ben Chen, Dehong Gao, Zhuoran Ran, Wang Zihan, Linbo Jin, Wen Jiang, Guannan Zhang, Xiaoyan Cai, Libin Yang

TESTEVAL: Benchmarking Large Language Models for Test Case Generation (2025.findings-naacl)

Challenge:	Recent advances in open-source Large Language Models (LLMs) have achieved notable successes in natural language processing.
Approach:	They propose a Parameter Efficient Fine-Tuning paradigm for improved fine-tuning and parameter efficiency in multi-task learning.
Outcome:	The proposed model outperforms existing methods on multi-task learning while reducing training costs by over 80% without losing general capability.

Copied to clipboard

Wenhan Wang, Chenyuan Yang, Zhijie Wang, Yuheng Huang, Zhaoyang Chu, Da Song, Lingming Zhang, An Ran Chen, Lei Ma

HowToNarrate: A General-Domain Benchmark for Synchronized Video Narration with External Knowledge (2026.acl-long)

Challenge:	Existing methods to generate test cases using large language models are limited in their ability to generate unit test cases.
Approach:	They propose a test case generation benchmark that uses large language models to generate unit test cases.
Outcome:	The proposed test case generation benchmarks compare LLMs with commercial and open-source LLM platforms and find that they lack the ability to comprehend program logic and execution paths.

Copied to clipboard

Xueyan Wang, Dingyi Yang, Qin Jin

CTC-based Non-autoregressive Speech Translation (2023.acl-long)

Challenge:	Existing MLLMs overemphasize knowledge retrieval while neglecting prior context, causing redundancy and incoherence.
Approach:	They propose a framework that combines context compression, knowledge retrieval, and narration generation to improve models' performance.
Outcome:	The proposed method significantly improves MLLM performance over existing models.

Copied to clipboard

Chen Xu, Xiaoqian Liu, Xiaowen Liu, Qingxuan Sun, Yuhao Zhang, Murun Yang, Qianqian Dong, Tom Ko, Mingxuan Wang, Tong Xiao, Anxiang Ma, Jingbo Zhu

A Sentence Cloze Dataset for Chinese Machine Reading Comprehension (2020.coling-main)

Challenge:	End-to-end speech translation (E2E ST) and non-autoregressive (NAR) generation are promising in language and speech processing for their advantages of less error propagation and low latency.
Approach:	They develop a model that uses connectionist temporal classification to predict the source and target texts.
Outcome:	The proposed model achieves an average BLEU score of 29.5 with a speed-up of 5.67.

Copied to clipboard

Yiming Cui, Ting Liu, Ziqing Yang, Zhipeng Chen, Wentao Ma, Wanxiang Che, Shijin Wang, Guoping Hu

BMAM: Brain-inspired Multi-Agent Memory Framework (2026.findings-acl)

Challenge:	Using cloze-style reading comprehension, Chinese machine reading comprehension datasets are becoming more and more popular . a new task is proposed to fill the right candidate sentence into the passage with several blanks .
Approach:	They propose a Chinese task to fill the right candidate sentence into a passage with blanks . they build a dataset to evaluate the difficulty of the task and make fake candidates .
Outcome:	The proposed task fills the right candidate sentence into the passage with blanks . the proposed dataset contains over 100K blanks within over 10K passages based on Chinese narrative stories .

Copied to clipboard

Yang Li, Jiaxiang Liu, Yusong Wang, Yujie Wu, Mingkun Xu

Challenge:	Language-model-based agents operating over extended interactions face persistent challenges in preserving temporally grounded information and maintaining behavioral consistency across sessions.
Approach:	They propose a general-purpose memory architecture that decomposes agent memory into six components that operate at complementary time scales.
Outcome:	BMAM outperforms memory-augmented baselines on LoCoMo benchmarks with 78.45% accuracy . a targeted refinement of the temporal-trigger heuristics raises LongMemEval multi-session accuracy from 45.2% to 56.4%.

ACRM: Multi-Agent Trajectory Learning for Automated Credit Risk Model Refreshing in Production (2026.acl-industry)

Copied to clipboard

Liangzu Liu, Mengzhe Ruan, Xiaotian Chen, null HaonanChen, null XudongNiu, Wendi Yuan, null YuechenLi, Yang Liu, Guanjun Wang

Challenge:	Credit risk models suffer from rapid performance decay due to distribution shifts, requiring frequent updates to meet strict operational guardrails.
Approach:	They propose a multi-agent framework that treats model refreshing as a learnable trajectory of agent interactions.
Outcome:	The proposed framework reduces the average model refresh cycle from weeks to 1.1 days and iteration rounds by 65% while maintaining superior stability metrics.

CODEMENV: Benchmarking Large Language Models on Code Migration (2025.findings-acl)

Copied to clipboard

Keyuan Cheng, Xudong Shen, Yihao Yang, TengyueWang TengyueWang, Yang Cao, Muhammad Asif Ali, Hanbin Wang, Lijie Hu, Di Wang

MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualization (2024.findings-acl)

Challenge:	Large language models (LLMs) have demonstrated remarkable proficiency in handling a wide range of tasks within the software engineering domain, but their ability to perform code migration—adapting code to different environments—remains underexplored.
Approach:	They propose a benchmark to evaluate large language models’ performance in handling code migration tasks.
Outcome:	The proposed benchmark comprises 922 data points across 19 Python and Java packages and offers three tasks to systematically evaluate code migration: identifying version-incompatible functions, determining function changes, and adapting code to target environments.

Copied to clipboard

Zhiyu Yang, Zihan Zhou, Shuo Wang, Xin Cong, Xu Han, Yukun Yan, Zhenghao Liu, Zhixing Tan, Pengyuan Liu, Dong Yu, Zhiyuan Liu, Xiaodong Shi, Maosong Sun

LLM-Based Agent Society Investigation: Collaboration and Confrontation in Avalon Gameplay (2024.emnlp-main)

Challenge:	Scientific data visualization is an essential process in research, but its use of large language models remains unexplored.
Approach:	They propose a model-agnostic LLM agent framework to automate scientific data visualization tasks.
Outcome:	The proposed framework improves performance of commercial and open-source models.

Copied to clipboard

Yihuai Lan, Zhiqiang Hu, Lei Wang, Yang Wang, Deheng Ye, Peilin Zhao, Ee-Peng Lim, Hui Xiong, Hao Wang

Challenge:	Existing studies on LLM agents' social behaviors are lacking . previous studies focused on positive social behaviors, leaving research on negative social behaviors relatively scarce.
Approach:	They propose a framework that features a multi-agent system facilitating efficient communication and interaction with LLM agents.
Outcome:	The proposed framework is based on Avalon and evaluates on game success and analyzes agents’ social behaviors.

ImpRIF: Stronger Implicit Reasoning Leads to Better Complex Instruction Following (2026.acl-long)

Copied to clipboard

Yuancheng Yang, Lin Yang, Xu Wang, Chao Tong, Haihua Yang

Value Compass Benchmarks: A Comprehensive, Generative and Self-Evolving Platform for LLMs’ Value Evaluation (2025.acl-demo)

Challenge:	Experiments show that enhancing implicit reasoning capabilities can significantly improve complex instruction following in large language models.
Approach:	They propose a method to enhance LLMs’ understanding of implicit reasoning instructions by formalizing such instructions as verifiable reasoning graphs and fine-tuning with graph reasoning.
Outcome:	The proposed method outperforms existing models on five complex instruction following benchmarks and will be open-sourced in the near future.

Copied to clipboard

Jing Yao, Xiaoyuan Yi, Shitong Duan, Jindong Wang, Yuzhuo Bai, Muhua Huang, Yang Ou, Scarlett Li, Peng Zhang, Tun Lu, Zhicheng Dou, Maosong Sun, James Evans, Xing Xie

Challenge:	Current evaluation methods for large language models face two key challenges: 1. evaluation validity and 2. Result interpretation reduce the pluralistic and incommensurable values to one-dimensional scores.
Approach:	They propose a platform for comprehensive value diagnosis of large language models (LLMs) that provides a generative evaluation paradigm that automatically creates real-world test items co-evolving with ever-advancing LLMs.
Outcome:	The proposed platform provides a framework for comprehensive value diagnosis of large language models (LLMs) with fine-grained scores and case studies across 27 value dimensions for 33 leading LLMs, customized comparisons, and visualized analysis of LLM’s alignment with cultural values.

Consultant Decoding: Yet Another Synergistic Mechanism (2025.findings-acl)

Copied to clipboard

Chuanghao Ding, Jiaping Wang, Ziqing Yang, Xiaoliang Wang, Dahua Lin, Nguyen Cam-Tu, Fei Tan

Rethinking Token Reduction for State Space Models (2024.emnlp-main)

Challenge:	Large language models (LLMs) have attracted widespread attention and adoption across diverse domains due to their exceptional performance and robust generalization abilities.
Approach:	They propose a synergetic mechanism for Consultant Decoding (CD) that achieves a 2.5-fold increase in inference speed compared to the target model while maintaining comparable generation quality.
Outcome:	The proposed mechanism achieves 2.5-fold increase in inference speed while maintaining comparable generation quality (100% of the target model’s performance).

Copied to clipboard

Zheng Zhan, Yushu Wu, Zhenglun Kong, Changdi Yang, Yifan Gong, Xuan Shen, Xue Lin, Pu Zhao, Yanzhi Wang

Challenge:	Existing methods for token reduction for SSMs lead to performance drops . a recent study shows that Mamba-2 improves the accuracy of the model by 5.7% to 13.1% .
Approach:	They propose a token reduction method that integrates token importance and similarity into SSMs and takes advantage of pruning and merging.
Outcome:	The proposed method improves accuracy by 5.7% to 13.1% on six benchmarks with Mamba-2 compared to existing methods while reducing computational demands and memory requirements.

Prompt-Guided Retrieval Augmentation for Non-Knowledge-Intensive Tasks (2023.findings-acl)

Copied to clipboard

Zhicheng Guo, Sijie Cheng, Yile Wang, Peng Li, Yang Liu

WildSci: Advancing Scientific Reasoning from In-the-Wild Literature (2026.findings-acl)

Challenge:	Recent studies focus on retrieval to solve knowledge-intensive tasks, but the potential of retrieval for non-knowledge-intensive (NKI) tasks remains under-explored.
Approach:	They propose a task-agnostic retrieval framework for NKI tasks that uses a static index and a prompt-guided reranker to re-rank the nearest evidence according to task-specific relevance.
Outcome:	The proposed framework outperforms state-of-the-art retrieval-augmented methods on NKI tasks and will be released for further research.

Copied to clipboard

Tengxiao Liu, Deepak Nathani, Zekun Li, Kevin Yang, William Yang Wang

PsyCoT: Psychological Questionnaire as Powerful Chain-of-Thought for Personality Detection (2023.findings-emnlp)

Challenge:	Recent advances in large language model reasoning focus on mathematics and coding domains, but scientific reasoning remains limited in other domains due to limited dataset coverage.
Approach:	They propose a framework for sustainable scientific reasoning QA generation by synthesizing a new dataset of domain-specific science questions from peer-reviewed literature.
Outcome:	The proposed framework and dataset enable scalable and sustainable research in scientific reasoning.

Copied to clipboard

Tao Yang, Tianyuan Shi, Fanqi Wan, Xiaojun Quan, Qifan Wang, Bingzhe Wu, Jiaxiang Wu

Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens (2026.findings-acl)

Challenge:	Recent advances in large language models (LLMs) have demonstrated remarkable zero-shot performance across various NLP tasks.
Approach:	They propose a method which mimics the way individuals complete psychological questionnaires in a multi-turn dialogue manner and prompts an LLM to rate individual items at each turn.
Outcome:	The proposed method improves the performance and robustness of the standard GPT-3.5 personality detection task on two benchmark datasets.

Copied to clipboard

Chengshuai Zhao, Zhen Tan, Pingchuan Ma, Dawei Li, Bohan Jiang, Yancheng Wang, Yingzhen Yang, Huan Liu

AMA: Adaptive Memory via Multi-Agent Collaboration (2026.findings-acl)

Challenge:	Chain-of-Thought (CoT) prompting has been shown to be effective in eliciting structured reasoning from large language models (LLMs).
Approach:	They propose a data distribution lens to understand when and why CoT reasoning fails . they propose 'data-based' training that trains LLMs from scratch .
Outcome:	The proposed model enables models to generate reasoning trajectories that approximate those observed during training.

Copied to clipboard

Weiquan Huang, Zixuan Wang, Hehai Lin, Sudong Wang, Bo Xu, Qian Li, Beier Zhu, Linyi Yang, Chengwei Qin

Data Diversity Matters for Robust Instruction Tuning (2024.findings-emnlp)

Challenge:	Existing approaches to longterm memory rely on rigid retrieval granularity, accumulation-heavy maintenance strategies, and coarse-grained update mechanisms.
Approach:	They propose a framework that leverages coordinated agents to manage memory across multiple granularities.
Outcome:	The proposed framework outperforms state-of-the-art benchmarks while reducing token consumption by approximately 80%.

Copied to clipboard

Alexander Bukharin, Shiyang Li, Zhengyang Wang, Jingfeng Yang, Bing Yin, Xian Li, Chao Zhang, Tuo Zhao, Haoming Jiang

Contrastive Pre-training for Personalized Expert Finding (2023.findings-emnlp)

Challenge:	Recent studies have shown that by curating high quality and diverse instruction tuning datasets, we can significantly improve instruction-following capabilities.
Approach:	They propose an algorithm to control diversity and quality of instruction tuning datasets and validate it.
Outcome:	The proposed algorithm significantly improves worst and average case performance on large scale instruction tuning datasets.

Copied to clipboard

Qiyao Peng, Hongtao Liu, Zhepeng Lv, Qing Yang, Wenjun Wang

T2IAT: Measuring Valence and Stereotypical Biases in Text-to-Image Generation (2023.findings-acl)

Challenge:	Existing approaches to expert finding are effective for a community question answering platform.
Approach:	They propose a CQA-domain Contrastive Pre-training framework for Expert Finding which could learn more comprehensive question representations.
Outcome:	The proposed framework could learn more comprehensive question representations on six real-world datasets.

Copied to clipboard

Jialu Wang, Xinyue Liu, Zonglin Di, Yang Liu, Xin Wang

TextBrewer: An Open-Source Knowledge Distillation Toolkit for Natural Language Processing (2020.acl-demos)

Challenge:	Recent advances in text-to-image generative models have produced high quality images with a breakthrough of inference speed.
Approach:	They propose a text-to-image association test framework that quantifies implicit stereotypes between concepts and valence and those in images.
Outcome:	The proposed framework quantifies implicit stereotypes between concepts and valence and those in images.

Copied to clipboard

Ziqing Yang, Yiming Cui, Zhipeng Chen, Wanxiang Che, Ting Liu, Shijin Wang, Guoping Hu

Time-MQA: Time Series Multi-Task Question Answering with Context Enhancement (2025.acl-long)

Challenge:	Large pre-trained language models have hundreds of millions of parameters and take several gigabytes of memory to train and inference.
Approach:	They propose an open-source knowledge distillation toolkit designed for natural language processing that provides a set of predefined distillation methods and can be extended with custom code.
Outcome:	The proposed method is comparable with or even higher than the public distilled BERT models with similar numbers of parameters.

Copied to clipboard

Yaxuan Kong, Yiyuan Yang, Yoontae Hwang, Wenjie Du, Stefan Zohren, Zhangyang Wang, Ming Jin, Qingsong Wen

ETRQA: A Comprehensive Benchmark for Evaluating Event Temporal Reasoning Abilities of Large Language Models (2025.findings-acl)

Challenge:	Existing time series models focus on a narrow spectrum of tasks, such as forecasting or anomaly detection.
Approach:	They propose a framework that enables natural language queries across multiple time series tasks such as numerical analytical tasks and open-ended question answering with reasoning.
Outcome:	The proposed framework enables natural language queries across multiple time series tasks and allows for more advanced and intuitive interactions with temporal data.

Copied to clipboard

Sigang Luo, Yinan Liu, Dongying Lin, Yingying Zhai, Bin Wang, Xiaochun Yang, Junpeng Liu

Pixel-Level Reasoning Segmentation via Multi-turn Conversations (2025.acl-long)

Challenge:	Event temporal reasoning (ETR) is a significant indicator that a large language model understands the physical world.
Approach:	They propose a unified taxonomy for event temporal questions and construct a benchmark based on this taxonomies.
Outcome:	The proposed taxonomy inherits and expands existing datasets and contains multiple categories of compound questions.

Copied to clipboard

Dexian Cai, Xiaocui Yang, YongKang Liu, Daling Wang, Shi Feng, Yifei Zhang, Soujanya Poria

Comprehensive Benchmarking of Long-Form Speech Generation in Diverse Scenarios (2026.findings-acl)

Challenge:	Existing visual perception systems focus on region-level segmentation in single-turn dialogues . existing systems cannot reason at the pixel level and comprehend dynamic user intent .
Approach:	They propose a task that tracks evolving user intent via multi-turn interactions for fine-grained segmentation.
Outcome:	The proposed method outperforms existing baselines in segmentation and reasoning metrics.

Copied to clipboard

Changhao Pan, Rui Yang, Han Wang, Zhuan Zhou, Xuming He, Wenxiang Guo, Ziyue Jiang, Ruiqi Li, Yu Zhang, Chenyuhao Wen, Ke Lei, Xiang Yin, Jingyu Lu, Zhiyuan Zhu, Zhou Zhao

Recall and Learn: A Memory-augmented Solver for Math Word Problems (2021.findings-emnlp)

Challenge:	Existing evaluation benchmarks for long-form speech are limited to limited domains, creating a significant gap with the diverse downstream applications.
Approach:	They propose a benchmark that decomposes "long-form speech quality" into specific, disentangled dimensions.
Outcome:	The proposed benchmark decomposes “long-form speech quality” into specific, disentangled dimensions.

Copied to clipboard

Shifeng Huang, Jiawei Wang, Jiao Xu, Da Cao, Ming Yang

Deciphering Stereotypes in Pre-Trained Language Models (2023.emnlp-main)

Challenge:	Existing methods for solving math word problems are based on template-based generation which results in limited generalization capability.
Approach:	They propose a human-like analogical learning method for the math word problem . it uses modules of memory, representation, analogy, and reasoning to make a new exercise .
Outcome:	The proposed method outperforms state-of-the-art models on two well-known datasets.

Copied to clipboard

Weicheng Ma, Henry Scheible, Brian Wang, Goutham Veeramachaneni, Pratim Chowdhary, Alan Sun, Andrew Koulogeorge, Lili Wang, Diyi Yang, Soroush Vosoughi

InfiMM: Advancing Multimodal Understanding with an Open-Sourced Visual Language Model (2024.findings-acl)

Challenge:	Current approaches for examining stereotypes in PLMs require intricate human knowledge about these stereotypes and entail careful manual curation of examples.
Approach:	They propose a framework for examining stereotype-encoding behavior of PLMs using model probing and textual analyses.
Outcome:	The proposed approach can debiase PLMs without compromising their language modeling capabilities or performance.

Copied to clipboard

Haogeng Liu, Quanzeng You, Yiqi Wang, Xiaotian Han, Bohan Zhai, Yongfei Liu, Wentao Chen, Yiren Jian, Yunzhe Tao, Jianbo Yuan, Ran He, Hongxia Yang

Improving Deep Embedded Clustering via Learning Cluster-level Representations (2022.coling-1)

Challenge:	InfiMM is a multimodal large language model that adapts to complex vision-language tasks.
Approach:	They present a Multimodal Large Language Model that adapts to intricate vision-language tasks using large-scale training data and comprehensive training strategies.
Outcome:	Empirical evaluations across a variety of benchmarks underscore InfiMM’s remarkable capability in multimodal understanding.

Copied to clipboard

Qing Yin, Zhihua Wang, Yunya Song, Yida Xu, Shuai Niu, Liang Bai, Yike Guo, Xian Yang

OpenS2S: Advancing Fully Open-Source End-to-End Empathetic Large Speech Language Model (2025.emnlp-demos)

Challenge:	Existing efforts to learn meaningful representations at the instance level are limited.
Approach:	They propose a deep embedded clustering model with cluster-level representation learning to jointly learn cluster and instance level representations.
Outcome:	The proposed model produces meaningful clusters on real-world short text datasets.

Copied to clipboard

Chen Wang, Tianyu Peng, Wen Yang, YiNan Bai, Guangfu Wang, Jun Lin, Lanpeng Jia, Lingxiang Wu, Jinqiao Wang, Chengqing Zong, Jiajun Zhang

Speech-Hands: A Self-Reflection Voice Agentic Approach to Speech Recognition and Audio Reasoning with Omni Perception (2026.acl-long)

Challenge:	Empathetic speech models are increasingly closed off, leaving details about the architecture, data and development opaque to researchers.
Approach:	They propose an open-source empathetic speech-to-text model with a streaming interleaved decoding architecture and a data pipeline to enable end-to end training.
Outcome:	The proposed model is open-source and transparent, with no data or data required to build it.

Copied to clipboard

Zhen Wan, Chao-Han Huck Yang, Jinchuan Tian, Hanrong Ye, Ankita Pasad, Szu-Wei Fu, Arushi Goel, Ryo Hachiuma, Shizhe Diao, Kunal Dhawan, Sreyan Ghosh, Yusuke Hirota, Zhehuai Chen, Rafael Valle, Chenhui Chu, Shinji Watanabe, Boris Ginsburg, Yu-Chiang Frank Wang

INarIG: Iterative Non-autoregressive Instruct Generation Model For Word-Level Auto Completion (2023.findings-emnlp)

Challenge:	naively fine-tuning an omni-model on speech recognition and external sound understanding tasks often degrades performance . Xie and Wu's framework, Speech-Hands, recasts the problem as an explicit self-reflection decision.
Approach:	They propose a voice-agentic framework that learns one critical omni-understanding skill: trusting itself versus external audio perception.
Outcome:	The proposed framework outperforms baseline models on the OpenASR leaderboard by 12.1% WER and high F1 on audio QA decisions.

Copied to clipboard

Hengchao Shang, Zongyao Li, Daimeng Wei, Jiaxin Guo, Minghan Wang, Xiaoyu Chen, Lizhi Lei, Hao Yang

LACMA: Language-Aligning Contrastive Learning with Meta-Actions for Embodied Instruction Following (2023.emnlp-main)

Challenge:	Existing models for word-level autocompletion (WLAC) only use human typed sequences as prefixes in decoding module.
Approach:	They propose a novel iterative nonautoregressive instruct generation model for WLAC task . it uses human typed sequences and iterating decoding with subwords to fully utilize input information.
Outcome:	The proposed model is more competent in dealing with low-frequency words, and achieves state-of-the-art results on the WMT22 and benchmark datasets.

Copied to clipboard

Cheng-Fu Yang, Yen-Chun Chen, Jianwei Yang, Xiyang Dai, Lu Yuan, Yu-Chiang Wang, Kai-Wei Chang

Knowledge Poisoning Attacks on Medical Multi-Modal Retrieval-Augmented Generation (2026.acl-long)

Challenge:	Embodied Instruction Following has shown an impressive success rate when the environment has been seen in training, but when deployed in an unseen environment, it tends to struggle when deployed with an unsightly environment.
Approach:	They propose to explicitly align the agent’s hidden states with the instructions via contrastive learning to bridge the semantic gap between high-level language instructions and the agent's low-level action space.
Outcome:	The proposed meta-actions achieve a 4.5% success rate in unseen environments compared to a strong multi-modal Transformer baseline .

Copied to clipboard

Peiru Yang, Haoran Zheng, Tong Ju, Shiting Wang, Wanchun Ni, Jiajun Liu, Shangguang Wang, Yongfeng Huang, Tao Qi

MetaMem: Evolving Meta-Memory for Knowledge Utilization through Self-Reflective Symbolic Optimization (2026.findings-acl)

Challenge:	Existing studies have investigated knowledge poisoning attacks in medical RAG systems . knowledge poison attacks can disrupt model outputs and undermine system reliability .
Approach:	They propose a knowledge poisoning framework that injects misinformation into textual data . they propose to use paired visual data as a query-agnostic trigger to promote retrieval .
Outcome:	The proposed framework produces clinically plausible but incorrect generations on five LLMs and datasets.

Copied to clipboard

Haidong Xin, Xinze Li, Zhenghao Liu, Yukun Yan, Shuo Wang, Cheng Yang, Yu Gu, Ge Yu, Maosong Sun

V-MAGE: A Game Evaluation Framework for Assessing Vision-Centric Capabilities in Multimodal Large Language Models (2026.findings-acl)

Challenge:	Existing memory systems can support long-horizon human-LLM interactions by persisting historical interactions beyond limited context windows.
Approach:	They propose a framework that augments memory systems with a self-evolving meta-memory . meta-meso is iteratively distilling transferable knowledge utilization experiences . results show MetaMem outperforms strong baselines by over 3.6% .
Outcome:	The proposed framework outperforms baselines by over 3.6% in the long-horizon human-LLM interaction.

Copied to clipboard

Xiangxi Zheng, Linjie Li, Zhengyuan Yang, Ping Yu, Alex Jinpeng Wang, Rui Yan, Yuan Yao, Lijuan Wang

Elevating Legal LLM Responses: Harnessing Trainable Logical Structures and Semantic Knowledge with Legal Reasoning (2025.naacl-long)

Challenge:	Existing static image-text benchmarks are insufficient for evaluating multimodal large language models’ dynamic perception and interactive reasoning abilities.
Approach:	They propose a game-based evaluation framework to assess multimodal large language models’ visual reasoning in dynamic, continuous-space environments.
Outcome:	The proposed framework systematically assesses MLLMs’ visual reasoning in dynamic, continuous-space environments.

Copied to clipboard

Rujing Yao, Yang Wu, Chenghao Wang, Jingwei Xiong, Fang Wang, Xiaozhong Liu

Pruning via Merging: Compressing LLMs via Manifold Alignment Based Layer Merging (2024.emnlp-main)

Challenge:	Existing approaches to large language models focus on semantic similarity, neglecting the intricate logical structures and reasoning essential for addressing complex legal issues.
Approach:	They propose a Logical-Semantic Integration Model (LSIM) that bridges semantic and logical coherence and a supervised framework that integrates semantic features with in-context learning.
Outcome:	The proposed framework significantly improves accuracy and reliability on a real-world legal QA dataset.

Copied to clipboard

Deyuan Liu, Zhanyue Qin, Hairu Wang, Zhao Yang, Zecheng Wang, Fangying Rong, Qingbin Liu, Yanchao Hao, Bo Li, Xi Chen, Cunhang Fan, Zhao Lv, Dianhui Chu, Zhiying Tu, Dianbo Sui

Exploring Concept Depth: How Large Language Models Acquire Knowledge and Concept at Different Layers? (2025.coling-main)

Challenge:	Existing methods for parameter pruning fail to utilize the knowledge from pruned parameters.
Approach:	They propose a method that uses manifold learning and the Information Bottleneck measure to merge similar layers to preserve model performance.
Outcome:	The proposed method outperforms pruning methods on multiple datasets and LLMs with quantization and achieves substantial compression ratios.

Copied to clipboard

Mingyu Jin, Qinkai Yu, Jingyuan Huang, Qingcheng Zeng, Zhenting Wang, Wenyue Hua, Haiyan Zhao, Kai Mei, Yanda Meng, Kaize Ding, Fan Yang, Mengnan Du, Yongfeng Zhang

AlignedCoT: Prompting Large Language Models via Native-Speaking Demonstrations (2024.findings-emnlp)

Challenge:	Large language models have shown remarkable performances across a wide range of tasks, but mechanisms by which they encode tasks of varying complexity remain poorly understood.
Approach:	They propose to explore the possibility that LLMs process concepts in different layers . they propose to categorize concepts based on their level of abstraction .
Outcome:	The proposed model can process complex concepts in shallow layers, the authors show . the proposed model could be used to prob complex tasks in shallow ones .

Copied to clipboard

Zhicheng Yang, Yinya Huang, Jing Xiong, Liang Feng, Xiaodan Liang, Yiwei Wang, Jing Tang

Does Visual Grounding Enhance the Understanding of Embodied Knowledge in Large Language Models? (2025.findings-emnlp)

Challenge:	Existing LLMs are delicate and elusive in prompt words and styles.
Approach:	They propose an LLM-acquainted prompting technique that includes proficient "native-speaking" they propose to use in-context learning to prompt LLMs to perform high-performance reasoning .
Outcome:	The proposed technique achieves step-wise prompts in zero-shot scenarios while maintaining the prompt quality.

Copied to clipboard

Zhihui Yang, Yupei Wang, Kaijie Mo, Zhe Zhao, Renfen Hu

UniGeM: Unifying Data Selection and Mixing via Geometric Exploration and Mining (2026.findings-acl)

Challenge:	Despite significant progress in multimodal language models, it remains unclear whether visual grounding enhances their understanding of embodied knowledge compared to text-only models.
Approach:	They propose to assess vision-language models’ perceptual abilities across different sensory modalities through vector comparison and question-answering tasks with over 1,700 questions.
Outcome:	The proposed benchmark assesses the models’ perceptual abilities across different sensory modalities through vector comparison and question-answering tasks with over 1,700 questions.

Copied to clipboard

Changhao Wang, null Yunfeiyu, Xinhao Yao, Jiaolong Yang, Lu Yu, Junpeng Fang, Chaobo Li, Riccardo Cantoro, Qing Cui, Jun Zhou

Challenge:	Large Language Models (LLMs) scaling is limited by data quality and domain mixing and instance selection are two separate problems.
Approach:	They propose a framework that unifies mixing and selection without training proxy models or relying on external reference datasets.
Outcome:	The proposed framework achieves 2.0 data efficiency over a random baseline and further improves overall performance compared to SOTA methods in reasoning-heavy evaluations and multilingual generalization.

MMErroR: A Benchmark for Erroneous Reasoning in Vision-Language Models (2026.acl-long)

Copied to clipboard

Yang Shi, Yifeng Xie, Minzhe Guo, Liangsi Lu, Mingxuan Huang, Jingchao Wang, Zhihong Zhu, Boyan Xu, Zhiqi Huang

StableToolBench-MirrorAPI: Modeling Tool Environments as Mirrors of 7,000+ Real-World APIs (2025.findings-acl)

Challenge:	Recent advances in vision-language models have improved performance in multi-modal learning.
Approach:	They propose a multi-modal benchmark that embeds a single coherent reasoning error in 1997 samples.
Outcome:	The proposed benchmark is based on a set of 1997 samples embedding a single coherent reasoning error.

Copied to clipboard

Zhicheng Guo, Sijie Cheng, Yuchen Niu, Hao Wang, Sicheng Zhou, Wenbing Huang, Yang Liu

SUN: Exploring Intrinsic Uncertainties in Text-to-SQL Parsers (2022.coling-1)

Challenge:	Existing tool environments face challenges in balancing stability, scale, and realism, especially for benchmarking purposes.
Approach:	They propose a framework that trains specialized LLMs to accurately simulate real API responses by supervised fine-tuning and chain-of-thought reasoning.
Outcome:	The proposed framework achieves superior accuracy and stability compared to state-of-the-art methods on the newly constructed MirrorAPI-Bench and its integration into StableToolBench.

Copied to clipboard

Bowen Qin, Lihan Wang, Binyuan Hui, Bowen Li, Xiangpeng Wei, Binhua Li, Fei Huang, Luo Si, Min Yang, Yongbin Li

Improving Zero-shot LLM Re-Ranker with Risk Minimization (2024.emnlp-main)

Challenge:	Existing methods that learn from multiple semantically-equivalent questions are limited to one-to-one mapping .
Approach:	They propose a constraint to explore the underlying complementary semantic information among multiple semantically-equivalent questions and learn robust feature representations with reduced spurious associations.
Outcome:	The proposed method outperforms strong competitors and achieves state-of-the-art results on five benchmark datasets.

Copied to clipboard

Xiaowei Yuan, Zhao Yang, Yequan Wang, Jun Zhao, Kang Liu

From Mimesis to Metamorphosis: Evolving VLM Judges via In-Context Comparing and Knowledge Internalization (2026.findings-acl)

Challenge:	Large Language Models (LLMs) are effective Query Likelihood Models, but their estimation is biased and the model's accuracy is poor.
Approach:	They propose a framework which leverages Bayesian decision theory to quantify and mitigate this bias.
Outcome:	The proposed framework improves re-ranking, especially in improving the Top-1 accuracy.

Copied to clipboard

Juntuo Wang, Yuming Qiao, Yifan Yang, Lunxi Yuan, Liang Luo, Dan Meng

Sentient Agent as a Judge: Evaluating Higher-Order Social Cognition in Large Language Models (2026.findings-acl)

Challenge:	Existing approaches to subjective assessment are inconsistent and inconsistent due to inconsistent scales and inherent preference biases.
Approach:	They propose a framework that operationalizes subjective assessment as comparative analysis and internalizes it via Language Buttons.
Outcome:	The proposed framework achieves state-of-the-art performance across multiple benchmarks and is scale-steerable.

Copied to clipboard

Bang Zhang, Ruotian Ma, Qingxuan Jiang, Peisong Wang, Jiaqi Chen, Zheng Xie, Xingyu Chen, Yue Wang, Fanghua Ye, Jian Li, Yifan Yang, Zhaopeng Tu, Xiaolong Li

Multimodal Dialogue Response Generation (2022.acl-long)

Challenge:	Large language models (LLMs) have evolved from statistical sequence predictors to sophisticated autonomous agents capable of reasoning, planning, and sustaining multi-turn conversa-tions.
Approach:	They propose a system that instantiates a "Sentient Agent" that simulates human-like emotional changes and inner thoughts to provide a more realistic evaluation of the model in multi-turn conversations.
Outcome:	The proposed framework measures the agent's higher-order social cognition in multi-turn conversations.

Copied to clipboard

Qingfeng Sun, Yujing Wang, Can Xu, Kai Zheng, Yaming Yang, Huang Hu, Fei Xu, Jessica Zhang, Xiubo Geng, Daxin Jiang

A Speaker-Aware Co-Attention Framework for Medical Dialogue Information Extraction (2022.emnlp-main)

Challenge:	Existing studies focus on multimodal dialogue models but neglect generation methods.
Approach:	They propose a multimodal dialogue response generation task which requires multimodal dialogs containing both texts and images which are difficult to obtain.
Outcome:	Experiments show that the proposed model can generate informative text and high-resolution image responses.

Copied to clipboard

Yuan Xia, Zhenhui Shi, Jingbo Zhou, Jiayu Xu, Chao Lu, Yehui Yang, Lei Wang, Haifeng Huang, Xia Zhang, Junwei Liu

Evaluating Cognitive-Behavioral Fixation via Multimodal User Viewing Patterns on Social Media (2025.emnlp-main)

Challenge:	With the development of medical digitization, the extraction and structuring of electronic medical records (EMRs) have become challenging but fundamental tasks.
Approach:	They propose a speaker-aware dialogue encoder with multi-task learning which takes the speaker's identity into account and a co-attention fusion network to aggregate the utterance information.
Outcome:	The proposed framework outperforms the state-of-the-art methods on the public medical dialogue extraction datasets to demonstrate its superiority.

Copied to clipboard

Yujie Wang, Yunwei Zhao, Jing Yang, Han Han, Shiguang Shan, Jie Zhang

CodexGraph: Bridging Large Language Models and Code Repositories via Code Graph Databases (2025.naacl-long)

Challenge:	Digital media platforms often contribute to cognitive-behavioral fixation, a phenomenon in which users exhibit sustained and repetitive engagement with narrow content domains.
Approach:	They propose a multimodal topic extraction module and a cognitive-behavioral fixation quantification module that collaboratively enable adaptive, hierarchical, and interpretable assessment of user behavior.
Outcome:	The proposed framework lays the groundwork for scalable computational analysis of cognitive fixation.

Copied to clipboard

Xiangyan Liu, Bo Lan, Zhiyuan Hu, Yang Liu, Zhicheng Zhang, Fei Wang, Michael Qizhe Shieh, Wenmeng Zhou

Mimicking the Familiar: Dynamic Command Generation for Information Theft Attacks in LLM Tool-Learning System (2025.acl-long)

Challenge:	Large Language Models excel in stand-alone code tasks but struggle with handling entire code repositories.
Approach:	They propose a system that integrates LLM agents with graph database interfaces extracted from code repositories.
Outcome:	The proposed system integrates LLM agents with graph database interfaces extracted from code repositories.

Copied to clipboard

Ziyou Jiang, Mingyang Li, Guowei Yang, Junjie Wang, Yuekai Huang, Zhiyuan Chang, Qing Wang

Low-Resource Language Expansion and Translation Capacity Enhancement for LLM: A Study on the Uyghur (2025.coling-main)

Challenge:	Existing approaches to attack Large Language Model (LLM) tool-learning systems are black-box oriented and rely on static commands that cannot adapt flexibly to the changes in user queries and the invocation chain.
Approach:	They propose a dynamic attack comment generation approach for information theft attacks in LLM tool-learning systems that mimics the familiar by inferring the information utilized by upstream tools.
Outcome:	The proposed approach outperforms baselines with +13.2% ASRTheft and can be generalized to new tool-learning systems to expose their information leakage risks.

Copied to clipboard

Kaiwen Lu, Yating Yang, Fengyi Yang, Rui Dong, Bo Ma, Aihetamujiang Aihemaiti, Abibilla Atawulla, Lei Wang, Xi Zhou

RepSum: Unsupervised Dialogue Summarization based on Replacement Strategy (2021.acl-long)

Challenge:	Extensive experiments have shown that our strategy effectively expands the low-resource languages supported by large language models and significantly enhances the model’s translation ability in Uyghur with less parallel data.
Approach:	They propose a direct preference optimization based on translation self-evolution to expand low-resource languages into large language models by using Uyghur as an example.
Outcome:	The proposed strategy expands low-resource languages supported by large language models and significantly enhances the model’s translation ability in Uyghur with less parallel data.

Copied to clipboard

Xiyan Fu, Yating Zhang, Tianyi Wang, Xiaozhong Liu, Changlong Sun, Zhenglu Yang

Model-Based Imaginative Planning for Embodied Agents (2026.acl-long)

Challenge:	Existing methods to learn vital information from dialogue context with limited data are limited due to limited words in utterances and huge gap between dialogue and its summary.
Approach:	They propose an unsupervised strategy to learn vital information from dialogue context . the proposed model uses a hypothetical foundation that a superior summary approximates a replacement of the original dialogue .
Outcome:	The proposed model outperforms existing models on a number of datasets.

Copied to clipboard

Junru Song, Hengzhe Jin, Yucong Huang, Tingsong Jiang, Weien Zhou, Feifei Wang, Yang Yang, Ying Wen, Wen Yao

MdEval: Massively Multilingual Code Debugging (2026.findings-acl)

Challenge:	a lightweight world model converts raw pixels into object-centric symbolic states amenable to language-based reasoning . IMPLEMENT is a framework for grounding language agents in visual embodied environments .
Approach:	They propose a model-based reasoning framework that enables frozen large language models to perform imaginative planning.
Outcome:	The proposed framework can be used to ground language agents in visual embodied environments.

Copied to clipboard

Shukai Liu, Linzheng Chai, Jian Yang, Jiajun Shi, He Zhu, Liran Wang, Jin Ke, Wei Zhang, Hualei Zhu, Shuyue Guo, Tao Sun, Jiaheng Liu, Yunlong Duan, Yu Hao, Liqun Yang, Guanglin Niu, Ge Zhang, Zhoujun Li

SLoRA: Balancing Plasticity and Forgetting in Large Language Models for Continual Learning (2026.acl-long)

Challenge:	Existing benchmarks primarily focus on Python and are limited in terms of language diversity.
Approach:	They propose a multilingual debugging benchmark that includes 3.9K test samples of 20 programming languages and introduces the debug instruction corpora MdEval-Instruct by injecting bugs into the correct multilingual queries and solutions.
Outcome:	The proposed benchmark includes 3.9K test samples of 20 programming languages and covers the automated program repair task, bug localization task, and bug identification task.

Copied to clipboard

Lina Yang, Yusheng Liao, Yanfeng Wang, Yu Wang

Diffusion Glancing Transformer for Parallel Sequence-to-Sequence Learning (2024.naacl-long)

Challenge:	Large language models (LLMs) have achieved remarkable success across diverse tasks through large-scale pretraining.
Approach:	They propose a framework that filters noisy components from LoRA updates via subspace similarity with the base model.
Outcome:	The proposed framework improves accuracy by 12%, reduces forgetting by 29%, and filters out over 30% of LoRA parameters identified as noisy.

Copied to clipboard

Lihua Qian, Mingxuan Wang, Yang Liu, Hao Zhou

Diagnosing and Remedying Representation Deficiencies for Deterministic Reasoning in KGQA (2026.acl-long)

Challenge:	Experimental results show that non-autoregressive generation models are superior in generation efficiency but inferior in generation quality.
Approach:	They propose a diffusion glancing transformer which employs a modality diffusion process and residual glancy sampling to improve multi-modality modeling.
Outcome:	The proposed model outperforms autoregressive and non-autoregressive models on machine translation and text generation benchmarks.

Copied to clipboard

Gewen Liang, Mufan Xu, Kehai Chen, Wei Wang, Yuwei Wang, Muyun Yang, Tiejun Zhao, Min Zhang

ToTTo: A Controlled Table-To-Text Generation Dataset (2020.emnlp-main)

Challenge:	Existing approaches to solve non-deterministic reasoning problems in large language models are limited by their complexity and lack of a clear understanding of the problem.
Approach:	They propose a method to diagnose and correct non-deterministic reasoning behaviors in large language models.
Outcome:	The proposed method outperforms baselines and WebQSP benchmarks on the widely used WebQ SP and CWQ benchmarks.

Copied to clipboard

Ankur Parikh, Xuezhi Wang, Sebastian Gehrmann, Manaal Faruqui, Bhuwan Dhingra, Diyi Yang, Dipanjan Das

Concise and Precise Context Compression for Tool-Using Language Models (2024.findings-acl)

Challenge:	Existing methods for data-to-text generation often hallucinate phrases not supported by the Wikipedia table.
Approach:	They propose a controlled task where annotators directly revise existing Wikipedia sentences to generate a one-sentence description.
Outcome:	The proposed task produces a one-sentence description from a Wikipedia table and highlighted cells.

Copied to clipboard

Yang Xu, Yunlong Feng, Honglin Mu, Yutai Hou, Yitong Li, Xinghao Wang, Wanjun Zhong, Zhongyang Li, Dandan Tu, Qingfu Zhu, Min Zhang, Wanxiang Che

How Much Does Nonverbal Communication Conform to Entropy Rate Constancy?: A Case Study on Listener Gaze in Interaction (2024.findings-acl)

Challenge:	Existing methods suffer from key information loss and difficulty in adjusting the length of compressed sequences based on documentation lengths.
Approach:	They propose two strategies for compressing tool documentation into concise and precise summary sequences for tool-using language models.
Outcome:	The proposed approach achieves comparable performance to the upper-bound baseline under 16x compression ratio.

Copied to clipboard

Yu Wang, Yang Xu, Gabriel Skantze, Hendrik Buschmeier

Challenge:	Whether the Entropy Rate Constancy principle applies to nonverbal communication signals is still under investigation.
Approach:	They perform empirical analyses of video-recorded dialogue data and investigate whether listener gaze adheres to the Entropy Rate Constancy principle.
Outcome:	The results show that the ERC principle holds for listener gaze, and that linguistic factors syntactic complexity and turn transition potential are weakly correlated with local entropy of listener gaze.

Real-time Ad Retrieval via LLM-generative Commercial Intention for Sponsored Search Advertising (2025.emnlp-main)

Copied to clipboard

Tongtong Liu, Zhaohui Wang, Meiyue Qin, Zenghui Lu, Xudong Chen, Yuekui Yang, Peng Shu

Towards Robust Evidence-Aware Fake News Detection via Improving Semantic Perception (2024.lrec-main)

Challenge:	Existing methods for retrieving documents and ads use one-to-few mappings and time-consuming content extraction.
Approach:	They propose a framework that leverages LLM-generated commercial intents as an intermediate semantic representation to directly retrieve ads for queries in real-time.
Outcome:	The proposed framework has been implemented in a real-world online system, handling daily search volumes in billions.

Copied to clipboard

Yike Wu, Yang Xiao, Mengting Hu, Mengying Liu, Pengcheng Wang, Mingming Liu

NetSafe: Exploring the Topological Safety of Multi-agent System (2025.findings-acl)

Challenge:	Existing methods lack sufficient semantic perception and are easily blinded by textual expressions.
Approach:	They propose a model-agnostic training framework to improve the semantic perception of evidence-aware fake news detection by combining two kinds of data augmentations with synthetic data.
Outcome:	The proposed framework outperforms state-of-the-art methods on the extended test set while achieving competitive performance on the original one.

Copied to clipboard

Miao Yu, Shilong Wang, Guibin Zhang, Junyuan Mao, Chenlong Yin, Qijiong Liu, Kun Wang, Qingsong Wen, Yang Wang

Challenge:	Large language models (LLMs) have fueled significant progress in intelligent Multi-agent Systems (MAS), with expanding academic and industrial applications.
Approach:	They propose a framework that unifies diverse MAS workflows via iterative RelCom interactions to enable generalized analysis.
Outcome:	The proposed framework unifies diverse MAS workflows via iterative RelCom interactions to enable generalized analysis.

ACROSS: An Alignment-based Framework for Low-Resource Many-to-One Cross-Lingual Summarization (2023.findings-acl)

Copied to clipboard

Peiyao Li, Zhengkun Zhang, Jun Wang, Liang Li, Adam Jatowt, Zhenglu Yang

On the (In-)Security of the Shuffling Defense in the Transformer Secure Inference (2026.acl-long)

Challenge:	Existing studies ignore data imbalance in multilingual settings and do not utilize monolingual data.
Approach:	They propose a cross-lingual summarization model that aligns cross-linguistic data with high-resource monolingual data via contrastive and consistency loss.
Outcome:	The proposed model outperforms baseline models and consistently dominates on 45 language pairs.

Copied to clipboard

Zhengyi Li, Yakai Wang, Jingwen Leng, Kang Yang, Yu Yu, Jiaping Gui, Yu Feng, Ning Liu, Minyi Guo

WebUncertainty: Dual-Level Uncertainty Driven Planning and Reasoning For Autonomous Web Agent (2026.findings-acl)

Challenge:	Existing work reveals only randomly permuted activations to the client, allowing adversaries to extract model weights.
Approach:	They propose an attack that aligns differently shuffled activations to a common permutation and exploits them to extract model weights.
Outcome:	The proposed attack can align shuffled activations to a common permutation and exploit them to extract model weights with a query cost of approximately $1.

Copied to clipboard

Lingfeng Zhang, Yongan Sun, Jinpeng Hu, Hui Ma, Ying Yang, Kuien Liu, Zenglin Shi, Meng Wang

GigaSpeech 2: An Evolving, Large-Scale and Multi-domain ASR Corpus for Low-Resource Languages with Automated Crawling, Transcription and Refinement (2025.acl-long)

Challenge:	Existing web agents struggle with complex tasks due to rigid planning strategies and hallucination-prone reasoning.
Approach:	They propose a task-uncertainty-driven Adaptive Planning Mechanism that adaptively selects planning modes to navigate unknown environments.
Outcome:	The proposed framework performs better on the WebArena and WebVoyager benchmarks than existing frameworks.

Copied to clipboard

Yifan Yang, Zheshu Song, Jianheng Zhuo, Mingyu Cui, Jinpeng Li, Bo Yang, Yexing Du, Ziyang Ma, Xunying Liu, Ziyuan Wang, Ke Li, Shuai Fan, Kai Yu, Wei-Qiang Zhang, Guoguo Chen, Xie Chen

DR-HM: Distill-then-Reinforce Training with Cognition-Aware Data Synthesis for Harmful Meme Detection (2026.findings-acl)

Challenge:	GigaSpeech 2 is a large-scale, multi-domain, multilingual speech recognition corpus for low-resource languages.
Approach:	They propose a large-scale, multi-domain, multilingual speech recognition corpus for low-resource languages and an automated pipeline for data crawling, transcription, and label refinement.
Outcome:	The proposed corpus reduces the word error rate for Thai, Indonesian, and Vietnamese on a realistic YouTube test set by 25% to 40% compared to Whisper large-v3.

Copied to clipboard

Zihan Cheng, Jianxiang Ma, Xiaocui Yang, Peidong Wang, Wen Zhang, Shi Feng, Daling Wang, Yifei Zhang, Mingfu Zhang

From Long Videos to Engaging Clips: A Human-Inspired Video Editing Framework with Multimodal Narrative Understanding (2025.emnlp-industry)

Challenge:	Current methods for harmful meme detection lack the knowledge required to identify such hate . current methods lack the ability to identify cultural stereotypes and visual metaphors .
Approach:	They propose a framework that decomposes meme analysis into a human-inspired reasoning process . they propose DR-HM to transfer knowledge from closed-source models while mitigating biases .
Outcome:	The proposed framework outperforms existing methods on three benchmark datasets.

Copied to clipboard

Xiangfeng Wang, Xiao Li, Yadong Wei, null Songxueyu, Yang Song, null Xiaxiaoqiang, Fangrui Zeng, Zaiyi Chen, null Liuliu, Gu Xu, Tong Xu

A Versatile Adaptive Curriculum Learning Framework for Task-oriented Dialogue Policy Learning (2022.findings-naacl)

Challenge:	Existing methods for video editing rely on textual cues from ASR transcripts and segment selection, often neglecting rich visual context.
Approach:	They propose a human-inspired automatic video editing framework that leverages multimodal narrative understanding to address these limitations.
Outcome:	The proposed framework outperforms existing baselines across general and advertisement-oriented editing tasks.

Copied to clipboard

Yang Zhao, Hua Qin, Wang Zhenyu, Changxi Zhu, Shihan Wang

Efficient and Effective Prompt Tuning via Prompt Decomposition and Compressed Outer Product (2025.naacl-long)

Challenge:	Existing training paradigms for dialogue policy learning with brute-force random sampling are expensive and lack reliable evaluation of difficulty scores.
Approach:	They propose a flexible adaptive curriculum learning framework that integrates curriculum learning with a generic global curriculum.
Outcome:	The proposed framework improves learning performance and efficiency on three public dialogue datasets.

Copied to clipboard

Pengxiang Lan, Haoyu Xu, Enneng Yang, Yuliang Liang, Guibing Guo, Jianzhe Zhao, Xingwei Wang

LLMRouterBench: A Massive Benchmark and Unified Framework for LLM Routing (2026.findings-acl)

Challenge:	Existing methods for fine-tuning pre-trained language models overlook intrinsic semantic associations between soft prompt tokens, leading to high discreteness and limited interactions.
Approach:	They propose a low-parameters Prompt Tuning method which leverages prompt decomposition and compressed outer product to facilitate multiple interactions among prompt tokens.
Outcome:	Experiments on six architectures and eight datasets show that the proposed method outperforms state-of-the-art methods in performance and efficiency.

Copied to clipboard

Hao Li, Yiqun Zhang, Zhaoyan Guo, Chenxu Wang, Shengji Tang, Qiaosheng Zhang, Yang Chen, Biqing Qi, Peng Ye, Lei Bai, Zhen Wang, Shuyue Hu

Challenge:	Large language model (LLM) routing assigns each query to the best suitable model from an ensemble.
Approach:	They introduce a large-scale benchmark and unified framework for LLM routing . they find that many routing methods exhibit similar performance under unified evaluation .
Outcome:	The proposed benchmark provides comprehensive metrics for both performance-oriented and performance-cost trade-off routing.

Fair Federated Learning with Biased Vision-Language Models (2024.findings-acl)

Copied to clipboard

Huimin Zeng, Zhenrui Yue, Yang Zhang, Lanyu Shang, Dong Wang

PiKGL: Leveraging Pruned Knowledge Graphs for Explainable Stance Detection (2026.tacl-1)

Challenge:	Existing literature ignores the inherent group unfairness within CLIP and its ethical implications on FL applications.
Approach:	They propose a fairness-aware adaptation framework for CLIP in federated learning . they propose to leverage biased pre-trained VLMs to build fair FL frameworks .
Outcome:	The proposed framework addresses unique bias in FL, triggered by data heterogeneity . it trains a fair FL model with fairness-aware deep visual prompting (DVP) Extensive results on human face attribute recognition (FAR) applications show it outperforms state-of-the-art FL models .

Copied to clipboard

Bingbing Wang, Jingjie Lin, Zhixin Bai, Xintong Song, Qianlong Wang, Min Yang, Xi Zeng, Jing Li, Ruifeng Xu

LayoutLMv2: Multi-modal Pre-training for Visually-rich Document Understanding (2021.acl-long)

Challenge:	Experimental results demonstrate that a Pruned interpretable knowledge Graph Learning framework for explainable stance detection is state-of-the-art for social media stance prediction.
Approach:	They propose a Pruned interpretable knowledge Graph Learning framework for explainable stance detection that incorporates commonsense knowledge and prunes redundant information to ensure precision and minimize noise.
Outcome:	The proposed framework achieves state-of-the-art on three public datasets.

Copied to clipboard

Yang Xu, Yiheng Xu, Tengchao Lv, Lei Cui, Furu Wei, Guoxin Wang, Yijuan Lu, Dinei Florencio, Cha Zhang, Wanxiang Che, Min Zhang, Lidong Zhou

Interpretable Research Replication Prediction via Variational Contextual Consistency Sentence Masking (2022.findings-acl)

Challenge:	Existing pre-training tasks for text and layout are effective in visually-rich document understanding tasks.
Approach:	They propose to combine pre-training tasks with a multi-modal model to model interaction between text, layout and image in a single multi-module framework.
Outcome:	The proposed model outperforms LayoutLM by a large margin on visual-rich document understanding tasks.

Copied to clipboard

Tianyi Luo, Rui Meng, Xin Wang, Yang Liu

CARE-CR: Context-Aware Routing and Expert Fusion for Multi-Preference Cognitive Restructuring (2026.findings-acl)

Challenge:	Existing methods for predicting research replication are insufficient especially for long research papers.
Approach:	They propose to build an interpretable neural model which can provide sentence-level explanations and apply weakly supervised approach to leverage large corpus of unlabeled datasets.
Outcome:	The proposed model can provide sentence-level explanations and leverage large unlabeled datasets to boost interpretability and improve prediction performance.

Copied to clipboard

Hongzhi Qi, Liangcheng Wang, Yijing YU, Jianqiang Li, Bing Xiang Yang, Qing Zhao

Cognitive Modeling

Challenge:	Large Language Models (LLMs) offer promising avenues for automated cognitive restructuring in mental health settings, but current approaches lack the adaptability to balance conflicting therapeutic dimensions, such as empathy and rationality.
Approach:	They propose a decoupled optimization framework that implements a dimension-guided Monte Carlo tree search to train expert policies specialized for distinct therapeutic attributes rather than relying on a monolithic alignment strategy.
Outcome:	The proposed framework achieves consistent improvements over baselines across multiple evaluation dimensions, including diagnostic accuracy, contextual appropriateness, task effectiveness, and overall helpfulness, while enabling controllable cognitive restructuring generation.

Exploiting Contextual Knowledge in LLMs through 𝒱-usable Information based Layer Enhancement (2025.acl-long)

Copied to clipboard

Xiaowei Yuan, Zhao Yang, Ziyang Huang, Yequan Wang, Siqi Fan, Yiming Ju, Jun Zhao, Kang Liu

Challenge:	Existing approaches to enhance the context-faithfulness of Large Language Models (LLMs) ignore the fundamental mechanism of how contextual information is processed within LLMs’ internal states.
Approach:	They propose a method that enhances the utilization of contextual knowledge within LLMs’ internal representations by employing V-usable information analysis.
Outcome:	The proposed method improves context-faithfulness generation in Question-Answering tasks, particularly in scenarios involving unknown or conflicting contextual knowledge.

Two Birds One Stone: Dynamic Ensemble for OOD Intent Classification (2023.acl-long)

Copied to clipboard

Yunhua Zhou, Jianqiang Yang, Pengyu Wang, Xipeng Qiu

ECom-Bench: Can LLM Agent Resolve Real-World E-commerce Customer Support Issues? (2025.emnlp-industry)

Challenge:	Out-of-domain (OOD) intent classification is an active field of natural language understanding . previous studies have suggested that PTMs would be "overthinking" the semantic features of the sample in the open-world scenario .
Approach:	They propose a method that allows the model to decide whether to make a decision on OOD classification early during inference.
Outcome:	The proposed method can improve inference speed and achieve significant performance improvements.

Copied to clipboard

Haoxin Wang, Xianhan Peng, Huang Cheng, Yizhe Huang, Ming Gong, Chenghan Yang, Yang Liu, Jiang Lin

Challenge:	ECom-Bench is a benchmark framework for evaluating LLM agent with multimodal capabilities in e-commerce customer support domain.
Approach:	They introduce a benchmark framework for evaluating LLM agent with multimodal capabilities in the e-commerce customer support domain.
Outcome:	The proposed benchmark features dynamic user simulation based on persona information from real e-commerce customer interactions and a realistic task dataset derived from authentic ecommerce dialogues.

Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewards (2024.acl-long)

Copied to clipboard

Haoxiang Wang, Yong Lin, Wei Xiong, Rui Yang, Shizhe Diao, Shuang Qiu, Han Zhao, Tong Zhang

Challenge:	Reinforcement Learning from Human Feedback (RLHF) relies on scalar rewards to capture user preferences.
Approach:	They propose a framework that integrates multi-objective reward modeling to represent diverse preference profiles.
Outcome:	The proposed method improves performance across reward objectives and targets.

LeanK: Learnable K Cache Channel Pruning for Efficient Decoding (2025.emnlp-main)

Copied to clipboard

Yike Zhang, Zhiyuan He, Huiqiang Jiang, Chengruidong Zhang, Yuqing Yang, Jianyong Wang, Lili Qiu

SparkRA: A Retrieval-Augmented Knowledge Service System Based on Spark Large Language Model (2024.emnlp-demo)

Challenge:	Existing efforts to optimize the key-value (KV) cache include: (1) Eviction, which discards cache of less important tokens; (2) Selection, which retains the full KV cache but selectively reads relevant entries.
Approach:	They propose a learning-based method that prunes unimportant key (K) cache channels by leveraging static channel sparsity.
Outcome:	Experiments show that LeanK reduces GPU memory and accelerates decoding without sacrificing accuracy.

Copied to clipboard

Dayong Wu, Jiaqi Li, Baoxin Wang, Honghong Zhao, Siyuan Xue, Yanjie Yang, Zhijun Chang, Rui Zhang, Li Qian, Bo Wang, Shijin Wang, Zhixiong Zhang, Guoping Hu

MorphoBench: A Benchmark with Difficulty Adaptive to Model Reasoning (2026.findings-acl)

Challenge:	Large language models (LLMs) have shown remarkable achievements across various language tasks.
Approach:	They propose a scientific literature LLM and a knowledge service system based on it . they collect scientific literature and then pre-train it using autoregressive training .
Outcome:	The proposed system provides literature investigation, paper reading, and academic writing functions.

Copied to clipboard

Xukai Wang, Xuanbo Liu, Mingrui Chen, Haitian Zhong, Xuanlin Yang, Bohan Zeng, Jinbo Hu, Hao Liang, Junbo Niu, Xuchen Li, Ruitao Wu, Ruichuan An, Yang Shi, Liu Liu, Qiang Liu, Zhouchen Lin, Xu-Yao Zhang, Wentao Zhang, Bin Dong

Triviality Corrected Endogenous Reward (2026.acl-long)

Challenge:	Existing benchmarks designed to evaluate the reasoning capabilities of large models are limited in scope and lack flexibility to adapt difficulty according to evolving reasoning capacities of models.
Approach:	They propose a benchmark that incorporates multidisciplinary questions to evaluate the reasoning capabilities of large models and can adjust and update question difficulty based on the reasoning abilities of advanced models.
Outcome:	The proposed benchmark incorporates multidisciplinary questions to evaluate the reasoning capabilities of large models and can adjust and update question difficulty based on the reasoning abilities of advanced models.

Copied to clipboard

Xinda Wang, Zhengxu Hou, Yangshijie Zhang, null Yanbingren, Jialin Liu, ChenZhuo Zhao, Zhibo Yang, Bin-Bin Yang, Feng Xiao

YuLan-Mini: Pushing the Limits of Open Data-efficient Language Model (2025.acl-long)

Challenge:	Recent work on unsupervised reinforcement learning for mathematical reasoning using confidence-based endogenous rewards focuses on open-ended text generation, requiring either annotated data or powerful closed-source models.
Approach:	They propose a method that rewards the relative information gain between a specialist and a generalist reference policy, modulated by a probability-dependent correction mechanism.
Outcome:	The proposed model improves on multiple writing benchmarks and model architectures without external supervision and validates generality across different generation tasks.

Copied to clipboard

Hu Yiwen, Huatong Song, Jie Chen, Jia Deng, Jiapeng Wang, Kun Zhou, Yutao Zhu, Jinhao Jiang, Zican Dong, Yang Lu, Xu Miao, Xin Zhao, Ji-Rong Wen

Measure and Improve Robustness in NLP Models: A Survey (2022.naacl-main)

Challenge:	prevailing pre-training approaches for large language models involve several complexities.
Approach:	They propose a low-cost training recipe and a robust optimization approach to mitigate training instability . they also propose synthesis, curriculum, and data selection pipelines to integrate data .
Outcome:	The proposed model achieves top-tier performance among models with similar parameter scale . it is comparable to industry-leading models that require significantly more data .

Copied to clipboard

Xuezhi Wang, Haohan Wang, Diyi Yang

Automatic Slide Updating with User-Defined Dynamic Templates and Natural Language Instructions (2026.findings-acl)

Challenge:	Despite the performance gains, NLP models are still fragile and brittle to out-of-domain data, adversarial attacks, or small perturbation to the input.
Approach:	They propose a survey of how to define, measure and improve robustness in NLP by connecting multiple definitions of robustness and identifying failures.
Outcome:	The proposed models are robust against unseen or challenging scenarios, but are still fragile and brittle to out-of-domain data and adversarial attacks.

Copied to clipboard

Kun Zhou, Jiakai He, Wenmian Yang, Zhensheng Wang, Yiquan Zhang, Weijia Jia

Challenge:	Existing automation methods follow fixed template filling and cannot support dynamic updates for diverse, user-authored decks.
Approach:	They propose a framework that combines multimodal slide parsing, natural language instruction grounding, and tool-augmented reasoning for tables, charts, and textual conclusions.
Outcome:	The proposed framework updates content while preserving layout and style while maintaining a strong reference baseline on DynaSlide.

ICL-Bandit: Relevance Labeling in Advertisement Recommendation Systems via LLM (2025.findings-emnlp)

Copied to clipboard

Lu Wang, Chiming Duan, Pu Zhao, Fangkai Yang, Yong Shi, Xuefeng Luo, Bingjing Xu, Weiwei Deng, Qingwei Lin, Dongmei Zhang

RAV: Retrieval-Augmented Voting for Tactile Descriptions Without Training (2025.emnlp-main)

Challenge:	In-context learning (ICL) is a common practice to enhance LLM performance on domain-specific tasks.
Approach:	They propose a method that leverages large language models to enhance query-ad relevance labeling . they identify and provide superior demonstrations for ICL, thereby improving labeling performance .
Outcome:	The proposed method improves query-ad relevance labeling performance by providing demonstrations.

Copied to clipboard

Jinlin Wang, Yulong Ji, Hongyu Yang

Can Large Language Models Understand You Better? An MBTI Personality Detection Dataset Aligned with Population Traits (2025.coling-main)

Challenge:	Conventional approaches relying on extensive parameter learning for multimodal perception are rigid and computationally inefficient.
Approach:	They propose a parameter-free method that constructs visual-tactile cross-modal knowledge directly by retrieving similar visual-touch data for given visual and tactile inputs and generating tactile descriptions through a voting mechanism.
Outcome:	The proposed method achieves comparable performance to large-scale cross-modal models without training across a wide range of datasets.

Copied to clipboard

Bohan Li, Jiannan Guan, Longxu Dou, Yunlong Feng, Dingzirui Wang, Yang Xu, Enbo Wang, Qiguang Chen, Bichen Wang, Xiao Xu, Yimeng Zhang, Libo Qin, Yanyan Zhao, Qingfu Zhu, Wanxiang Che

RAMQA: A Unified Framework for Retrieval-Augmented Multi-Modal Question Answering (2025.findings-naacl)

Challenge:	Existing data on MBTI personality detection are based on self-reported labels and fail to capture the full range of population personality traits.
Approach:	They construct a manually annotated MBTI personality detection dataset with soft labels under the guidance of psychologists and use them to identify the task.
Outcome:	The MBTIBench is the first manually annotated MBti personality detection dataset with soft labels under the guidance of psychologists.

Copied to clipboard

Yang Bai, Christan Grant, Daisy Zhe Wang

DAGCN: Distance-based and Aspect-oriented Graph Convolutional Network for Aspect-based Sentiment Analysis (2024.findings-naacl)

Challenge:	Existing ranking methods rely on small encoder-based ranking models, which are incompatible with modern decoder--based generative large language models (LLMs) Existing methods based on small LLaVA rankers are incompatible with advanced LLMs.
Approach:	They propose a framework that combines learning-to-rank methods with generative permutation-enhanced ranking techniques.
Outcome:	The proposed framework improves on two benchmarks, WebQA and MultiModalQA, showing significant improvements over baselines.

Copied to clipboard

Zhihao Wang, Bo Zhang, Ru Yang, Chang Guo, Maozhen Li

A Reinforcement Learning Framework for Natural Question Generation using Bi-discriminators (C18-1)

Challenge:	Recent advances in sentiment analysis tend to interference from local factors such as irrelevant words and edges, hindering the precise identification of opinion words.
Approach:	They propose a distance-based syntactic weight and Aspect-Fusion Attention to solve this problem.
Outcome:	The proposed model outperforms state-of-the-art models on three public datasets and verify its effectiveness.

Copied to clipboard

Zhihao Fan, Zhongyu Wei, Siyuan Wang, Yang Liu, Xuanjing Huang

Overcome Noise and Bias: Segmentation-Aided Multi-Granularity Denoising and Debiasing for Enhanced Quarduples Extraction in Dialogue (2024.emnlp-main)

Challenge:	Existing research on visual question generation is focused on training models to fit the annotated data set that makes them indifferent from other language generation tasks.
Approach:	They propose to use two discriminators to enhance the training of a visual question generator to ask natural questions about an image.
Outcome:	The proposed model outperforms state-of-the-art models in terms of automatic and human evaluation metrics.

Copied to clipboard

Xianlong Luo, Meng Yang, Yihao Wang

Local Additivity Based Data Augmentation for Semi-supervised NER (2020.emnlp-main)

Challenge:	Existing methods for generating sentiment quadruples in dialogues face heightened noise and order bias challenges, leading to decreased robustness and accuracy.
Approach:	They propose a Segmentation-Aided multi-grained denoising and debiasing method to address noise and order bias challenges in ABSA.
Outcome:	The proposed method achieves word-level denoising and utterance-level demoising via topic-aware dialogue segmentation.

Copied to clipboard

Jiaao Chen, Zhenghui Wang, Ran Tian, Zichao Yang, Diyi Yang

Enhancing LLM-Based Persuasion Simulations with Cultural and Speaker-Specific Information (2025.findings-emnlp)

Challenge:	Named Entity Recognition (NER) is one of the first stages in deep language understanding yet current NER models heavily rely on human-annotated data.
Approach:	They propose a Local Additivity based Data Augmentation method for semi-supervised Named Entity Recognition (NER) that creates virtual samples by interpolating sequences close to each other.
Outcome:	The proposed method improves both entity and context learning by adding to training data and extending it to semi-supervised setting.

Copied to clipboard

Weicheng Ma, Hefan Zhang, Shiyu Ji, Farnoosh Hashemi, Qichao Wang, Ivory Yang, Joice Chen, Juanwen Pan, Michael Macy, Saeed Hassanpour, Soroush Vosoughi

R3 Prompting: Review, Rephrase and Resolve for Chain-of-Thought Reasoning in Large Language Models under Noisy Context (2023.findings-emnlp)

Challenge:	Existing approaches to persuasive dialogue generation suffer from stance oscillation and low informativeness.
Approach:	They propose reinforced instructional prompting, a method that ensures speaker characteristics consistently guide all stages of dialogue generation.
Outcome:	The proposed method ensures speaker characteristics guide all stages of dialogue generation and aligns language use with speakers’ native languages to better capture cultural nuances.

Copied to clipboard

Qingyuan Tian, Hanlun Zhu, Lei Wang, Yang Li, Yunshi Lan

Generating Questions, Answers, and Distractors for Videos: Exploring Semantic Uncertainty of Object Motions (2025.findings-acl)

Challenge:	Existing studies have evaluated LLMs under noise-free context but the dilemma for LLM to produce inaccurate results under noisy context has not been fully investigated.
Approach:	They propose a new method for CoT reasoning using Chain-of-Thought prompting that interacts with LLMs to perform key sentence extraction, variable declaration and answer prediction.
Outcome:	The proposed method outperforms existing CoT prompting methods on five reasoning tasks under noisy context.

Copied to clipboard

Wenjian Ding, Yao Zhang, Jun Wang, Adam Jatowt, Zhenglu Yang

Optimizing Packing and Shuffling Strategies for Enhanced Performance in Generative Language Models (2026.acl-srw)

Challenge:	Existing video QADs are generated using video captions, incurring significant costs and resulting in bias.
Approach:	They propose to use temporal motion to describe video objects to generate diverse QADs focusing on different objects and interactions.
Outcome:	The proposed approach improves consistency and diversity of generated QADs on the NExT-QA and Perception Test benchmarks.

Copied to clipboard

Yanbing Chen, Ruilin Wang, Zihao Yang, Lavender Yao Jiang, Eric Karl Oermann

Capturing Minds, Not Just Words: Enhancing Role-Playing Language Models with Personality-Indicative Data (2024.findings-emnlp)

Challenge:	Documents are typically concatenated to chunks of maximum sequence length (MSL) and shuffled in chunks (atom-size chunks).
Approach:	They propose to pack and shuff documents in chunks of tokens to prevent overfitting . they also propose to use padding to only include one document per chunk .
Outcome:	The proposed method reduces the risk of overfitting and improves generalizability.

Copied to clipboard

Yiting Ran, Xintao Wang, Rui Xu, Xinfeng Yuan, Jiaqing Liang, Yanghua Xiao, Deqing Yang

Task-agnostic Distillation of Encoder-Decoder Language Models (2024.lrec-main)

Challenge:	Existing role-playing models focus on character knowledge and tones, but lack personality-indicative data to capture characters' minds.
Approach:	They propose to enhance role-playing agents (RPAs) via personality-indicative data by asking psychological scales to capture broad aspects of personality traits in individuals.
Outcome:	The proposed model exhibits advanced role-playing capabilities for both general and personality-related evaluations.

Copied to clipboard

Chen Zhang, Yang Yang, Qiuchi Li, Jingang Wang, Dawei Song

Constructing Your Model’s Value Distinction: Towards LLM Alignment with Anchor Words Tuning (2025.findings-emnlp)

Challenge:	Existing distillation methods that focus on encoder-only LMs fail to handle the distillation of encoder decoder LM.
Approach:	They propose a method that finetunes pretrained language models (LMs) they propose 'MiniEnD' that allows for task-agnostic distillation of LMs.
Outcome:	The proposed distillation method is generally effective and competitive compared to other alternatives.

Copied to clipboard

Zhen Yang, Ping Jian, Chengzhi Li, Chenxu Wang, Xinyue Zhang, Wenpeng Lu

Challenge:	a study of large language models (LLMs) shows that they can generate outputs that are honest, positive, harmless, etc.
Approach:	They propose a method that amplifies logits difference between positive and negative tokens . they propose to use the logits gap to generate positive and positive tokens after alignment .
Outcome:	The proposed method achieves effective alignment, but requires fewer computational resources compared to training-time alignment methods.

SGM: Sequence Generation Model for Multi-label Classification (C18-1)

Copied to clipboard

Pengcheng Yang, Xu Sun, Wei Li, Shuming Ma, Wei Wu, Houfeng Wang

From Evasion to Concealment: Stealthy Knowledge Unlearning for LLMs (2025.findings-acl)

Challenge:	Existing methods ignore the correlations between labels and different parts of the text can contribute differently for predicting different labels.
Approach:	They propose to view the multi-label classification task as a sequence generation problem and apply a decoder-based sequence generation model to solve it.
Outcome:	The proposed methods outperform previous work by a substantial margin.

Copied to clipboard

Tianle Gu, Kexin Huang, Ruilin Luo, Yuanqi Yao, Xiuying Chen, Yujiu Yang, Yan Teng, Yingchun Wang

Forewarned is Forearmed: Pre-Synthesizing Jailbreak-like Instructions to Enhance LLM Safety Guardrail to Potential Attacks (2025.findings-emnlp)

Challenge:	Existing approaches to unlearning often treat nonsensical responses or template-based refusals as the unlearning target, making the process even more vulnerable to attacks and jailbreaks.
Approach:	They propose a method that uses inverted facts to remove the need for auxiliary models or retaining data while avoiding leakage.
Outcome:	Evaluated on the ToFU Knowledge Unlearning dataset using Llama2-7B-Chat and Phi-1.5, MEOW outperforms baselines in forgetting quality while preserving model utility.

Copied to clipboard

Sheng Liu, Qiang Sheng, Danding Wang, Yang Li, Guang Yang, Juan Cao

BabelDOC: Better Layout-Preserving PDF Translation via Intermediate Representation (2026.acl-demo)

Challenge:	Despite advances in improving large language model (LLM) to refuse to answer malicious instructions, LLMs remain vulnerable to jailbreak attacks where attackers generate instructions with distributions differing from safety alignment corpora.
Approach:	They propose a framework that leverages embedding space distribution analysis to generate jailbreak-like instructions.
Outcome:	The proposed framework shows significant decreases in attack success rate on Qwen2.5, Llama3.1, and Llma3.2 without compromising their utility.

Copied to clipboard

Yang Qi, Xiangyao Ma, Xiao Wang, Hao Wang, Rui Wang

MixPAVE: Mix-Prompt Tuning for Few-shot Product Attribute Value Extraction (2023.findings-acl)

Challenge:	Existing document translation pipelines face a tension between linguistic processing and layout preservation.
Approach:	They propose a framework for layout-preserving PDF translation that decouples visual layout metadata from semantic content.
Outcome:	The proposed framework improves layout fidelity, visual aesthetics, and terminology consistency over representative baselines while maintaining competitive translation precision.

Copied to clipboard

Li Yang, Qifan Wang, Jingang Wang, Xiaojun Quan, Fuli Feng, Yu Chen, Madian Khabsa, Sinong Wang, Zenglin Xu, Dongfang Liu

Learning to Detect Noisy Labels Using Model-Based Features (2022.findings-emnlp)

Challenge:	Existing methods for product attribute value extraction focus on extracting values for a set of known attributes with sufficient training data.
Approach:	They propose a prompt tuning approach to extract attributes from product information using mixed prompts.
Outcome:	The proposed approach improves on two product benchmarks and shows parameter-efficient training and avoids model overfitting.

Copied to clipboard

Zhihao Wang, Zongyu Lin, Junjie Wen, Xianxin Chen, Peiqi Liu, Guidong Zheng, Yujun Chen, Zhilin Yang

NoteChat: A Dataset of Synthetic Patient-Physician Conversations Conditioned on Clinical Notes (2024.findings-acl)

Challenge:	Existing approaches to reduce label noise rely on heuristics and sample losses.
Approach:	They propose a method that transfers the noise distribution to a clean set and trains a model to distinguish noisy labels from clean ones using model-based features.
Outcome:	Empirically, the proposed approach improves over strong baselines on a wide range of tasks including text classification and speech recognition.

Copied to clipboard

Junda Wang, Zonghai Yao, Zhichao Yang, Huixue Zhou, Rumeng Li, Xun Wang, Yucheng Xu, Hong Yu

Logic-guided Semantic Representation Learning for Zero-Shot Relation Classification (2020.coling-main)

Challenge:	NoteChat is a cooperative multi-agent framework for generating patient-physician dialogues . evaluator finds it outperforms state-of-the-art models for generating clinical notes . clinical documentation is largely done by physicians at both steps .
Approach:	They propose a cooperative multi-agent framework leveraging Large Language Models to generate patient-physician dialogues.
Outcome:	The proposed framework outperforms state-of-the-art models for generating clinical notes . it can engage patients directly and help clinical documentation, a leading cause of physician burnout .

Copied to clipboard

Juan Li, Ruoxu Wang, Ningyu Zhang, Wen Zhang, Fan Yang, Huajun Chen

Integrating Vectorized Lexical Constraints for Neural Machine Translation (2022.acl-long)

Challenge:	Existing methods to zero-shot relation classification can only identify seen relations . existing methods rely on descriptive information to improve understandability of relation types .
Approach:	They propose a logic-guided semantic representation learning model for zero-shot relation classification that builds connections between seen and unseen relations via implicit and explicit semantic representations with knowledge graph embeddings and logic rules.
Outcome:	The proposed model can generalize to unseen relation types and achieve promising improvements.

Copied to clipboard

Shuo Wang, Zhixing Tan, Yang Liu

REG: Retrieval via Emotion Similarity for Guiding Empathetic Dialogue Generation (2026.acl-long)

Challenge:	Existing studies focus on integrating discrete lexical constraints into neural machine translation models.
Approach:	They propose to integrate constraints into NMT models by integrating them into keys and values . they show that their method outperforms representative baselines on four language pairs .
Outcome:	The proposed method outperforms baselines on four language pairs, showing superiority .

Copied to clipboard

Xu Wang, Bo Wang, Yang Xiang, Yihong Tang, Dongming Zhao, null Yuzifei, Yuexian Hou

Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task (D18-1)

Challenge:	Empathy relies on the cognitive capacity to relate to similar past experiences. Existing methods prioritize semantic similarity over emotion characteristics, leading to unempathetic responses.
Approach:	They propose a framework that integrates four Emotion Attributes into the retrieval process to ensure explicit emotional alignment.
Outcome:	Empirical results show that REG significantly outperforms baselines, offering a robust solution for empathetic generation.

Copied to clipboard

Tao Yu, Rui Zhang, Kai Yang, Michihiro Yasunaga, Dongxu Wang, Zifan Li, James Ma, Irene Li, Qingning Yao, Shanelle Roman, Zilin Zhang, Dragomir Radev

Using Large Corpus N-gram Statistics to Improve Recurrent Neural Language Models (N19-1)

Challenge:	Existing datasets for semantic parsing are too small in terms of number of programs for training modern data-intensive models.
Approach:	They propose a large-scale complex and cross-domain semantic parsing task for a database . they use a dataset with 10,181 questions and 5,693 unique complex SQL queries .
Outcome:	The proposed task is different from previous tasks because it uses the same database and program . the best model achieves only 9.7% exact matching accuracy on a database split setting.

Copied to clipboard

Yiben Yang, Ji-Ping Wang, Doug Downey

PRCA: Fitting Black-Box Large Language Models for Retrieval Question Answering via Pluggable Reward-Driven Contextual Adapter (2023.emnlp-main)

Challenge:	a technique that uses large corpus n-gram statistics as a regularizer for training a neural network LM on a smaller corpus is effective, and more time-efficient than training on ngrams.
Approach:	They propose a technique that uses large corpus n-gram statistics as a regularizer for training on a smaller corpus.
Outcome:	The proposed technique is effective and more time-efficient than training on a larger corpus.

Copied to clipboard

Haoyan Yang, Zhitao Li, Yong Zhang, Jianzong Wang, Ning Cheng, Ming Li, Jing Xiao

TOXIFRENCH: Benchmarking and Enhancing Language Models via CoT Fine-Tuning for French Toxicity Detection (2026.findings-acl)

Challenge:	Large Language Models (LLMs) are too large to be fine-tuned with budget constraints and some are only accessible via APIs.
Approach:	They propose a pluggable Reward-Driven Contextual Adapter that integrates large language models as generators and trains them to refine the retrieved information.
Outcome:	The proposed method improves ReQA performance on three datasets by up to 20% compared to existing methods.

Copied to clipboard

Axel Delaval, Shujian Yang, Haicheng Wang, Han Qiu, Jialiang LU

Demystifying Data Organization for Enhanced LLM Training (2026.acl-long)

Challenge:	toxicity detection in French remains underdeveloped due to the lack of culturally relevant, human-annotated, large-scale datasets.
Approach:	They propose a method that generalizes French online comments using a semi-automated annotation pipeline that reduces manual labeling to only 10% through high-confidence LLM-based pre-annotation and human verification.
Outcome:	The proposed model outperforms GPT-4o and DeepSeek-R1 on the benchmark while maintaining cross-lingual capabilities.

Copied to clipboard

Yalun Dai, Yangyu Huang, Tongshen Yang, Yonghan Wang, Xin Zhang, Wenshan Wu, Qihao Zhao, Hao Li, Yuanyuan Gao, Kim-Hui Yap, Scarlett Li

Sparse Brains are Also Adaptive Brains: Cognitive-Load-Aware Dynamic Activation for LLMs (2026.findings-eacl)

Challenge:	Large Language Models (LLMs) have revolutionized various fields, yet their training efficiency is heavily reliant on effective data curation.
Approach:	They propose to reuse pre-computed sample-level scores originally generated for data efficiency and introduce two new data ordering methods to improve LLM training.
Outcome:	The proposed methods improve the stability and performance of LLM training.

Copied to clipboard

Yiheng Yang, Yujie Wang, Chi Ma, Lei Yu, Emmanuele Chersoni, Chu-Ren Huang

Double-Checker: Large Language Model as a Checker for Few-shot Named Entity Recognition (2024.findings-emnlp)

Challenge:	Existing sparsity methods lack adaptivity to contextual or model structural demands or incur prohibitive computational overhead.
Approach:	They propose a Cognitive-Load-Aware Dynamic Activation framework that synergizes statistical sparsity with semantic adaptability.
Outcome:	The proposed framework achieves 20% average speedup with less than 2% accuracy degradation outperforming Griffin and TT.

Copied to clipboard

Wei Chen, Lili Zhao, Zhi Zheng, Tong Xu, Yang Wang, Enhong Chen

MedDialog: Large-scale Medical Dialogue Datasets (2020.emnlp-main)

Challenge:	Recent studies have demonstrated remarkable performance on few-shot Named Entity Recognition tasks due to the high cost of obtaining high-quality labeled data.
Approach:	They propose to decompose the task into entity span detection and entity type classification using a type-independent entity span detector and then classify the detected spans based on their types.
Outcome:	The proposed method consistently yields improvements over two baseline approaches.

Copied to clipboard

Guangtao Zeng, Wenmian Yang, Zeqian Ju, Yue Yang, Sicheng Wang, Ruisi Zhang, Meng Zhou, Jiaqi Zeng, Xiangyu Dong, Ruoyu Zhang, Hongchao Fang, Penghui Zhu, Shu Chen, Pengtao Xie

Fraud-R1 : A Multi-Round Benchmark for Assessing the Robustness of LLM Against Augmented Fraud and Phishing Inducements (2025.findings-acl)

Challenge:	telemedicine is a medical practice that provides patient care remotely using video conferencing tools.
Approach:	They build large-scale medical dialogue datasets to facilitate research . they pretrain several models on the Chinese MedDialog dataset and compare their performance .
Outcome:	The proposed datasets show that models trained on MedDialog can generate doctor-like medical dialogues.

Copied to clipboard

Shu Yang, Shenzhe Zhu, Zeyu Wu, Keyu Wang, Junchi Yao, Junchao Wu, Lijie Hu, Mengdi Li, Derek F. Wong, Di Wang

CaM-HG: Causal-Enhanced MoE and Hypergraphs Network for Incomplete Multimodal Emotion Recognition in Conversations (2026.findings-acl)

Challenge:	Existing fraud detection benchmarks focus on single-turn classification tasks, failing to capture dynamic nature of real-world fraud attempts.
Approach:	They propose a bilingual benchmark to assess LLMs' ability to resist fraud and phishing attacks across five key fraud categories: Fraudulent Services, Impersonation, Phishing Scams, Fake Job Postings, and Online Relationships.
Outcome:	The proposed model improves in role-play settings and in e-commerce and recommendation systems.

Copied to clipboard

Mingjian Yang, Yong Wang, Peng Liu, Wen Yin

Sketch and Refine: Towards Faithful and Informative Table-to-Text Generation (2021.findings-acl)

Challenge:	Existing methods that focus on statistical reconstruction often fail to bridge these gaps, effectively leaving semantic holes.
Approach:	They propose a Causal-Enhanced Mixture-of-Experts and Hypergraph Network to bridge missing features . they use experts to synthesize missing features that are realistic and causally consistent .
Outcome:	The proposed model synthesizes missing features that are realistic and causally consistent . it surpasses benchmarks on IEMOCAP, CMU-MOSI, and CMU MOSEI by 1.43% and 1.25% .

Copied to clipboard

Peng Wang, Junyang Lin, An Yang, Chang Zhou, Yichang Zhang, Jingren Zhou, Hongxia Yang

AutoRAG-HP: Automatic Online Hyper-Parameter Tuning for Retrieval-Augmented Generation (2024.findings-emnlp)

Challenge:	Existing methods for table-to-text generation suffer from poor faithfulness and low coverage.
Approach:	They propose a method that combines Autoregressive and Non-Autoregressive generation to generate a table-to-text from a key-value table using a skeleton and an edit-based non-autoregressively generation model.
Outcome:	The proposed method outperforms the existing methods on WikiPerson and WikiBio datasets on coverage and faithfulness.

Copied to clipboard

Jia Fu, Xiaoting Qin, Fangkai Yang, Lu Wang, Jue Zhang, Qingwei Lin, Yubo Chen, Dongmei Zhang, Saravan Rajmohan, Qi Zhang

Information Aggregation for Multi-Head Attention with Routing-by-Agreement (N19-1)

Challenge:	Recent advances in Large Language Models have transformed ML/AI development . a reevaluation of AutoML principles for Retrieval-Augmented Generation (RAG) systems is needed.
Approach:	They propose a framework for hyper-parameter tuning and a hierarchical MAB method for efficient exploration of large search spaces.
Outcome:	The proposed framework outperforms baseline methods in more challenging optimization scenarios.

Copied to clipboard

Jian Li, Baosong Yang, Zi-Yi Dou, Xing Wang, Michael R. Lyu, Zhaopeng Tu

Sibyl: Empowering Empathetic Dialogue Generation in Large Language Models via Sensible and Visionary Commonsense Inference (2025.coling-main)

Challenge:	Existing studies focus on extracting informative or distinct partial-representations from different subspaces, while few studies have paid attention to the aggregation of the extracted partial-Representations.
Approach:	They propose to use a routing-by-agreement algorithm to improve multi-head attention by iteratively updating the proportion of how much a part should be assigned to a whole based on agreement between parts and wholes.
Outcome:	The proposed algorithm improves the information aggregation for multi-head attention over the standard linear transformation on linguistic probing and machine translation tasks.

Copied to clipboard

Lanrui Wang, Jiangnan Li, Chenxu Yang, Zheng Lin, Hongyin Tang, Huan Liu, Yanan Cao, Jingang Wang, Weiping Wang

Lost in Translation? Translation Errors and Challenges for Fair Assessment of Text-to-Image Models on Multilingual Concepts (2024.naacl-short)

Challenge:	Recent studies have focused on integrating commonsense knowledge into chatbots to enhance their ability to understand and generate dialogue responses.
Approach:	They propose a framework that integrates commonsense knowledge into chatbots to enable them to elicit more empathetic responses.
Outcome:	The proposed framework enables LLMs to uncover the implicit requirements of the conversation, aiming to elicit more empathetic responses.

Copied to clipboard

Michael Saxon, Yiran Luo, Sharon Levy, Chitta Baral, Yezhou Yang, William Yang Wang

A Corpus and Method for Chinese Named Entity Recognition in Manufacturing (2024.lrec-main)

Challenge:	With growth in the popularity of text-to-image models has come interest in assessing their multilingual capabilities, including multilingual accessibility.
Approach:	They propose to correct translation errors in a concept list translated to seven languages and compare the outputs of the benchmark to those conditioned on the old.
Outcome:	The proposed benchmark contains translation errors in Spanish, Japanese, and Chinese.

Copied to clipboard

Ruiting Li, Peiyan Wang, Libang Wang, Danqingxin Yang, Dongfeng Cai

Measuring What Makes You Unique: Difference-Aware User Modeling for Enhancing LLM Personalization (2025.findings-acl)

Challenge:	Existing resources and techniques for named entity recognition (NER) for manufacturing-specific named entities are limited.
Approach:	They propose a corpus of Chinese manufacturing specifications, named MS-NERC, with 4,424 sentences and 16,383 entities.
Outcome:	The proposed model outperforms neural methods in few-shot and rich-resource domains.

Copied to clipboard

Yilun Qiu, Xiaoyan Zhao, Yang Zhang, Yimeng Bai, Wenjie Wang, Hong Cheng, Fuli Feng, Tat-Seng Chua

Challenge:	Extensive experiments on real-world datasets demonstrate that DPL significantly enhances LLM personalization.
Approach:	They propose a novel approach that emphasizes extracting inter-user differences to enhance LLM personalization.
Outcome:	The proposed approach extracts inter-user differences to enhance LLM personalization.

Memo-SQL: Structured Decomposition and Experience-Driven Self-Correction for Training-Free NL2SQL (2026.findings-acl)

Copied to clipboard

Yang Zerui, Weichuan Wang, Yanwei Xu, Linqi Song, Yudai Matsuda, Wei Han, Bo Bai

Robustness-Aware Word Embedding Improves Certified Robustness to Adversarial Word Substitutions (2023.findings-acl)

Challenge:	Existing NL2SQL systems rely on in-context learning with only correct examples . current test-time scaling methods often decompose questions arbitrarily, resulting in poor performance .
Approach:	They propose a structured decomposition and experience-aware self-correction framework for NL2SQL . they build a dynamic memory of successful queries and historical error–fix pairs .
Outcome:	The proposed framework achieves 68.5% execution accuracy on BIRD, setting new state of the art among open, zero-fine-tuning methods.

Copied to clipboard

Yibin Wang, Yichen Yang, Di He, Kun He

Everyone is unique: Towards Behaviorally Heterogeneous Negotiation Dialogue Systems for Debt Collection (2026.acl-long)

Challenge:	Embedding interval bound constraint is important for NLP models to be certified robust, but adversarial examples can be crafted by synonym substitutions.
Approach:	They propose a triplet loss to train robustness-aware word embeddings for better certified robustness.
Outcome:	The proposed method outperforms state-of-the-art certified defense baselines and generalizes well to unseen substitutions.

Copied to clipboard

Yuhang Yang, Kai Tang, Chao Ye, Haobo Wang, Qiqi Luo, Jin Guang Zheng, Zhixin Zhang

ToNER: Type-oriented Named Entity Recognition with Generative Language Model (2024.lrec-main)

Challenge:	Existing models that assume users to be static, rational agents with fixed preferences fail to capture rich behavioral heterogeneity in real-world debt collection scenarios.
Approach:	They propose a public persona-enriched debt collection benchmark that highlights behavioral heterogeneity in negotiation.
Outcome:	The proposed benchmark outperforms existing models in realistic scenarios using 16 state-of-the-art LLMs.

Copied to clipboard

Guochao Jiang, Ziqin Luo, Yuchen Shi, Dixuan Wang, Jiaqing Liang, Deqing Yang

HMoE: Heterogeneous Mixture of Experts for Language Modeling (2025.emnlp-main)

Challenge:	Input too many potential entity types would distract the model inevitably.
Approach:	They propose to use a generative model to exploit entity types' merit on promoting NER task by appending a type matching model to identify the entity types most likely to appear in the sentence.
Outcome:	The proposed framework exploits entity types' merit on promoting NER task by adding auxiliary task to the model to discover the entity types.

Copied to clipboard

An Wang, Xingwu Sun, Ruobing Xie, Shuaipeng Li, Jiaqi Zhu, Zhen Yang, Pinxue Zhao, Weidong Han, Zhanhui Kang, Di Wang, Naoaki Okazaki, Cheng-zhong Xu

OS-Symphony: A Holistic Framework for Robust and Generalist Computer-Using Agents (2026.acl-long)

Challenge:	Mixture of Experts (MoE) models use homogeneous experts with diverse capacities, resulting in a lack of expert specialization and parameter utilization.
Approach:	They propose a framework where experts differ in size and possess diverse capacities . they propose HMoE to encourage frequent activation of smaller experts .
Outcome:	The proposed framework outperforms homogeneous homogenous MoE models on evaluation benchmarks and achieves lower loss rate with fewer activated parameters.

Copied to clipboard

Bowen Yang, Kaiming Jin, Zhenyu Wu, Zhaoyang Liu, Qiushi Sun, Zehao Li, JingJing Xie, Zhoumianze Liu, Fangzhi Xu, Kanzhi Cheng, Yian Wang, Qingyun Li, Yu Qiao, Zun Wang, Zichen Ding

SCAN: Structured Capability Assessment and Navigation for LLMs (2026.acl-long)

Challenge:	Vision-Language Models (VLMs) lack visual-aware tutorial retrieval and historical visual context curation and pruning.
Approach:	They propose a framework that integrates an orchestrator and a Reflection-Memory Agent for robust automation.
Outcome:	Experimental results show that OS-Symphony delivers substantial performance gains across model scales.

Copied to clipboard

Zongqi Wang, Tianle Gu, Chen Gong, Xin Tian, Siqi Bao, Yujiu Yang

PUPPET: Neural-Symbolic Standardized Patients for Mental Health (2026.acl-long)

Challenge:	Existing research has focused on approximating model rankings, but such benchmarks fail to provide users and developers with a comprehensive and fine-grained understanding of a specific model’s capabilities.
Approach:	They propose a framework that enables detailed characterization of LLM capabilities through comprehensive and fine-grained evaluation.
Outcome:	The proposed framework enables detailed characterization of large language models through comprehensive and fine-grained evaluation.

Copied to clipboard

Chen Xu, Yu ji, Zhenyu Lv, Yang Yi, Yizhe Yang, Luyao Ji, Chaoyi Chen, Xianyang Wang, Tian Lan, Zhihua Wang, Juan Wang, Xunde Dong, Fuze Tian, Qunxi Dong, Bin Hu

Efficient Integration of External Knowledge to LLM-based World Models via Retrieval-Augmented Generation and Reinforcement Learning (2025.findings-emnlp)

Challenge:	Existing LLM-based training approaches lack faithful responses to clinical errors and explainable feedback.
Approach:	They propose a neural-symbolic virtual standardized patient governed by an OBSERVE-THINK-BEHAVE architecture that embeds LLM reasoning into a symbolic system where experts implant causal associations between intervention logic and patient mental states.
Outcome:	The proposed model outperforms baselines in faithfulness and pedagogical value.

Copied to clipboard

Chang Yang, Xinrun Wang, Qinggang Zhang, Qi Jiang, Xiao Huang

FusionFlow: Enabling Deep Structural Exploration for Automated Agentic Workflow Generation (2026.acl-long)

Challenge:	Existing attempts to enhance LLM-based world models through prompting or fine-tuning approaches are either requiring human knowledge or computationally extensive.
Approach:	They propose a framework that leverages retrieval-augmented generation to integrate external knowledge to LLM-based world models.
Outcome:	The proposed framework outperforms baseline models and exhibits strong generalizability.

Copied to clipboard

Xiang Wang, Zongtao Yang, Zhuojian Hong, Shuhao Zhang, Wei Wei

Multi-Party Empathetic Dialogue Generation: A New Task for Dialog Systems (2022.acl-long)

Challenge:	Existing workflow generation methods rely on incremental refinement or tree-based search over a single evolving workflow.
Approach:	They propose a framework centered on workflow fusion that synthesizes multiple independently evolved workflows and allows exploration of deeper regions of the workflow space within a finite budget.
Outcome:	Experiments show that FusionFlow outperforms existing workflow generation methods on six reasoning benchmarks.

Copied to clipboard

Ling.Yu Zhu, Zhengkun Zhang, Jun Wang, Hongbin Wang, Haiying Wu, Zhenglu Yang

Guided by the Plan: Enhancing Faithful Autoregressive Text-to-Audio Generation with Guided Decoding (2026.eacl-long)

Challenge:	Existing work on empathetic dialogues focused on the two-party scenario, but multi-party dialogues are pervasive in reality.
Approach:	They propose a multi-party empathetic dialogue generation task that uses a static-dynamic model to explore emotion and sensibility.
Outcome:	The proposed task is based on a model with static sensibility and dynamic emotion . it achieves state-of-the-art performance in multi-party empathetic dialogue learning .

Copied to clipboard

Juncheng Wang, Zhe Hu, Chao Xu, Siyue Ren, Yuxiang Feng, Yang Liu, Baigui Sun, Shujun Wang

MultiAgent Collaboration Attack: Investigating Adversarial Attacks in Large Language Model Collaborations via Debate (2024.findings-emnlp)

Challenge:	Autoregressive (AR) models excel at generating temporally coherent audio by producing tokens sequentially, yet they often falter in faithfully following complex textual prompts.
Approach:	They propose a lightweight auxiliary model trained with a GAE-inspired objective to predict final instruction-following quality from partial generations.
Outcome:	The proposed model achieves 10 points improvement in CLAP score over baseline AR models while maintaining computational parity with best-of-N decoding.

Copied to clipboard

Alfonso Amayuelas, Xianjun Yang, Antonis Antoniades, Wenyue Hua, Liangming Pan, William Yang Wang

VIRT: Improving Representation-based Text Matching via Virtual Interaction (2022.emnlp-main)

Challenge:	Large Language Models (LLMs) have shown exceptional results when working individually, and have reduced parameter size and inference times.
Approach:	They evaluate the behavior of a network of models collaborating through debate under the influence of an adversary and examine inference-time methods to generate more compelling arguments.
Outcome:	The proposed model-based model-driven analysis shows that the model-led model-mediated debates generate more compelling arguments and provide a defensive strategy.

Copied to clipboard

Dan Li, Yang Yang, Hongyin Tang, Jiahao Liu, Qifan Wang, Jingang Wang, Tong Xu, Wei Wu, Enhong Chen

Achieving binary weight and activation for LLMs using Post-Training Quantization (2025.findings-acl)

Challenge:	Experimental results show that representation-based text matching methods suffer from performance degradation due to the lack of interactions between the pair of texts.
Approach:	They propose a virtual interaction mechanism that enables deep interaction between texts . they propose 'inteRacTion mechanism' that can be integrated into existing methods as plugins .
Outcome:	The proposed method outperforms state-of-the-art models on six text matching benchmarks.

Copied to clipboard

Siqing Song, Chuang Wang, Rui-Qi Wang, Yi Yang, Xu-Yao Zhang

The Staircase of Ethics: Probing LLM Value Priorities through Multi-Step Induction to Complex Moral Dilemmas (2025.emnlp-main)

Challenge:	Existing methods for quantizing large language models suffer from performance degradation when weights are quantized to 1 bit.
Approach:	They propose a post-training quantization framework with W(1+1)A(14) configuration . they propose utilizing Hessian-aware fine-grained grouping along with an EM-based quantization scheme .
Outcome:	The proposed method surpasses state-of-the-art (SOTA) LLM quantization baselines on W2A4 across multiple tasks.

Copied to clipboard

Ya Wu, Qiang Sheng, Danding Wang, Guang Yang, Yifan Sun, Zhengjia Wang, Yuyan Bu, Juan Cao

DUET: Joint Exploration of User–Item Profiles in Recommendation System (2026.findings-acl)

Challenge:	Existing evaluations of LLMs' moral reasoning capabilities rely on single-step evaluations, ignoring how models adapt to evolving ethical challenges.
Approach:	They propose a framework to evaluate evolving moral judgments of large language models (LLMs) using multi-step moral dilemma questionnaires.
Outcome:	The proposed framework enables a fine-grained analysis of how LLMs adjust their moral reasoning across escalating dilemmas.

Copied to clipboard

Yue Chen, Yifei Sun, Lu Wang, Fangkai Yang, Pu Zhao, Minjie Hong, Yifei Dong, Minghua He, Nan Hu, Jianjin Zhang, Zhiwei Dai, Yuefeng Zhan, Weihao Han, Hao Sun, Qingwei Lin, Weiwei Deng, Feng Sun, Qi Zhang, Saravan Rajmohan, Dongmei Zhang

Challenge:	Existing LLMs are opaque and difficult to interpret, resulting in limited interpretability.
Approach:	They propose an interaction-aware profile generator that jointly produces user and item profiles conditioned on both user history and item evidence.
Outcome:	The proposed model outperforms baselines on three real-world datasets.

Decoding in Latent Spaces for Efficient Inference in LLM-based Recommendation (2025.findings-emnlp)

Copied to clipboard

Chengbing Wang, Yang Zhang, Zhicheng Wang, Tianhao Shi, Keqin Bao, Fuli Feng, Tat-Seng Chua

Audio-Aware Large Language Models as Judges for Speaking Styles (2025.findings-emnlp)

Challenge:	Light Latent-space Decoding (L2D) is an efficient and efficient latent- space decoding method.
Approach:	They propose to bypass language-space decoding by matching candidate items with LLM's internal thought representations in the latent space.
Outcome:	The proposed method is 10x faster than language-space decoding while maintaining or enhancing performance.

Copied to clipboard

Cheng-Han Chiang, Xiaofei Wang, Chung-Ching Lin, Kevin Lin, Linjie Li, Radu Kopetz, Yao Qian, Zhendong Wang, Zhengyuan Yang, Hung-yi Lee, Lijuan Wang

GLA: Grounding Large Language Models in Molecular Hierarchy for Chemical Understanding (2026.findings-acl)

Challenge:	Audio-aware large language models (ALLMs) can understand textual and non-textual information in the audio input.
Approach:	They use audio-aware large language models (ALLMs) to evaluate the speaking styles of SLMs on two tasks: voice style instruction following and role-playing.
Outcome:	The proposed models can understand the textual and non-textual information in the audio input and can be used as a judge to assess the speaking styles of SLMs.

Copied to clipboard

Yingxu Li, Jingjie Zeng, Zekun Wang, Hongfei Lin, Liang Yang

RewardDS: Privacy-Preserving Fine-Tuning for Large Language Models via Reward Driven Data Synthesis (2025.emnlp-main)

Challenge:	Existing molecule-language models obscure the hierarchical organization of chemical semantics . Existing models rely on linear or uniform encodings, causing structural distortion .
Approach:	They propose a framework that integrates intrinsic molecular topology into large language models.
Outcome:	The proposed framework improves on cross-modal retrieval, captioning, and property prediction benchmarks.

Copied to clipboard

Jianwei Wang, Chengming Shi, Junyao Yang, Haoran Li, Qianli Ma, Huiping Zhuang, Cen Chen, Ziqian Zeng

An Effective Deployment of Contrastive Learning in Multi-label Text Classification (2023.findings-acl)

Challenge:	Existing solutions to fine-tune large language models for domain-specific tasks are ineffective in addressing privacy concerns.
Approach:	They propose a privacy-preserving framework that fine-tunes a reward proxy model and uses reward signals to guide the synthetic data generation.
Outcome:	The proposed framework fine-tunes a reward proxy model and uses reward signals to guide the synthetic data generation.

Copied to clipboard

Nankai Lin, Guanqiu Qin, Gang Wang, Dong Zhou, Aimin Yang

RICO: Improving Accuracy and Completeness in Image Recaptioning via Visual Reconstruction (2025.emnlp-main)

Challenge:	Existing studies on contrastive learning in natural language processing tasks have not explored the effectiveness of the technology.
Approach:	They propose five novel contrastive losses for multi-label text classification tasks that exploit the complexity of the input logic and the semantic representation space.
Outcome:	The proposed contrastive losses improve multi-label text classification tasks and can be adapted for multi-task tasks.

Copied to clipboard

Yuchi Wang, Yishuo Cai, Shuhuai Ren, Sihan Yang, Linli Yao, Yuanxin Liu, Yuanxing Zhang, Pengfei Wan, Xu Sun

Pre3: Enabling Deterministic Pushdown Automata for Faster Structured LLM Generation (2025.acl-long)

Challenge:	Existing recaptioning methods suffer from inaccuracies due to missing fine-grained details.
Approach:	They propose a framework that refines captions through visual reconstruction using a text-to-image model and a visual reconstruction framework.
Outcome:	The proposed framework outperforms baselines on CapsBench and CompreCap by 10%.

Copied to clipboard

Junyi Chen, Shihao Bai, Zaijun Wang, Siyu Wu, Chuheng Du, Hailong Yang, Ruihao Gong, Shengzhong Liu, Fan Wu, Guihai Chen

OASum: Large-Scale Open Domain Aspect-based Summarization (2023.findings-acl)

Challenge:	Existing methods for structured generation of outputs are inefficient under large inference batches.
Approach:	They propose a new LLM-based method that parses LR(1) grammars into a pushdown automaton and exploits deterministic pushdown automation to optimize the constrained LLM decoding efficiency.
Outcome:	The proposed method improves time per output token (TPOT) by 40% and throughput by 36% .

Copied to clipboard

Xianjun Yang, Kaiqiang Song, Sangwoo Cho, Xiaoyang Wang, Xiaoman Pan, Linda Petzold, Dong Yu

Summarization

Challenge:	Existing generic summarization methods generate only one summary for all different requests which is not optimal for diverse demands.
Approach:	They use crowd-sourced knowledge on Wikipedia to create a large-scale open-domain aspect-based summarization dataset with 1 million different aspects on 2 million Wikipedia pages.
Outcome:	The proposed model can generate diverse aspect-based summarizations on Wikipedia with zero/few-shot and fine-tuning on seven downstream datasets.

HyperPELT: Unified Parameter-Efficient Language Model Tuning for Both Language and Vision-and-Language Tasks (2023.findings-acl)

Copied to clipboard

Zhengkun Zhang, Wenya Guo, Xiaojun Meng, Yasheng Wang, Yadao Wang, Xin Jiang, Qun Liu, Zhenglu Yang

Concept Pointer Network for Abstractive Summarization (D19-1)

Challenge:	Pretraining and fine-tuning are the dominant paradigms in natural language processing.
Approach:	They propose a parameter-efficient multitask learning framework that takes trainable hyper-embeddings and visual modality as input and outputs weights for different modules in a pretrained language model.
Outcome:	The proposed framework adds fewer trainable parameters in multi-task learning while achieving superior performances and transfer ability compared to state-of-the-art methods.

Copied to clipboard

Wenbo Wang, Yang Gao, Heyan Huang, Yuxiang Zhou

Generation-driven Contrastive Self-training for Zero-shot Text Classification with Instruction-following LLM (2024.eacl-long)

Challenge:	Abstractive summarization (ABS) has gained overwhelming success owing to a tremendous development of sequence-to-sequence models and its variants.
Approach:	They propose a concept pointer network that leverages knowledge-based, context-aware conceptualizations to derive an extended set of candidate concepts and then points to the most appropriate choice using both the concept set and original source text.
Outcome:	The proposed model improves on the DUC-2004 and Gigaword datasets and human evaluation of its abstractive abilities supports the quality of the summaries produced.

Copied to clipboard

Ruohong Zhang, Yau-Shian Wang, Yiming Yang

Investigating the Representation of Backchannels and Fillers in Fine-tuned Language Models (2026.acl-long)

Challenge:	a novel method to train a smaller model with LLMs for zero-shot text classification requires immense computational resources due to their substantial model size.
Approach:	They propose a method which leverages the generative power of large language models to train a smaller model.
Outcome:	The proposed method outperforms state-of-the-art methods when limited data is available.

Copied to clipboard

Yu Wang, Leyi Lao, Langchu Huang, Gabriel Skantze, Yang Xu, Hendrik Buschmeier

MARS: Unleashing the Power of Speculative Decoding via Margin-Aware Verification (2026.findings-acl)

Challenge:	Backchannels and fillers are important linguistic expressions in dialogue, but often ignored in modern transformer-based language models.
Approach:	They use clustering analysis to learn backchannels and fillers in dialogues in English and Japanese and use natural language generation metrics to confirm this.
Outcome:	The proposed models can learn representations of backchannels and fillers using three fine-tuning strategies.

Copied to clipboard

Jingwei Song, Xinyu Wang, Hanbin Wang, Xiaoxuan Lei, Tianyu Shi, Shixin Han, Eric Yang, Xiao-Wen Chang, Lynn Ai

Challenge:	Autoregressive large language models suffer from high inference latency due to memorybandwidth constraints.
Approach:	They propose a method that decouples generation and verification by decoupling tokens and a lightweight draft model.
Outcome:	The proposed method delivers consistent and significant speedups over state-of-the-art baselines while preserving generation quality across diverse benchmarks.

KC-ISA: An Implicit Sentiment Analysis Model Combining Knowledge Enhancement and Context Features (2022.coling-1)

Copied to clipboard

Minghao Xu, Daling Wang, Shi Feng, Zhenfei Yang, Yifei Zhang

Bounding the Capabilities of Large Language Models in Open Text Generation with Prompt Constraints (2023.findings-eacl)

Challenge:	Existing research results on explicit sentiment analysis are limited . implicit sentiment analysis is a process of analyzing text based on whether it contains explicit sentiment words.
Approach:	They propose a model that integrates external knowledge and contextual features . they use a knowledge graph to supplement implicit sentiment expression .
Outcome:	The proposed model can achieve better results on the SMP2019 implicit sentiment analysis dataset.

Copied to clipboard

Albert Lu, Hongxin Zhang, Yanzhe Zhang, Xuezhi Wang, Diyi Yang

TextBind: Multi-turn Interleaved Multimodal Instruction-following in the Wild (2024.findings-acl)

Challenge:	Existing and potential applications of open-ended text generation are farreaching, spanning domains such as QA, story generation, open-end dialogue, and ChatGPT 1 .
Approach:	They propose a prompt-centric approach to analyzing and bounding the abilities of open-ended generative models by a set of structural and stylistic prompts.
Outcome:	The proposed method can be generalized to other large models like BLOOM and OPT.

Copied to clipboard

Huayang Li, Siheng Li, Deng Cai, Longyue Wang, Lemao Liu, Taro Watanabe, Yujiu Yang, Shuming Shi

Communication-Efficient Desire Alignment for Proactive Embodied Human–Agent Interaction (2026.acl-long)

Challenge:	Large language models with instruction-following capabilities have revolutionized the field of artificial intelligence.
Approach:	They propose an annotation-free framework for empowering large language models with instruction-following capabilities.
Outcome:	The proposed framework generates multi-turn multimodal instruction-response conversations from a language model.

Copied to clipboard

Yuanfei Wang, Xinju Huang, Fangwei Zhong, Yaodong Yang, Yizhou Wang, Yuanpei Chen, Hao Dong

NOTA: Multimodal Music Notation Understanding for Visual Large Language Model (2025.findings-naacl)

Challenge:	Effective real-world human–agent interactions are long-term and repeated.
Approach:	They propose a simulation that uses a proxy user with value-driven preferences and natural language behavior to evaluate how agents adapt to users across interactions and satisfy their desires.
Outcome:	HA-Desire, a home assistance simulation, shows that agents can adapt to user needs and provide proactive assistance within limited communication.

Copied to clipboard

Mingni Tang, Jiajia Li, Lu Yang, Zhiqiang Zhang, Jinhao Tian, Zuchao Li, Lefei Zhang, Ping Wang

Finding and Editing Multi-Modal Neurons in Pre-Trained Transformers (2024.findings-acl)

Challenge:	Existing general-domain visual language models lack ability of music notation understanding . Symbolic music is represented in two distinct forms: auditory music and symbolic music .
Approach:	They propose to train a multimodal music notation model using a large-scale dataset . they use cross-modal alignment to train the model for music notations analysis .
Outcome:	The proposed model improves on music understanding by training with a multimodal music notation model.

Copied to clipboard

Haowen Pan, Yixin Cao, Xiaozhi Wang, Xun Yang, Meng Wang

GLIMPSE: Do Large Vision-Language Models Truly Think With Videos or Just Glimpse at Them? (2025.emnlp-main)

Challenge:	Existing methods to identify key neurons for interpretability of multi-modal large language models are unclear.
Approach:	They propose a method to identify key neurons for interpretability by multi-modal large language models.
Outcome:	The proposed method improves conventional works upon efficiency and applied range by removing needs of costly gradient computation.

Copied to clipboard

Yiyang Zhou, Linjie Li, Shi Qiu, Zhengyuan Yang, Yuyang Zhao, Siwei Han, Yangfan He, Kangqi Li, Haonian Ji, Zihao Zhao, Haibo Tong, Lijuan Wang, Huaxiu Yao

Identifying Tension in Holocaust Survivors’ Interview: Code-switching/Code-mixing as Cues (2022.lrec-1)

Challenge:	Existing video benchmarks often resemble image-based questions with scans of only a few key frames, without deep temporal reasoning.
Approach:	They propose a video benchmark to assess whether large vision-language models can genuinely think with videos rather than perform superficial frame-level analysis.
Outcome:	The proposed benchmark consists of 3,269 videos and over 4,342 highly visual-centric questions across 11 categories, including Trajectory Analysis, Temporal Reasoning, and Forensics Detection.

Copied to clipboard

Xinyuan Xia, Lu Xiao, Kun Yang, Yueyue Wang

Curse of Knowledge: Your Guidance and Provided Knowledge are biasing LLM Judges in Complex Evaluation (2025.findings-emnlp)

Challenge:	Using CS/CM as a linguistic phenomenon could be a sign of tension in Holocaust survivors’ interviews.
Approach:	They annotated CS/CM codes and annotate silence situations in an open corpus . they found that most annotations were captured in the tension places .
Outcome:	The proposed method shows that annotations are captured in the tension places . the study calls for more research endeavors on tension detection .

Copied to clipboard

Weiyuan Li, Xintao Wang, Siyu Yuan, Rui Xu, Jiangjie Chen, Qingqing Dong, Yanghua Xiao, Deqing Yang

Challenge:	a recent study has focused on simple settings, but their reliability in complex tasks remains understudied.
Approach:	They propose to use large language models as judges to evaluate reliability in complex tasks . they use a challenge benchmark to expose and quantify Auxiliary Information Induced Biases .
Outcome:	The proposed benchmark exposes and quantifies Auxiliary Information Induced Biases across 12 basic and 3 advanced scenarios.

MDTeamGPT: Mitigating Context Collapse and Enabling Self-Evolution in Medical Multi-Agent Reasoning (2026.findings-acl)

Copied to clipboard

Kai Chen, Xinfeng Li, Tianpei Yang, Hewei Wang, Guang Yang, Jing Huo, Yang Gao

CODIS: Benchmarking Context-dependent Visual Comprehension for Multimodal Large Language Models (2024.acl-long)

Challenge:	Long, multi-round, multirole interaction trajectories lead to severe information dilution and context window overload, triggering context collapse which destabilizes reasoning.
Approach:	They propose a multi-agent framework that compresses and reorganizes multi-round consensus.
Outcome:	The proposed framework outperforms baselines across text-based and multimodal tasks while demonstrating superior diagnostic performance and stability in complex clinical scenarios.

Copied to clipboard

Fuwen Luo, Chi Chen, Zihao Wan, Zhaolu Kang, Qidong Yan, Yingjie Li, Xiaolong Wang, Siyu Wang, Ziyue Wang, Xiaoyue Mi, Peng Li, Ning Ma, Maosong Sun, Yang Liu

MultiAgentBench : Evaluating the Collaboration and Competition of LLM agents (2025.acl-long)

Challenge:	Multimodal large language models have demonstrated promising results in a variety of tasks that combine vision and language.
Approach:	They propose a benchmark to assess the ability of models to use contextual information in free-form text to enhance visual comprehension.
Outcome:	The proposed model fails to extract and utilize contextual information to improve understanding of images.

Copied to clipboard

Kunlun Zhu, Hongyi Du, Zhaochen Hong, Xiaocheng Yang, Shuyi Guo, Zhe Wang, Zhenhailong Wang, Cheng Qian, Robert Tang, Heng Ji, Jiaxuan You

Challenge:	Large Language Models (LLMs) have shown remarkable capabilities as autonomous agents, yet existing benchmarks focus on single-agent tasks or are confined to narrow domains, failing to capture the dynamics of multi-agent coordination and competition.
Approach:	They propose a benchmark to evaluate LLM-based multi-agent systems across diverse, interactive scenarios.
Outcome:	The proposed framework measures task completion and quality of collaboration and competition using novel, milestone-based key performance indicators.

Hierarchical-Task-Aware Multi-modal Mixture of Incremental LoRA Experts for Embodied Continual Learning (2025.acl-long)

Copied to clipboard

Ziqi Jia, Anmin Wang, Xiaoyang Qu, Xiaowen Yang, Jianzong Wang

Can MLLMs Understand the Deep Implication Behind Chinese Images? (2025.acl-long)

Challenge:	Existing continual learning setups for embodied intelligence focus on executing low-level actions, neglecting the ability to learn high-level planning and multi-level knowledge.
Approach:	They propose a Hierarchical Embodied Continual Learning Setups (HEC) that divides the agent’s continual learning process into two layers: high-level instructions and low-level actions.
Outcome:	The proposed method reduces the forgetting of old tasks compared to other methods, while orthogonally training the remaining parts.

Copied to clipboard

Chenhao Zhang, Xi Feng, Yuelin Bai, Xeron Du, Jinchang Hou, Kaixin Deng, Guangzeng Han, Qinrui Li, Bingli Wang, Jiaheng Liu, Xingwei Qu, Yifei Zhang, Qixuan Zhao, Yiming Liang, Ziqiang Liu, Feiteng Fang, Min Yang, Wenhao Huang, Chenghua Lin, Ge Zhang, Shiwen Ni

RecMind: Large Language Model Powered Agent For Recommendation (2024.findings-naacl)

Challenge:	MLLMs perform poorly on traditional culture images, indicating limitations in understanding high-level semantics and lacking a deep knowledge base of Chinese traditional culture.
Approach:	They propose to use Chinese images to assess MLLMs' higher-order perception and understanding of Chinese visual content.
Outcome:	The proposed model incorporates images that represent Chinese traditional culture, such as famous Chinese traditional paintings, to ensure the authenticity of the Chinese context.

Copied to clipboard

Yancheng Wang, Ziyan Jiang, Zheng Chen, Fan Yang, Yingxue Zhou, Eunah Cho, Xing Fan, Yanbin Lu, Xiaojiang Huang, Yingzhen Yang

Pathway2Text: Dataset and Method for Biomedical Pathway Description Generation (2022.findings-naacl)

Challenge:	Existing recommendations systems are limited in generalizing to new tasks due to model scale and data size constraints.
Approach:	They propose an LLM-powered autonomous recommender agent, RecMind, which is capable of leveraging external knowledge to provide zero-shot personalized recommendations.
Outcome:	The proposed model outperforms existing zero/few-shot LLM-based recommendation baseline methods in various tasks and achieves comparable performance to a fully trained recommendation model P5.

Copied to clipboard

Junwei Yang, Zequn Liu, Ming Zhang, Sheng Wang

Knowledge Decoupling via Orthogonal Projection for Lifelong Editing of Large Language Models (2025.acl-long)

Challenge:	Neural text generation is a novel technique to describe biomedical pathways without manually curation.
Approach:	They propose a new dataset Pathway2Text which contains 2,367 pairs of biomedical pathways and textual descriptions.
Outcome:	The proposed method improves on both Graph2Text and Text2Graph tasks and can be used as a benchmark for biomedical named entity recognition.

Copied to clipboard

Haoyu Xu, Pengxiang Lan, Enneng Yang, Guibing Guo, Jianzhe Zhao, Linying Jiang, Xingwei Wang

DivScene: Towards Open-Vocabulary Object Navigation with Large Vision Language Models in Diverse Scenes (2025.findings-emnlp)

Challenge:	Existing methods for enhancing large language models (LLMs) have achieved some success, but their knowledge understanding and memory capacity significantly degrades after extensive editing.
Approach:	They propose a method that stores the basis vectors of the representation space of past edits in a knowledge cache and projects the gradient of the current edit onto a space orthogonal to previous knowledge for updating.
Outcome:	The proposed method improves question-answering ability and hallucination mitigation by 14% and 61% for large language models after 3,000 edits.

Copied to clipboard

Zhaowei Wang, Hongming Zhang, Tianqing Fang, Ye Tian, Yue Yang, Kaixin Ma, Xiaoman Pan, Yangqiu Song, Dong Yu

Non-Autoregressive Math Word Problem Solver with Unified Tree Structure (2023.emnlp-main)

Challenge:	Large Vision-Language Models (LVLMs) have achieved significant progress in tasks like visual question answering and document understanding.
Approach:	They introduce DivScene, a large-scale dataset with 4,614 houses across 81 scene types and 5,707 kinds of target objects.
Outcome:	The proposed dataset provides a much greater diversity of target objects and scene types than existing datasets, enabling a comprehensive task evaluation.

Copied to clipboard

Yi Bin, Mengqun Han, Wenhao Shi, Lei Wang, Yang Yang, See-Kiong Ng, Heng Shen

Numerical Reasoning

Challenge:	Existing MWP solvers do not handle variants that can be derived via mathematical manipulation.
Approach:	They propose a non-autoregressive solver to present a solution expression and decode it from a given problem description.
Outcome:	The proposed solver is able to decode multiple expression variants and correct them . it is based on a unified tree structure and is available on Math23K and MAWPS.

Dual Dynamic Memory Network for End-to-End Multi-turn Task-oriented Dialog Systems (2020.coling-main)

Copied to clipboard

Jian Wang, Junhao Liu, Wei Bi, Xiaojiang Liu, Kejing He, Ruifeng Xu, Min Yang

RTFE: A Recursive Temporal Fact Embedding Framework for Temporal Knowledge Graph Completion (2021.naacl-main)

Challenge:	Existing task-oriented dialog systems struggle to dynamically model long dialog context for interactions and effectively incorporate knowledge base (KB) information into dialog generation.
Approach:	They propose a dual dynamic memory network for multi-turn dialog generation . the model dynamically expands the dialog memory turn by turn and keeps track of dialog history .
Outcome:	The proposed model outperforms baseline models on three benchmark datasets on human evaluation and automatic evaluation.

Copied to clipboard

Youri Xu, Haihong E, Meina Song, Wenyu Song, Xiaodong Lv, Wang Haotian, Yang Jinrui

Sign2Vis: Automated Data Visualization from Sign Language (2025.findings-acl)

Challenge:	Existing methods for static knowledge graph embedding (SKGE) ignore the continuity of states of TKGs in time evolution.
Approach:	They propose a Recursive Temporal Fact Embedding framework to transplant SKGE models to TKGs and enhance the performance of existing TKGE models.
Outcome:	The proposed framework can be used to transplant SKGE models to TKGs and improve existing models for TKG completion.

Copied to clipboard

Yao Wan, Yang Wu, Zhen Li, Guobiao Zhang, Hongyu Zhang, Zhou Zhao, Hai Jin, April Wang

Challenge:	Existing methods to translate natural language descriptions into visualization queries focus on spoken languages, not sign languages.
Approach:	They propose a sign language interface that enables the DHH community to engage more fully with data analysis.
Outcome:	The proposed interface can be used by the deaf and hard-of-hearing community.

DICA: Dual-Indicator Guided Contrastive Alignment in Multimodal Large Language Models (2026.findings-acl)

Copied to clipboard

Hao Yang, Jin Wang, Xuejie Zhang

Detecting Training Data of Large Language Models via Expectation Maximization (2026.eacl-long)

Challenge:	Multimodal large language models may deviate from this pattern due to attention drift and underutilization of visual evidence.
Approach:	They propose a Dual-Indicator Guided Contrastive Alignment (DICA) that tracks visual attention and output image correlations to improve visual grounding.
Outcome:	The proposed model outperforms existing approaches and significantly reduces hallucinations.

Copied to clipboard

Gyuwan Kim, Yang Li, Evangelia Spiliopoulou, Jie Ma, William Yang Wang

SeqAR: Jailbreak LLMs with Sequential Auto-Generated Characters (2025.naacl-long)

Challenge:	Membership inference attacks aim to determine whether a specific example was used to train a given language model.
Approach:	They propose a membership inference approach that iteratively refines prefix effectiveness and membership scores using an expectation-maximization strategy without requiring labeled non-member examples.
Outcome:	The proposed approach outperforms baselines under systematically varied distributional overlap and difficulty.

Copied to clipboard

Yan Yang, Zeguan Xiao, Xin Lu, Hongru Wang, Xuetao Wei, Hailiang Huang, Guanhua Chen, Yun Chen

Why Stop at One Error? Benchmarking LLMs as Data Science Code Debuggers for Multi-Hop and Multi-Bug Errors (2025.emnlp-main)

Challenge:	Existing studies have focused on the potential misuse of large language models (LLMs) however, the ability to align LLMs with human values is still vulnerable to malicious attacks.
Approach:	They propose a red-teaming strategy to enhance LLM safety by using a framework to design jailbreak prompts automatically.
Outcome:	The proposed framework achieves attack success rates of 88% and 60% in cold-start scenarios.

Copied to clipboard

Zhiyu Yang, Shuo Wang, Yukun Yan, Yang Deng

Learning with Noisy Labels for Sentence-level Sentiment Classification (D19-1)

Challenge:	Recent advances in Large Language Models (LLMs) have significantly reshaped software development practices, particularly in automating code generation and debugging.
Approach:	They propose to evaluate LLMs' capabilities on multi-hop error tracing and multi-bug detection in data science code debugging.
Outcome:	DSDBench adapts datasets from existing data science task benchmarks, such as DABench and MatPlotBench, featuring realistic data science debugging tasks with automatically synthesized multi-hop, multi-bug code snippets.

Copied to clipboard

Hao Wang, Bing Liu, Chaozhuo Li, Yan Yang, Tianrui Li

ProActor: Timing-Aware Reinforcement Learning for Proactive Task Scheduling Agents (2026.acl-long)

Challenge:	Existing research on learning with noisy labels dates back to the 1980s, but it is still vibrant today.
Approach:	They propose a novel DNN model called NetAb to deal with noisy labels during training and train the networks using their respective loss functions in mutual reinforcement.
Outcome:	The proposed model can fit training data with noisy labels and predict clean labels.

Copied to clipboard

Lei Ding, Bin He, Chenguang Wang, Yang Liu

HyperCRS: Hypergraph-Aware Multi-Grained Preference Learning to Burst Filter Bubbles in Conversational Recommendation System (2025.findings-acl)

Challenge:	Existing approaches to measuring and optimizing proactive task-oriented agents lack generalizable end-to-end solutions.
Approach:	They propose a framework for conversational task scheduling that integrates proactiveness reinforcement learning with a domain-agnostic annotation methodology.
Outcome:	The proposed framework enables scalable proactiveness reinforcement learning (RL) Experiments on two newly auto-annotated datasets demonstrate significant improvements in proactive timing while maintaining action consistency comparable to state-of-the-art baselines.

Copied to clipboard

Yongsen Zheng, Mingjie Qian, Guohua Wang, Yang Liu, Ziliang Chen, Mingzhi Mao, Liang Lin, Kwok-Yan Lam

Leveraging Language-based Representations for Better Solving Symbol-related Problems with Large Language Models (2025.coling-main)

Challenge:	Existing methods to analyze filter bubbles in the static recommendation environment are unable to burst them during user interactions.
Approach:	They propose a paradigm to learn multi-grained user preferences during dynamic user-system interactions via natural language conversations to burst filter bubbles.
Outcome:	The proposed paradigm achieves state-of-the-art performance and the superior of bursting filter bubbles in the conversational recommendation system.

Copied to clipboard

Yile Wang, Sijie Cheng, Zixin Sun, Peng Li, Yang Liu

M-TRACE: Detecting and Mitigating Time-Anchor Drift via Step-wise Conflict Checking in Temporal Reasoning (2026.findings-acl)

Challenge:	Symbols are used in abstract reasoning, chemical property prediction, and tabular question-answering.
Approach:	They propose a method that converts symbols to language-based representations to improve their accuracy.
Outcome:	The proposed method improves the accuracy of symbols in language-based models.

Copied to clipboard

Danyu Huang, Jiayuan Jiang, Yao Zhang, Jun Wang, Huijia Li, Zhenglu Yang

IPS: In-Prompt Process Supervision for Short Video Content Moderation (2026.acl-industry)

Challenge:	Experimental results show that M-TRACE effectively reduces time-anchor drift . external knowledge may be inaccurate while internal knowledge can become outdated .
Approach:	They propose a multi-agent reasoning framework for temporal knowledge conflicts . they propose 'TimeConfQA' which guides conflict-aware final reasoning .
Outcome:	Experimental results show that M-TRACE reduces time-anchor drift and improves performance on complex temporal question answering tasks.

Copied to clipboard

Mingchao Liu, Yu Sun, Ruixiao Sun, Xin Dong, Xiang Shen, Hongwei Wang, Hongyu Xiong, Yang Song

LinkAlign: Scalable Schema Linking for Real-World Large-Scale Multi-Database Text-to-SQL (2025.emnlp-main)

Challenge:	Multimodal large language models (MLLMs) capture semantics of short video content but fail to account for policy-specific details.
Approach:	They propose a framework that integrates In-prompt Process Supervision into MLLMs . they propose sequential reasoning over ancillary questions during fine-tuning .
Outcome:	IPS outperforms baseline MLLMs on public and proprietary benchmarks . replacing human-annotated ancillary labels with MLML-generated ones results in performance degradation.

Copied to clipboard

Yihan Wang, Peiyu Liu, Xin Yang

Simulated Misinformation Susceptibility (SMISTS): Enhancing Misinformation Research with Large Language Model Simulations (2024.findings-acl)

Challenge:	Existing Text-to-SQL models fail to address schema linking problems in large-scale multi-database environments.
Approach:	They propose a framework that aims to enable non-expert users to retrieve data effortlessly . they highlight four core errors leading to schema linking failures .
Outcome:	The proposed framework outperforms baselines on all schema linking metrics.

Copied to clipboard

Weicheng Ma, Chunyuan Deng, Aram Moossavi, Lili Wang, Soroush Vosoughi, Diyi Yang

Learning from Emptiness: De-biasing Listwise Rerankers with Content-Agnostic Probability Calibration (2026.acl-short)

Challenge:	Psychological inoculations have shown efficacy in curbing its spread and mitigating its adverse effects at early stages, but their design and optimization typically requires substantial human and financial resources due to the need for repeated experimental trials.
Approach:	They propose to use large language models to simulate participant responses in misinformation studies to mitigate caricatures and stereotypes in the simulations.
Outcome:	The proposed method mitigates caricatures and stereotypes in LLM simulations and enhances response diversity.

Copied to clipboard

Hang Lv, Hongchao Gu, Ruiqing Yang, Liangyue Li, Zulong Chen, Defu Lian, Hao Wang, Enhong Chen

VehicleWorld: A Highly Integrated Multi-Device Environment for Intelligent Vehicle Interaction (2025.findings-emnlp)

Challenge:	Existing methods for listwise reranking exhibit intrinsic position bias . existing methods are constrained by an inherent trade-off between efficiency and flexibility .
Approach:	They propose a training-free framework that mechanically decouples positional bias from ranking decisions.
Outcome:	a training-free framework decouples position bias from ranking decisions . evaluations show it outperforms training-based methods and outperformed expensive methods .

Copied to clipboard

Jie Yang, Jiajun Chen, Zhangyue Yin, Shuo Chen, Yuxin Wang, Yiran Guo, Yuan Li, Yining Zheng, Xuanjing Huang, Xipeng Qiu

Challenge:	Traditional Function Calling (FC) approaches operate statelessly, requiring multiple exploratory calls to build environmental awareness before execution, leading to inefficiency and limited error recovery.
Approach:	They propose a state-based function call approach that maintains explicit system state awareness and implements direct state transitions to achieve target conditions.
Outcome:	The proposed approach outperforms traditional function calling approaches, achieving superior execution accuracy and reduced latency.

MultiFinBen: Benchmarking Large Language Models for Multilingual and Multimodal Financial Application (2026.acl-long)

Copied to clipboard

Xueqing Peng, Lingfei Qian, Yan Wang, Ruoyu Xiang, Yueru He, Yang Ren, Mingyang Jiang, Vincent Jim Zhang, Yuqing Guo, Jeff Zhao, Huan He, Yi Han, Yun Feng, Yuechen Jiang, Yupeng Cao, Haohang Li, Yangyang Yu, Xiaoyu Wang, Penglei Gao, Shengyuan Lin, Keyi Wang, Shanshan Yang, Yilun Zhao, Zhiwei Liu, Peng Lu, Jerry Huang, Suyuchen Wang, Triantafillos Papadopoulos, Polydoros Giannouris, Efstathia Soufleri, Nuo Chen, Zhiyang Deng, Heming Fu, Yijia Zhao, Mingquan Lin, Meikang Qiu, Kaleb E Smith, Arman Cohan, Xiao-Yang Liu, Jimin Huang, Guojun Xiong, Alejandro Lopez-Lira, Xi Chen, Junichi Tsujii, Jian-Yun Nie, Sophia Ananiadou, Qianqian Xie

Tagging-Assisted Generation Model with Encoder and Decoder Supervision for Aspect Sentiment Triplet Extraction (2023.emnlp-main)

Challenge:	Existing evaluations of LLMs in finance are text-only, monolingual, and largely saturated by current models.
Approach:	They propose a multilingual and multimodal benchmark for evaluating LLMs in real financial contexts.
Outcome:	The first expert-annotated multilingual and multimodal benchmark is released . it evaluates 21 leading LLMs and shows they perform better in multilingual settings .

Copied to clipboard

Luo Xianlong, Meng Yang, Yihao Wang

Not All Citations Are Equal:Entropy-Guided Citation Selection for Noise-Resistant Medical LLM (2026.findings-acl)

Challenge:	Recent advances in the ASTE task have been driven by Natural Language Generation-based approaches, but most NLG methods overlook the supervision of the encoder-decoder hidden representations and fail to fully utilize the semantic information provided by the labels.
Approach:	They propose a tagging-assisted generation model with encoder and decoder supervision that enhances the supervision of the encoder-decoder through multiple-perspective tabbing assistance and label semantic representations.
Outcome:	The proposed model enhances the supervision of the encoder and decoder through multiple-perspective tagging assistance and label semantic representations.

Copied to clipboard

Minyu Gao, Hanlin Xiao, Ruoyu Wang, Shuai Yang, YeXuan Zhang, Xin Wu, Xingyu Liu

M3: A Multi-Task Mixed-Objective Learning Framework for Open-Domain Multi-Hop Dense Sentence Retrieval (2024.lrec-main)

Challenge:	Large language models have demonstrated extensive potential in medical applications . however, their practical deployment in healthcare faces significant challenges .
Approach:	They propose a training-free multi-turn reasoning framework and a post-training methodology that provides external knowledge support for large language models.
Outcome:	The proposed framework elicits internal thought, external thought, and fusion thought, with an entropy-based reward that encourages selective citation of beneficial external knowledge while penalizing noisy citations.

Copied to clipboard

Yang Bai, Anthony Colas, Christan Grant, Zhe Wang

Nash-Pruned CredMAS: Dynamic Panel Pruning for VLM-MAS using Nash-based Selection and Doubly-Robust Credits (2026.findings-acl)

Challenge:	Recent research shows that contrastive learning can lead to suboptimal retrieval performance.
Approach:	They propose an advanced recursive Multi-hop dense sentence retrieval system built upon a novel Multi-task Mixed-objective approach for dense text representation learning.
Outcome:	The proposed approach yields state-of-the-art performance on a large-scale open-domain fact verification benchmark dataset, FEVER.

Copied to clipboard

Yijia Fan, Mingyu Liu, Jing Yang, Jian Wang, Keze Wang, Jusheng Zhang

Augmenting Reasoning Capabilities of LLMs with Graph Structures in Knowledge Base Question Answering (2024.findings-emnlp)

Challenge:	Multi-Agent Systems (MAS) are expensive due to static panel designs, where all N agents communicate at every T round.
Approach:	They propose an economic framework that transforms agent selection into a dynamic resource allocation game.
Outcome:	The proposed system reduces token consumption by over 25% on challenging benchmarks while reducing token consumption.

Copied to clipboard

Yuhang Tian, Dandan Song, Zhijing Wu, Changzhi Zhou, Hao Wang, Jun Yang, Jing Xu, Ruanmin Cao, HaoYu Wang

Blinded by Generated Contexts: How Language Models Merge Generated and Retrieved Contexts When Knowledge Conflicts? (2024.acl-long)

Challenge:	Recent work uses Large Language Models (LLMs) for semantic parsing to address Knowledge Base Question Answering tasks.
Approach:	They propose a framework that augments reasoning capabilities of LLMs with Graph Structures in Knowledge Base Question Answering to retrieve question-related graph structures.
Outcome:	The proposed framework outperforms existing methods on GrailQA and WebQSP under the few-shot setting.

Copied to clipboard

Hexiang Tan, Fei Sun, Wanli Yang, Yuanzhuo Wang, Qi Cao, Xueqi Cheng

Pluggable Neural Machine Translation Models via Memory-augmented Adapters (2024.lrec-main)

Challenge:	Recent advances in augmenting Large Language Models (LLMs) with auxiliary information have significantly revolutionized their efficacy in knowledge-intensive tasks.
Approach:	They propose a systematic framework to identify whether LLMs’ responses are attributed to either generated or retrieved contexts.
Outcome:	The proposed framework identifies whether LLMs’ responses are attributed to either generated or retrieved contexts.

Copied to clipboard

Yuzhuang Xu, Shuo Wang, Peng Li, Xuebo Liu, Xiaolong Wang, Weidong Liu, Yang Liu

Improving Language Model Reasoning with Self-motivated Learning (2024.lrec-main)

Challenge:	Recent years, neural machine translation systems are often developed with large-scale parallel data extracted from the Web.
Approach:	They propose a memory-augmented adapter to steer pretrained neural machine translation models in a pluggable manner by combining model representations and retrieved results.
Outcome:	The proposed method outperforms several representative pluggable baselines on style- and domain-specific experiments.

Copied to clipboard

Yunlong Feng, Yang Xu, Libo Qin, Yasheng Wang, Wanxiang Che

Adaptive Gating in Mixture-of-Experts based Language Models (2023.emnlp-main)

Challenge:	Large-scale high-quality training data is important for improving the performance of models.
Approach:	They propose a framework that motivates the model to automatically generate rationales on existing datasets and improves the performance of reasoning through reinforcement learning.
Outcome:	The proposed model outperforms InstructGPT on multiple reasoning datasets and outperformed InstructGPT on other datasets.

Copied to clipboard

Jiamin Li, Qiang Su, Yitao Yang, Yimin Jiang, Cong Wang, Hong Xu

ETC: Encoding Long and Structured Inputs in Transformers (2020.emnlp-main)

Challenge:	Existing models employ a fixed gating network where each token is computed by the same number of experts.
Approach:	They propose a flexible training strategy that allows tokens to be processed by a variable number of experts based on expert probability distribution.
Outcome:	The proposed model reduces training time and inference quality while maintaining sparsity while maintaining inference accuracy.

Copied to clipboard

Joshua Ainslie, Santiago Ontanon, Chris Alberti, Vaclav Cvicek, Zachary Fisher, Philip Pham, Anirudh Ravula, Sumit Sanghai, Qifan Wang, Li Yang

DMSD: Dual-Modal Semantic Disentanglement for Compositional Zero-Shot Learning (2026.findings-acl)

Challenge:	Existing models for natural language processing (NLP) have been challenging to scale attention to longer inputs.
Approach:	They propose an extended Transformer construction architecture that scales attention to longer inputs by combining global-local attention with relative position encodings and a "Contrastive Predictive Coding" objective.
Outcome:	The proposed architecture scales attention to longer inputs and encodes structured inputs.

Copied to clipboard

Pan Yang, Jing Yang, Ruan Xiao li, Yuling Chen, Yuankai Wu, Quan Zhou, Xu Wang

Enhancing Learning-Based Binary Code Similarity Detection Model through Adversarial Training with Multiple Function Variants (2024.findings-emnlp)

Challenge:	Compositional Zero-Shot Learning (CZSL) is a new research paradigm that learns sub-concepts from seen compositions and recognizes unseen novel combinations.
Approach:	They propose a Dual-Modal Semantic Disentanglement framework that integrates visual and textual information to achieve effective sub-concept disentangling.
Outcome:	The proposed framework achieves state-of-the-art performance on three benchmark datasets . it integrates a class-centroid bridge module to guide class centroids toward the textual space .

Copied to clipboard

Lichen Jia, Chenggang Wu, Bowen Tang, Peihua Zhang, Zihan Jiang, Yang Yang, Ning Liu, Jingfeng Zhang, Zhe Wang

Adversarial Preference Learning for Robust LLM Alignment (2025.findings-acl)

Challenge:	Existing Learning-Based Binary Code Similarity Detection (LB-BCSD) methods exhibit lower accuracy in recognizing functions with the same functionality but different implementations.
Approach:	They propose a gradient-guided adversarial attack method based on critical code called FuncFooler which perturbs critical code to generate multiple variants of the same function.
Outcome:	The proposed method increases the accuracy of the current Learning-Based Binary Code Similarity Detection (LB-BCSD) model by 5%-7%.

Copied to clipboard

Yuanfu Wang, Pengyu Wang, Chenyang Xi, Bo Tang, Junyi Zhu, Wenqiang Wei, Chen Chen, Chao Yang, Jingfeng Zhang, Chaochao Lu, Yijun Niu, Keming Mao, Zhiyu Li, Feiyu Xiong, Jie Hu, Mingchuan Yang

Act as you think: Reinforcing Consistent Reasoning in Medical Visual Question Answering (2026.acl-long)

Challenge:	Modern language models rely on Reinforcement Learning from Human Feedback (RLHF) to encourage safe behaviors, but they remain vulnerable to adversarial attacks due to three key limitations: (1) the inefficiency and high cost of human annotation; (2) the vast diversity of potential adversarials; and (3) the risk of feedback bias and reward hacking.
Approach:	They propose an iterative adversarial training method that incorporates three key innovations to address these challenges.
Outcome:	Experiments on Mistral-7B-Instruct-v0.3 show that the proposed method significantly enhances robustness and reduces harmful outputs from 5.88% to 0.43%.

Copied to clipboard

Songtao Jiang, Yuan Wang, Ruizhe Chen, Yan Zhang, Ruilin Luo, Bohan Lei, Yeying Jin, Sibo Song, ZhiBo Yang, Jimeng Sun, Jian Wu, Zuozhu Liu

Aligning Language Models with Real-time Knowledge Editing (2026.acl-long)

Challenge:	Recent advances have improved the accuracy of medical visual question answering (Med-VQA) however, the high stakes nature of the medical domain has precipitated a shift towards interpretability and transparency of reasoning processes.
Approach:	They propose a reinforcement learning from verifiable rewards framework that rewards internal consistency and logical coherence.
Outcome:	The proposed framework rewards internal consistency and logical coherence, and is highly versatile, the authors show.

Copied to clipboard

Chenming Tang, Yutong Yang, Kexue Wang, Yunfang Wu

Well Begun is Half Done: Generator-agnostic Knowledge Pre-Selection for Knowledge-Grounded Dialogue (2023.emnlp-main)

Challenge:	Mainstream knowledge editing methods are static and fail to keep pace with the evolving real-world knowledge.
Approach:	They propose a new paradigm for knowledge editing that integrates edit augmentation and self-adaptive post-alignment inference into CRAFT to improve edit success.
Outcome:	The proposed method shows significant performance gain on CRAFT and traditional datasets compared to existing methods.

Copied to clipboard

Lang Qin, Yao Zhang, Hongru Liang, Jun Wang, Zhenglu Yang

UORA: Uniform Orthogonal Reinitialization Adaptation in Parameter Efficient Fine-Tuning of Large Models (2025.acl-long)

Challenge:	Existing knowledge selection methods are costly to learn and difficult to interpret when errors arise in the generated responses.
Approach:	They propose a generator-agnostic knowledge selection method to select context-related knowledge among different knowledge structures and variable knowledge requirements.
Outcome:	The proposed method can select knowledge accurately in advance and reduce learning, adjustment, and interpretation burden of later models.

Copied to clipboard

Xueyan Zhang, Jinman Zhao, Zhifei Yang, Yibo Zhong, Shuhao Guan, Linbo Cao, Yining Wang

Attention Optimization for Abstractive Document Summarization (D19-1)

Challenge:	Existing methods such as LoRA and VeRA use a low-rank approximation method that reduces the number of trainable parameters without compromising performance.
Approach:	They propose a parameter-efficient fine-tuning approach that leverages a low-rank approximation method that reduces the number of trainable parameters without compromising performance.
Outcome:	The proposed approach outperforms existing methods on GLUE and E2E benchmarks and is effective in instruction-tuning large language models and image classification models.

Copied to clipboard

Min Gui, Junfeng Tian, Rui Wang, Zhenglu Yang

UR2 : Unify RAG and Reasoning through Reinforcement Learning (2026.acl-long)

Challenge:	Abstractive summarization models require attention to reproduce the most salient information.
Approach:	They propose to use local and global variances to augment the vanilla attention model to reproduce the most salient information and avoid repetitions.
Outcome:	The proposed attention refinement unit can reproduce the most salient information and avoid repetitions on CNN/Daily Mail dataset.

Copied to clipboard

Weitao Li, Boran Xiang, Xiaolong Wang, Jingyi Ren, Ante Wang, Zhinan Gou, Weizhi Ma, Yang Liu

Transforming Visual Scene Graphs to Image Captions (2023.acl-long)

Challenge:	Existing attempts to unify large language models are limited to open-domain QA with fixed retrieval settings.
Approach:	They propose a general reinforcement learning framework that dynamically coordinates retrieval and reasoning.
Outcome:	The proposed framework outperforms existing paradigms on open-domain QA, MMLU-Pro, medical, and mathematical reasoning tasks.

Copied to clipboard

Xu Yang, Jiawei Peng, Zihua Wang, Haiyang Xu, Qinghao Ye, Chenliang Li, Songfang Huang, Fei Huang, Zhangzikang Li, Yu Zhang

Toward Optimal LLM Alignments Using Two-Player Games (2025.findings-emnlp)

Challenge:	Existing approaches to generate captions using image captioning are based on multi-head attention (MHA)
Approach:	They propose to transform scene graphs into more descriptive captions by using multi-head attention to build a Graph Neural Network (GNN) . they construct a Mixture-of-Expert (MOE)-based decoder where each expert is built on MHA for discriminating the graph embeddings to generate different kinds of words.
Outcome:	The proposed framework can generate captions from multiple visual features and objects . it is based on a mixture-of-expert (MOE)-based decoder based upon MHA .

Copied to clipboard

Rui Zheng, Hongyi Guo, Zhihan Liu, Xiaoying Zhang, Yuanshun Yao, Xiaojun Xu, Zhaoran Wang, Zhiheng Xi, Tao Gui, Qi Zhang, Xuanjing Huang, Yang Liu, Hang Li

JX4MEI: Multimodal Semantically-Enhanced LLM for Joint Multimodal Emotion-Intent Explanation and Classification (2026.findings-acl)

Challenge:	Alignment of large language models (LLM) is a process that ensures the model’s responses to user prompts align with human intentions and social values.
Approach:	They propose an alignment method based on a two-agent game consisting of an adversarial agent and a defensive agent.
Outcome:	The proposed method improves on a two-agent game with an adversarial agent and a defensive agent.

Copied to clipboard

YiJie Huang, Xiaocui Yang, Shi Feng, Daling Wang, Yifei Zhang, Ning Yuan, Zhuoyue Jia, Wen Zhang

Reconstructing Event Regions for Event Extraction via Graph Attention Networks (2020.aacl-main)

Challenge:	Existing multimodal emotion and intent recognition tasks focus on classification, not rationale and intrinsic connections between these states.
Approach:	They propose a task that requires models to jointly predict emotion and intent while generating natural language explanations for why they co-occur.
Outcome:	The proposed model outperforms baseline models in prediction and explanation generation.

Copied to clipboard

Pei Chen, Hang Yang, Kang Liu, Ruihong Huang, Yubo Chen, Taifeng Wang, Jun Zhao

PASs-MoE: Mitigating Misaligned Co-drift among Router and Experts via Pathway Activation Subspaces for Continual Learning (2026.acl-long)

Challenge:	Existing approaches for event extraction focus on sentence-level event extraction, but they lack a broader view of the document context.
Approach:	They build graphs with candidate event filler extractions enriched by sentential embeddings as nodes and use graph attention networks to identify event regions in a document and aggregate event information.
Outcome:	The proposed method performs well on two languages and shows that it is faster than previous methods.

Copied to clipboard

ZhiYan Hou, Haiyun Guo, Haokai Ma, Yandu Sun, Yonghui Yang, Jinqiao Wang

Challenge:	Existing LoRA-based Mixture-of-Experts (MoE) methods often jointly update the router and experts in an indiscriminate way, causing the router’s preferences to co-drift with experts’ adaptation pathways and exacerbate forgetting.
Approach:	They propose a LoRA-induced subspace that reflects which low-rank pathway directions an input activates in each expert, providing a capability-aligned coordinate system for routing and preservation.
Outcome:	The proposed method outperforms conventional continual learning baselines and MoE–LoRA variants in accuracy and resistance to forgetting, without increasing model parameters.

Answer Quality Aware Aggregation for Extractive QA Crowdsourcing (2022.findings-emnlp)

Copied to clipboard

Peide Zhu, Zhen Wang, Claudia Hauff, Jie Yang, Avishek Anand

When Audio and Text Disagree: Revealing Text Bias in Large Audio-Language Models (2025.emnlp-main)

Challenge:	Existing methods for creating extractive question answering datasets are crowdsourcing, but results are often inconsistent.
Approach:	They propose a method for aggregating answers from different crowd workers that takes into account the relations between the answer, question, and context passage.
Outcome:	The proposed method outperforms baselines by 16% on precision and effectively conduct answer aggregation for extractive question answering task.

Copied to clipboard

Cheng Wang, Gelei Deng, Xianglin Yang, Han Qiu, Tianwei Zhang

Transformer-Based Direct Hidden Markov Model for Machine Translation (2021.acl-srw)

Challenge:	Large Audio-Language Models (LALMs) are augmented with the ability to perceive audio, but their reliability when faced with conflicting inputs remains largely unexplored.
Approach:	They examine how LALMs prioritize information when presented with inconsistent audio-text pairs.
Outcome:	The proposed models display a significant bias toward textual input when presented with inconsistent audio-text pairs.

Copied to clipboard

Weiyue Wang, Zijian Yang, Yingbo Gao, Hermann Ney

Beyond Local vs. External: A Game-Theoretic Framework for Trustworthy Knowledge Acquisition (2026.findings-acl)

Challenge:	Recent studies have found that word alignments produced by the multi-head cross-attention weights are poor.
Approach:	They propose to introduce the hidden Markov model to the transformer architecture and introduce alignment components while keeping the system monolithic.
Outcome:	The proposed model outperforms the baseline model but is slower in training and decoding.

Copied to clipboard

Rujing Yao, Yufei Shi, Yang Wu, Ang Li, Zhuoren Jiang, XiaoFeng Wang, Haixu Tang, Xiaozhong Liu

PrismRAG: Boosting RAG Factuality with Distractor Resilience and Strategized Reasoning (2025.emnlp-industry)

Challenge:	Cloud-hosted Large Language Models (LLMs) offer unmatched reasoning capabilities and dynamic knowledge, yet submitting raw queries to these services can expose sensitive user intent.
Approach:	They propose a framework that formulates the trade-off between knowledge utility and privacy as a strategic game.
Outcome:	The proposed framework reduces intent leakage while maintaining high-fidelity answer quality.

Copied to clipboard

Mohammad Kachuee, Teja Gollapudi, Minseok Kim, Yin Huang, Kai Sun, Xiao Yang, Jiaqi Wang, Nirav Shah, Yue Liu, Aaron Colak, Anuj Kumar, Wen-tau Yih, Xin Luna Dong

Observations and Remedies for Large Language Model Bias in Self-Consuming Performative Loop (2026.acl-long)

Challenge:	Existing methods to improve factuality of large language models (LLMs) rely on human-engineered instructions.
Approach:	They propose a retrieval-augmented generation framework that trains the model with distractor-aware QA pairs mixing gold evidence with subtle distractor passages and instills reasoning-centric habits that make the LLM plan, rationalize, and synthesize without extensive human engineered instructions.
Outcome:	The proposed framework outperforms state-of-the-art solutions across 12 open-book RAG QA benchmarks and is being deployed in production.

Copied to clipboard

Yaxuan Wang, Zhongteng Cai, Yujia Bao, Xueru Zhang, Yang Liu

Streaming Hallucination Detection in Long Chain-of-Thought Reasoning (2026.findings-acl)

Challenge:	Existing synthetic training loops for large language models cause performance drops and induce emerging biases . a large amount of generated content is posted to coding platforms, social media platforms and other platforms on the internet .
Approach:	They propose a self-consuming retraining loop where models are trained on their own outputs . they use a control loop to isolate and analyze feedback-driven bias evolution .
Outcome:	The proposed model increases preference bias and decreases disparate bias.

Copied to clipboard

Haolang Lu, Minghui Pan, Ripeng LI, Guoshun Nan, Jialin Zhuang, Zijie Zhao, Zhongxiang Sun, Kun Wang, Yang Liu

OpenResearcher: Unleashing AI for Accelerated Scientific Research (2024.emnlp-demo)

Challenge:	Long chain-of-thought reasoning improves performance of large language models, yet hallucinations in such settings often emerge subtly and propagate across reasoning steps.
Approach:	They propose to treat step-level hallucination judgments as local observations and introduce a cumulative prefix-level signal that tracks the global evolution of the reasoning state over the entire trajectory.
Outcome:	The proposed method enables streaming hallucination detection in long CoT reasoning, providing real-time, interpretable evidence.

Copied to clipboard

Yuxiang Zheng, Shichao Sun, Lin Qiu, Dongyu Ru, Cheng Jiayang, Xuefeng Li, Jifan Lin, Binjie Wang, Yun Luo, Renjie Pan, Yang Xu, Qingkai Min, Zizhao Zhang, Yiwen Wang, Wenjie Li, Pengfei Liu

InternalInspector I2: Robust Confidence Estimation in LLMs through Internal States (2024.findings-emnlp)

Challenge:	Global scientific publications are growing annually by about 4%-5% (Pinedo et al., 2024).
Approach:	They introduce an AI-assisted platform that answers diverse questions from researchers using Retrieval-Augmented Generation (RAG) they develop various tools to understand queries, search from the scientific literature, filter retrieved information, provide accurate and comprehensive answers, and self-refine answers.
Outcome:	OpenResearcher is built on Retrieval-Augmented Generation (RAG) to integrate Large Language Models (LLMs) with up-to-date, domain-specific knowledge.

Copied to clipboard

Mohammad Beigi, Ying Shen, Runing Yang, Zihao Lin, Qifan Wang, Ankith Mohan, Jianfeng He, Ming Jin, Chang-Tien Lu, Lifu Huang

Chain-of-Thought Reasoning in Tabular Language Models (2023.findings-emnlp)

Challenge:	Large Language Models (LLMs) often struggle with generating reliable outputs, often producing high-confidence inaccuracies known as hallucinations.
Approach:	They propose a framework that leverages contrastive learning on internal states including attention states, feed-forward states, and activation states of all layers to enhance confidence estimation in LLMs.
Outcome:	The framework outperforms existing methods in the hallucination detection benchmark HaluEval and the previous methods at the same time.

Copied to clipboard

Mingyu Zheng, Hao Yang, Wenbin Jiang, Zheng Lin, Yajuan Lyu, Qiaoqiao She, Weiping Wang

Revisiting Model Interpolation for Efficient Reasoning (2026.acl-long)

Challenge:	Existing approaches to extend chain-of-thought reasoning into large language models are not viable in the scenario of privatization deployment or limited resources.
Approach:	They propose a framework that extends chain-of-thought reasoning into tabular language models . framework coordinates two TaLMs responsible for CoT generation and answer inference .
Outcome:	The proposed framework outperforms the state-of-the-art ChatGPT on the TABMWP dataset by 9.55% (82.60%92.15% in accuracy) with less parameters (0.8B).

Copied to clipboard

Taiqiang Wu, Runming Yang, Tao Liu, Jiahao Wang, Ngai Wong

SmartTrim: Adaptive Tokens and Attention Pruning for Efficient Vision-Language Models (2024.lrec-main)

Challenge:	Existing models that interpolate weights of two specialized models can be abused for efficient reasoning.
Approach:	They propose to merge two specialized models and create a model that combines efficiency and efficiency.
Outcome:	The proposed method outperforms existing models on efficiency and effectiveness.

Copied to clipboard

Zekun Wang, Jingchang Chen, Wangchunshu Zhou, Haichao Zhu, Jiafeng Liang, Liping Shan, Ming Liu, Dongliang Xu, Qing Yang, Bing Qin

Faster MoE LLM Inference for Extremely Large Models (2026.findings-acl)

Challenge:	Experimental results show that SmartTrim accelerates the original model by 2-3 times with minimal performance degradation.
Approach:	They propose an adaptive acceleration framework which prunes redundant token representations and attention heads within each layer of the original model.
Outcome:	The proposed framework accelerates the original model by 2-3 times with minimal performance degradation across vision-language tasks.

Copied to clipboard

Haoqi Yang, Luohe Shi, Qiwei Li, Zuchao Li, Ping Wang, Hao Huang, Hai Zhao

RouterHGC: Optimized Router for LLM-based Multi-Agent Systems via Heterogeneous Graph Contrastive Learning (2026.findings-acl)

Challenge:	Existing inference optimizations for coarse-grained Mixture-of-Experts models implicitly assume a fixed activation budget, which is poorly understood.
Approach:	They propose a training-free policy that adapts token-level activation using router confidence and entropy while remaining within the model’s original budget.
Outcome:	The proposed skipping policy can provide substantial throughput gains, but optimal static schedules vary significantly across models and routing mechanisms.

Copied to clipboard

Yitao Xiao, Shaoyong Guo, Guoming Yang, Qingnan Wang, Yinlin Ren, Xuesong Qiu, Qi Feng

Latent Part-of-Speech Sequences for Neural Machine Translation (D19-1)

Challenge:	Large Language Models (LLMs)-driven Multi-Agent Systems (MAS) have demonstrated remarkable scalability and generalizability across complex tasks.
Approach:	They propose a new framework for routing using large language models . they formalize routing as node selection through edge-weight prediction .
Outcome:	The proposed framework outperforms the best single LLM and baselines on five datasets . it achieves 0.80%–6.17% accuracy gains on MATH and HotpotQA while reducing inference cost by 27.40%.

Copied to clipboard

Xuewen Yang, Yingru Liu, Dongliang Xie, Xin Wang, Niranjan Balasubramanian

MUCAR: Benchmarking Multilingual Cross-Modal Ambiguity Resolution for Multimodal Large Language Models (2025.emnlp-main)

Challenge:	Existing methods for learning target side syntactic structure are greedy and only allow them to explore a limited portion of the latent space.
Approach:	They propose a new latent variable model, LaSyn, that captures the co-dependence between syntax and semantics while allowing for effective inference over the latent space.
Outcome:	The proposed model captures the co-dependence between syntax and semantics while allowing for efficient inference over the latent space.

Copied to clipboard

Xiaolong Wang, Zhaolu Kang, Wangyuxuan Zhai, Xinyue Lou, Yunghwei Lai, Ziyue Wang, Yawen Wang, Kaiyu Huang, Yile Wang, Peng Li, Yang Liu

Enhancing LLM-based Search Agents via Contribution Weighted Group Relative Policy Optimization (2026.acl-long)

Challenge:	Existing multimodal benchmarks overlook linguistic and visual ambiguities, authors say . ambiguity resolution between modalities is lacking in multimodal large language models .
Approach:	They propose a benchmark to evaluate multimodal ambiguity resolution across multilingual and cross-modal scenarios.
Outcome:	a new benchmark evaluates multimodal ambiguity resolution across multilingual and cross-modal scenarios . the benchmark shows that MLLMs can resolve ambiguities in image-text alignment . however, existing benchmarks often overlook linguistic and visual ambiguties .

Copied to clipboard

Junzhe Wang, Zhiheng Xi, Yajie Yang, Hao Luo, Shihan Dou, Tao Gui, Qi Zhang

Minimal Distillation Schedule for Extreme Language Model Compression (2024.findings-eacl)

Challenge:	Existing approaches to training large language models suffer from unstable value estimation, whereas outcome supervision struggles with credit assignment due to sparse, trajectory-level rewards.
Approach:	They propose a framework that integrates process supervision into group relative policy optimization.
Outcome:	The proposed framework outperforms standard GRPO on knowledge-intensive benchmarks by 5.0% and 6.3% on Qwen3-1.7B.

Copied to clipboard

Chen Zhang, Yang Yang, Qifan Wang, Jiahao Liu, Jingang Wang, Wei Wu, Dawei Song

DataSciBench: An LLM Agent Benchmark for Data Science (2026.findings-acl)

Challenge:	Existing methods for teacher assistant-based distillation require multiple trials to find the optimal teacher assistant.
Approach:	They propose a method that allows scheduling of an optimal teacher assistant in just one trial . they show that student performance is positively correlated with the scale-performance tradeoff .
Outcome:	The proposed method can select the optimal teacher assistant in just one trial . it can be used to compare performance of student and teacher assistants on GLUE benchmarks.

Copied to clipboard

Dan Zhang, Sining Zhoubian, Min Cai, Fengzu Li, Lekang Yang, Wei Wang, Tianjiao Dong, Ziniu Hu, Jie Tang, Yisong Yue

Challenge:	Existing benchmarks focus on single task, simple evaluation metrics, and readily available ground truth (GT) DataSciBench is built on curated, natural, and challenging prompts with complex evaluation criteria and uncertain GT.
Approach:	They propose a benchmark for evaluating Large Language Models in data science that integrates LLM-based self-consistency and human verification to ensure accuracy.
Outcome:	The proposed framework outperforms open-source models in all metrics and offers rigorous insights into LLM strengths and weaknesses.

Chain of Strategy Optimization Makes Large Language Models Better Emotional Supporter (2025.findings-emnlp)

Copied to clipboard

Weixiang Zhao, Xingyu Sui, Xinyang Han, Yang Deng, Yulin Hu, Jiahe Guo, Libo Qin, Qianyun Du, Shijin Wang, Yanyan Zhao, Bing Qin, Ting Liu

Thinking-Based Non-Thinking: Solving the Reward Hacking Problem in Training Hybrid Reasoning Models via Reinforcement Learning (2026.acl-long)

Challenge:	Existing supervised fine-tuning (SFT) fails to address these issues, as it trains models on single gold-standard responses without modeling nuanced strategy trade-offs.
Approach:	They propose a two-stage framework that optimizes strategy selection preferences at each dialogue turn.
Outcome:	The proposed framework improves strategy selection preferences at each dialogue turn.

Copied to clipboard

Siyuan Gan, Jiaheng Liu, Boyan Wang, Tianpei Yang, Runqing Miao, Yuyao Zhang, Fanyu Meng, Junlan Feng, Linjian Meng, Jing Huo, Yang Gao

Lifting the Curse of Capacity Gap in Distilling Language Models (2023.acl-long)

Challenge:	Existing work on large reasoning models (LRMs) focuses on using reinforcement learning (RL) to train hybrid reasoning models that automatically decide whether to engage in thinking or not based on the complexity of the query.
Approach:	They propose to use reinforcement learning to train hybrid reasoning models that automatically decide whether to engage in thinking or not based on the complexity of the query.
Outcome:	The proposed model reduces token usage by around 50%$ compared to DeepSeek-R1-Distill-Qwen-1.5B/7B and DeepScaleR-1.5b, while significantly improving accuracy.

Copied to clipboard

Chen Zhang, Yang Yang, Jiahao Liu, Jingang Wang, Yunsen Xian, Benyou Wang, Dawei Song

Chase: A Large-Scale and Pragmatic Chinese Dataset for Cross-Database Context-Dependent Text-to-SQL (2021.acl-long)

Challenge:	Existing studies have shown that pretrained language models require a tremendous amount of inference compute to perform.
Approach:	They propose to compress pretrained language models to small ones with a teacher-student paradigm to fill the capacity gap.
Outcome:	The proposed model achieves state-of-the-art performance at small FLOPs compared with competitive baselines.

Copied to clipboard

Jiaqi Guo, Ziliang Si, Yu Wang, Qian Liu, Ming Fan, Jian-Guang Lou, Zijiang Yang, Ting Liu

ReAgent: Reversible Multi-Agent Reasoning for Knowledge-Enhanced Multi-Hop QA (2025.emnlp-main)

Challenge:	XDTS is a cross-database context-dependent text-to-sql problem with wide range of applications.
Approach:	They present a large-scale Chinese dataset for cross-database context-dependent Text-to-SQL . they find that only 35% of questions are context-independent and 28% of SQL queries are easy .
Outcome:	The proposed approach achieves an exact match accuracy of 40% over all questions and 16% over all question sequences.

Copied to clipboard

Zhao Xinjie, Fan Gao, Xingyu Song, Yingjian Chen, Rui Yang, Yanran Fu, Yuyang Wang, Yusuke Iwasawa, Yutaka Matsuo, Irene Li

NUMCoT: Numerals and Units of Measurement in Chain-of-Thought Reasoning using Large Language Models (2024.findings-acl)

Challenge:	Multi-hop question answering (QA) is a central challenge in natural language processing . early mistakes can cause errors and undermine the final result, authors say .
Approach:	They propose a reversible multi-agent reasoning framework that backtracks to earlier valid states when conflicts arise.
Outcome:	Empirical evaluation shows that the framework improves on forward-only benchmarks by 6% . the approach enables agents to backtrack to valid states when conflicts arise .

Copied to clipboard

Ancheng Xu, Minghuan Tan, Lei Wang, Min Yang, Ruifeng Xu

We Need to Talk About Reproducibility in NLP Model Comparison (2023.emnlp-main)

Challenge:	Existing LLMs are not able to handle numerals and units of measurement, but they can be improved by introducing perturbations.
Approach:	They propose to analyze existing LLMs on processing numerals and units of measurement by perturbing their datasets.
Outcome:	The proposed model improves on ancient Chinese arithmetic problems and can handle numeral and measurement conversions.

Copied to clipboard

Yan Xue, Xuefei Cao, Xingli Yang, Yu Wang, Ruibo Wang, Jihong Li

PDR: A Plug-and-Play Positional Decay Framework for LLM Pre-training Data Detection (2026.acl-long)

Challenge:	Existing studies show that standard splits produce low reproducible and unreliable conclusions . reproducibility of empirical experimental conclusions is a problem in NLP domain .
Approach:	They propose to transform the reproducibility of a model comparison into a probabilistic function . they propose to use a regularized corpus splitting strategy to estimate the model's performance .
Outcome:	The proposed estimator achieves a high SNR and significantly increases reproducibility.

Copied to clipboard

Jinhan Liu, Yibo Yang, Ruiying Lu, Piotr Piękos, Yimeng Chen, Peng Wang, Dandan Guo

Alignment with Fill-In-the-Middle for Enhancing Code Generation (2025.emnlp-main)

Challenge:	Existing likelihood-based methods for detecting pretraining data are limited in black-box, zero-shot settings.
Approach:	They propose a training-free and plug-and-play framework that reweights token-level scores to amplify distinct signals from early positions while suppressing noise from later ones.
Outcome:	The proposed framework amplifys signals from early positions while suppressing noise from later positions.

Copied to clipboard

Houxing Ren, Zimu Lu, Weikang Shi, Haotian Hou, Yunqiao Yang, Ke Wang, Aojun Zhou, Junting Pan, Mingjie Zhan, Hongsheng Li

Toward Fast and Accurate Neural Discourse Segmentation (D18-1)

Challenge:	Existing methods for generating test cases with limited training data are not reliable and may be counterproductive.
Approach:	They propose a method that splits code snippets into smaller, granular blocks, creating more diverse DPO pairs from the same test cases.
Outcome:	The proposed approach shows significant improvements in code generation tasks on benchmark datasets such as HumanEval (+), MBPP (+), and APPS.

Copied to clipboard

Yizhong Wang, Sujian Li, Jingfeng Yang

Discourse & Pragmatics

Challenge:	Existing discourse segmenters rely on complicated hand-crafted features and are not practical in actual use.
Approach:	They propose an end-to-end neural segmenter based on BiLSTM-CRF framework that can segment texts fast and accurately using a large corpus.
Outcome:	The proposed model is significantly faster than previous methods while achieving state-of-the-art performance on the RST-DT corpus.

Position Engineering: Boosting Large Language Models through Positional Information Manipulation (2024.emnlp-main)

Copied to clipboard

Zhiyuan He, Huiqiang Jiang, Zilong Wang, Yuqing Yang, Luna Qiu, Lili Qiu

JTAV: Jointly Learning Social Media Content Representation by Fusing Textual, Acoustic, and Visual Features (C18-1)

Challenge:	Recent advances in Large Language Models (LLMs) have demonstrated significant strides towards achieving artificial general intelligence.
Approach:	They propose a technique termed position engineering which alters the positional information in the prompt without modifying the text itself.
Outcome:	The proposed technique significantly improves on the baseline in retrieval-augmented generation and in-context learning scenarios.

Copied to clipboard

Hongru Liang, Haozheng Wang, Jun Wang, Shaodi You, Zhe Sun, Jin-Mao Wei, Zhenglu Yang

Beyond Prompt Engineering: A Systematic Analysis of Prompt Lexical Sensitivity and Its Impacts on Quality (2026.findings-acl)

Challenge:	Existing studies on learning social media content focus on single modal or bi-modal learning, but this approach is non-trivial and challenging because content is multi-modal and involves several types of data, including text, audio, and image.
Approach:	They propose to combine textual, acoustic, and visual information to learn social media content by fusing them jointly.
Outcome:	The proposed model outperforms the state-of-the-art approaches on real-world datasets by a large margin.

Copied to clipboard

Qipeng Xie, Zi Liang, Jiafei Wu, Yufei Chen, Weizheng Wang, Wenao Ma, Zhong Ming, Haiqin Yang, Kaishun Wu

Prompting and Evaluating Large Language Models for Proactive Dialogues: Clarification, Target-guided, and Non-collaboration (2023.findings-emnlp)

Challenge:	Existing studies on prompt engineering have focused on optimizing models for performance under stylistic perturbations.
Approach:	They conduct the first analysis of n-gram token-level mechanisms . they find that higher average performance is inherently associated with lower variance and greater stability.
Outcome:	The proposed model reduces the variance of the generated code by 40% . the proposed model is based on a large-scale dataset of 132,000 prompt variants .

Copied to clipboard

Yang Deng, Lizi Liao, Liang Chen, Hongru Wang, Wenqiang Lei, Tat-Seng Chua

Evolution in Simulation: AI-Agent School with Dual Memory for High-Fidelity Educational Dynamics (2025.findings-emnlp)

Challenge:	Recent studies have shown that ChatGPT has limitations such as failing to ask clarifying questions to ambiguous queries or refusing problematic user requests.
Approach:	They propose a Proactive Chain-of-Thought prompting scheme which augments LLMs with the goal planning capability over descriptive reasoning chains to trigger proactivity.
Outcome:	The proposed scheme augments LLMs with the goal planning capability over descriptive reasoning chains to trigger the proactivity of LLM-based proactive dialogue systems.

Copied to clipboard

Sheng Jin, Haoming Wang, Zhiqi Gao, Yongbo Yang, Bao Chunjia, Chengliang Wang

Challenge:	Large language models (LLMs) based Agents are increasingly pivotal in simulating complex human systems and interactions.
Approach:	They propose an AI-Agent School system that leverages agents for simulating educational dynamics.
Outcome:	The proposed system can simulate complex educational dynamics in simulated schools.

StableToolBench: Towards Stable Large-Scale Benchmarking on Tool Learning of Large Language Models (2024.findings-acl)

Copied to clipboard

Zhicheng Guo, Sijie Cheng, Hao Wang, Shihao Liang, Yujia Qin, Peng Li, Zhiyuan Liu, Maosong Sun, Yang Liu

Emotion Inference in Multi-Turn Conversations with Addressee-Aware Module and Ensemble Strategy (2021.emnlp-main)

Challenge:	Large Language Models (LLMs) have witnessed remarkable advancements in recent years, prompting the exploration of tool learning.
Approach:	They propose a virtual API server and stable evaluation system to assess the stability of large-scale real-time APIs.
Outcome:	The proposed benchmarks demonstrate the stability of the proposed system and its caching system.

Copied to clipboard

Dayu Li, Xiaodan Zhu, Yang Li, Suge Wang, Deyu Li, Jian Liao, Jianxing Zheng

MultiCapCLIP: Auto-Encoding Prompts for Zero-Shot Multilingual Visual Captioning (2023.acl-long)

Challenge:	Empirical studies on three different benchmark conversation datasets demonstrate the effectiveness of the proposed model over several strong baselines.
Approach:	They propose an addressee-aware module to automatically learn whether the participant keeps the historical emotional state or is affected by others in the next upcoming turn.
Outcome:	The proposed model can predict the participant's emotion in the next upcoming turn without knowing the participant’s response yet.

Copied to clipboard

Bang Yang, Fenglin Liu, Xian Wu, Yaowei Wang, Xu Sun, Yuexian Zou

Multimodal Sentiment Detection Based on Multi-channel Graph Neural Networks (2021.acl-long)

Challenge:	Existing methods for supervised visual captioning require large scale of images or videos paired with descriptions in a specific language.
Approach:	They propose a zero-shot approach that generates captions for different scenarios without labeling . they use concept prompts to retrieve concepts and auto-encode them to learn writing styles .
Outcome:	The proposed approach generates captions for different scenarios and languages without labeled vision-caption pairs.

Copied to clipboard

Xiaocui Yang, Shi Feng, Yifei Zhang, Daling Wang

Rethinking Kullback-Leibler Divergence in Knowledge Distillation for Large Language Models (2025.coling-main)

Challenge:	Existing studies only considered the representation of a single image-text post . Fig. 1 shows that multimodal sentiment expressions have global characteristics .
Approach:	They propose a multi-channel Graph Neural Networks with Sentiment-awareness approach for image-text sentiment detection.
Outcome:	The proposed approach is effective for image-text sentiment detection on three publicly available datasets.

Copied to clipboard

Taiqiang Wu, Chaofan Tao, Jiahao Wang, Runming Yang, Zhe Zhao, Ngai Wong

Retrieve-Plan-Generation: An Iterative Planning and Answering Framework for Knowledge-Intensive LLM Generation (2024.emnlp-main)

Challenge:	Large Language Models (LLMs) have been used in Knowledge Distillation (KD) to compress large models.
Approach:	They propose a Kullback-Leiber divergence method which adaptively allocates weights to combine RKL and FKL to reduce the size of Large Language Models (LLMs).
Outcome:	The proposed method outperforms baselines and improves diversity and quality of generated responses.

Copied to clipboard

Yuanjie Lyu, Zihan Niu, Zheyong Xie, Chao Zhang, Tong Xu, Yang Wang, Enhong Chen

MUSEG: Reinforcing Video Temporal Understanding via Timestamp-Aware Multi-Segment Grounding (2026.acl-long)

Challenge:	Large language models (LLMs) often produce factual errors due to limited internal knowledge.
Approach:	They propose a retrieval-augmented generation framework that generates plan tokens to guide subsequent generation.
Outcome:	The proposed framework improves the accuracy of large language models with external knowledge sources.

Copied to clipboard

Fuwen Luo, Shengfeng Lou, Chi Chen, Ziyue Wang, Chenliang Li, Weizhou Shen, Jiyue Guo, Peng Li, Ming Yan, Ji Zhang, Fei Huang, Yang Liu

FineState-Bench: Benchmarking State-Conditioned Grounding for Fine-grained GUI State Setting (2026.findings-acl)

Challenge:	Existing methods for MLLMs struggle with fine-grained temporal reasoning . despite advances in video understanding, current methods struggle with time-sensitive tasks .
Approach:	They propose a time-stamp-aware multi-segment grounding method that enhances temporal understanding by introducing timestamps.
Outcome:	The proposed method outperforms existing methods on time-sensitive tasks and generalizes well across diverse temporal understanding scenarios.

Copied to clipboard

Fengxian Ji, Jingpu Yang, Zirui Song, Yuanxi Wang, Zhexuan Cui, Yuke Li, Qian Jiang, Xiuying Chen

AutoSUIT Bench - Automated Security UnIt Test Benchmark for LLM Coding (2026.findings-acl)

Challenge:	FineState-Bench evaluates whether an agent can correctly ground an instruction to the intended UI control and reach the exact target state.
Approach:	They propose a benchmark that evaluates whether an agent can correctly ground an instruction to the intended UI control and reach the exact target state.
Outcome:	The proposed benchmark evaluates whether an agent can ground an instruction to the intended UI control and reach the exact target state.

Copied to clipboard

Samuel Osebe, Fan Yang, Junyi Li, Yue Gu, Yongxin Wang, Satyapriya Krishna, Kai-Wei Chang, Aram Galstyan, Rahul Gupta, Weitong Ruan

Towards Robust Real-World Spreadsheet Understanding with Multi-Agent Multi-Format Reasoning (2026.acl-long)

Challenge:	Large Language Models (LLMs) are evolving rapidly on code generation tasks.
Approach:	They propose to automate the vulnerability code benchmark creation with iterative auto validation.
Outcome:	The proposed benchmark covers 232 CWE categories across C/C++, Java, and Python languages.

Copied to clipboard

Houxing Ren, Mingjie Zhan, Zimu Lu, Ke Wang, Yunqiao Yang, Haotian Hou, Hongsheng Li

Read Anywhere Pointed: Layout-aware GUI Screen Reading with Tree-of-Lens Grounding (2024.emnlp-main)

Challenge:	Spreadsheets are among the most widely used data formats in real-world applications . existing large language models treat tables as plain text, overlooking layout cues and visual semantics.
Approach:	They propose a two-stage multi-agent framework for spreadsheet understanding that adopts a step-by-step reading and reasoning paradigm.
Outcome:	Extensive experiments on two spreadsheet datasets show the proposed framework outperforms existing methods on Spreadsheet Bench.

Copied to clipboard

Yue Fan, Lei Ding, Ching-Chen Kuo, Shan Jiang, Yang Zhao, Xinze Guan, Jie Yang, Yi Zhang, Xin Wang

Challenge:	Existing models for GUI understanding ignore a key GUI-referring task: screen reading based on user-indicated points.
Approach:	They propose a Tree-of-Lens agent that constructs a Hierarchical Layout Tree based on user input points and a GUI screenshot.
Outcome:	The proposed agent can interpret the Screen Point-and-Read task on mobile, web, and operating systems.

Visual Prompting in LLMs for Enhancing Emotion Recognition (2024.emnlp-main)

Copied to clipboard

Qixuan Zhang, Zhifeng Wang, Dylan Zhang, Wenjia Niu, Sabrina Caldwell, Tom Gedeon, Yang Liu, Zhenyue Qin

SAMem: State-Aware Memory as a Fine-Grained Memory for LLM Agents in Decision-Making (2026.findings-acl)

Challenge:	Existing methods for enhancing in-context emotion classification fail to include spatial relationships between different people and facial features within a single face.
Approach:	They propose a set-of-vision prompting approach that uses spatial information to mark targets precisely.
Outcome:	The proposed approach improves face count and emotion categorization while preserving the enriched image context.

Copied to clipboard

Tong Wang, Pei Xu, Shiyue Cao, Likun Yang, Daipeng Li, Jianbin Jiao, Kaiqi Huang

UCFE: A User-Centric Financial Expertise Benchmark for Large Language Models (2025.findings-naacl)

Challenge:	Existing experiential memory approaches rely on task-level memory, but this lacks the situational alignment required for complex multi-step decision-making.
Approach:	They propose a new fine-grained memory paradigm that aligns memory retrieval with the current state instead of storing and reusing globally shared experiences.
Outcome:	Experiments on complex decision-making benchmarks show that the proposed state-aware memory outperforms existing experiential memory approaches and significantly improves task-solving efficiency.

Copied to clipboard

Yuzhe Yang, Yifei Zhang, Yan Hu, Yilin Guo, Ruoli Gan, Yueru He, Mingcong Lei, Xiao Zhang, Haining Wang, Qianqian Xie, Jimin Huang, Honghai Yu, Benyou Wang

Robust and Minimally Invasive Watermarking for EaaS (2025.findings-acl)

Challenge:	Recent advances in large language models (LLMs) have expanded their potential applications in finance.
Approach:	They propose a framework to evaluate the ability of large language models to handle financial tasks using human expert evaluations and task-specific interactions.
Outcome:	The proposed framework evaluates the ability of large language models to handle complex financial tasks and combines human expert evaluations with dynamic, task-specific interactions to simulate the complexities of evolving financial scenarios.

Copied to clipboard

Zongqi Wang, Baoyuan Wu, Jingyuan Deng, Yujiu Yang

GRACE: Gradient-guided Controllable Retrieval for Augmenting Attribute-based Text Generation (2023.findings-acl)

Challenge:	Existing watermarking methods use a target embedding to create watermarks, but this method results in each embeddable having the same component, making it difficult to remove the watermark.
Approach:	They propose to use embedding watermarks to protect EaaS from model extraction attacks . eaas is vulnerable to model extraction, highlighting the need for copyright protection .
Outcome:	The proposed method can watermark embeddings against model extraction attacks without sacrificing the quality of the embeddables.

Copied to clipboard

Zhihua Wen, Zhiliang Tian, Zhen Huang, Yuxin Yang, Zexin Jian, Changjian Wang, Dongsheng Li

SELF-GUARD: Empower the LLM to Safeguard Itself (2024.naacl-long)

Challenge:	Existing methods for controlling the generation of pre-trained language models infuse domain bias into the generation process, making it difficult to generate out-of-domain texts.
Approach:	They propose a retrieval-augmented generation framework that uses retrieval to generate fluent sentences with high attribute relevance.
Outcome:	The proposed method can generate fluent sentences with high attribute relevance while keeping domain bias out of the model.

Copied to clipboard

Zezhong Wang, Fangkai Yang, Lu Wang, Pu Zhao, Hongru Wang, Liang Chen, Qingwei Lin, Kam-Fai Wong

FrontCoder: Scaling Visual Fidelity in Front-End Code Generation (2026.findings-acl)

Challenge:	Recent studies have investigated methods to improve the safety of large language models (LLMs) safety training involves fine-tuning the LLM with adversarial samples, which activate the LRM’s capabilities against jailbreak.
Approach:	They propose a safety training approach that integrates safety training and safeguards to train the LLM to perform harmfulness detection on its own outputs.
Outcome:	The proposed method reduces harmful output and adds a [harmful] or [harmless] tag to the end of the LLM's response.

Copied to clipboard

Jun Feng, Jian Yang, Wei Zhang, Jing Wang, Keyi Chen, Xiaokun Yang, Weicheng Gu, Yihang Lou, Yan Bai, Xianglong Liu

Auto-Instruct: Automatic Instruction Generation and Ranking for Black-Box Language Models (2023.findings-emnlp)

Challenge:	Existing work on front-end code generation fails to provide visual fidelity and rendering quality for front- end developers.
Approach:	They propose a three-stage pipeline to enhance front-end code generation capabilities in LLMs . they use synthetic data, quality-controlled supervised fine-tuning, and reinforcement learning .
Outcome:	The proposed model achieves competitive performance with frontier models while maintaining generation efficiency.

Copied to clipboard

Zhihan Zhang, Shuohang Wang, Wenhao Yu, Yichong Xu, Dan Iter, Qingkai Zeng, Yang Liu, Chenguang Zhu, Meng Jiang

Beyond Inherent Cognition Biases in LLM-Based Event Forecasting: A Multi-Cognition Agentic Framework (2025.findings-emnlp)

Challenge:	Large language models can perform a wide range of tasks by following natural language instructions without task-specific fine-tuning.
Approach:	They propose a method to automatically improve the quality of LLM instructions . they leverage the generative ability of LMS to generate diverse candidate instructions based on a scoring model trained on 575 existing NLP tasks.
Outcome:	The proposed method surpasses human-written and LLM-generated instructions on 118 out-of-domain tasks.

Copied to clipboard

Zhen Wang, Xi Zhou, Yating Yang, Bo Ma, Lei Wang, Rui Dong, Azmat Anwar

Challenge:	Large Language Models exhibit human-like cognitive biases in event forecasting . a human-curated dataset reveals significant cognitive bias in LLMs .
Approach:	They propose a human-curated dataset to explore LLMs' cognitive biases . they leverage LLM participants to act as multi-cognition event participants .
Outcome:	The proposed framework alleviates cognitive biases in LLMs and offers diverse perspectives.

CoEvolve: Training LLM Agents via Agent-Data Mutual Evolution (2026.acl-long)

Copied to clipboard

Shidong Yang, Ziyu Ma, Tongwen Huang, Yiming Hu, Yong Wang, Xiangxiang Chu

Challenge:	Extensive experiments on AppWorld and BFCL demonstrate consistent and significant improvements over strong base models, yielding absolute gains of 19.43%, 15.58%, and 18.14%, respectively.
Approach:	They propose a framework that extracts feedback signals such as forgetting and uncertainty from rollout trajectories and utilizes them to guide LLM-based task synthesis.
Outcome:	Extensive experiments on AppWorld and BFCL show that the proposed framework improves over strong base models.

Piecing It All Together: Verifying Multi-Hop Multimodal Claims (2025.coling-main)

Copied to clipboard

Haoran Wang, Aman Rangapur, Xiongxiao Xu, Yueqing Liang, Haroon Gharwi, Carl Yang, Kai Shu

Explain the Synth: Interpretable Evaluation of LLM Data Synthesis (2026.acl-long)

Challenge:	Existing claim verification datasets often do not require systems to perform complex reasoning or effectively interpret multimodal evidence.
Approach:	They propose a task that requires models to reason over multiple pieces of evidence . they construct a large-scale dataset comprising 15k multi-hop claims paired with multimodal evidence - generated and refined using large language models with additional input from human feedback.
Outcome:	The proposed method is based on human performance benchmarks and human reasoning hops.

Copied to clipboard

Yue Yang, Fan Yang, Yu Bai, Hao Wang

Vulnerability of Text-to-Image Models to Prompt Template Stealing: A Differential Evolution Approach (2025.findings-acl)

Challenge:	Large language models (LLMs) are increasingly used to generate tabular data.
Approach:	They propose a framework that uses a rule-based model as a shared explanatory language to examine the explanation of real versus synthetic data.
Outcome:	The proposed framework compares the explanatory structure induced by real versus synthetic data.

Copied to clipboard

Yurong Wu, Fangwen Mu, Qiuhong Zhang, Jinjing Zhao, Xinrun Xu, Lingrui Mei, Yang Wu, Lin Shi, Junjie Wang, Zhiming Ding, Yiwei Wang

Mitigating Reversal Curse in Large Language Models via Semantic-aware Permutation Training (2024.findings-acl)

Challenge:	Prompt trading has emerged as a significant intellectual property concern in recent years, where vendors entice users by showcasing sample images before selling prompt templates that can generate similar images.
Approach:	They propose a prompt-stealing benchmark consisting of 50 templates and 450 images organized into Easy and Hard difficulty levels.
Outcome:	The proposed method outperforms baseline methods with an average improvement of over 10%.

Copied to clipboard

Qingyan Guo, Rui Wang, Junliang Guo, Xu Tan, Jiang Bian, Yujiu Yang

Towards Efficient LLM Grounding for Embodied Multi-Agent Collaboration (2025.findings-acl)

Challenge:	Large language models (LLMs) have achieved impressive performance across diverse tasks, but suffer from the "reversal curse" this limitation poses a challenge to the advancement of artificial general intelligence (AGI)
Approach:	They propose to use training data to permute training sentences into entities and feed them into the model.
Outcome:	The proposed method improves the performance of large language models (LLMs) on reversed questions and improves existing models.

Copied to clipboard

Yang Zhang, Shixin Yang, Chenjia Bai, Fei Wu, Xiu Li, Zhen Wang, Xuelong Li

ConQuer: A Framework for Concept-Based Quiz Generation (2025.naacl-srw)

Challenge:	Existing methods for grounding large language models suffer from inefficient querying . Existing approaches that rely on physical verification or self-reflection suffer from excessive querying.
Approach:	They propose a framework that introduces Reinforced Advantage feedback for efficient self-refinement of plans.
Outcome:	The proposed framework surpasses baselines in success rate and significantly decreases interaction steps of agents and query rounds of LLMs.

Copied to clipboard

Yicheng Fu, Zikui Wang, Liuxin Yang, Meiqing Huo, Zhongdongming Dai

Orca: A Few-shot Benchmark for Chinese Conversational Machine Reading Comprehension (2023.findings-emnlp)

Challenge:	Existing concepts-based quiz generation frameworks that leverage external knowledge sources are challenging and labor intensive.
Approach:	They propose a concept-based quiz generation framework that leverages external knowledge sources to assess the quality of the generated quizzes, using LLMs as judges.
Outcome:	The proposed framework shows a 4.8% improvement in evaluation scores and a 77.52% win rate in pairwise comparisons against baseline quiz sets.

Copied to clipboard

Nuo Chen, Hongguang Li, Junqing He, Yinan Bao, Xinshi Lin, Qi Yang, Jianfeng Liu, Ruyi Gan, Jiaxing Zhang, Baoyuan Wang, Jia Li

MGR: Multi-generator Based Rationalization (2023.acl-long)

Challenge:	Existing benchmarks for conversational machine reading comprehension are inconsistent with real scenarios.
Approach:	They propose to use a Chinese CMRC benchmark to evaluate model's generalization ability towards diverse domains by using zero-shot/few-shot settings.
Outcome:	The proposed benchmarks are based on 831 hot-topic driven conversations with 4,742 turns and cover 33 domains.

Copied to clipboard

Wei Liu, Haozhao Wang, Jun Wang, Ruixuan Li, Xinyang Li, YuanKai Zhang, Yang Qiu

Challenge:	Existing approaches to explain NLP models have two key challenges: spurious correlation and degeneration.
Approach:	They propose a rationalization framework using a generator and a predictor to construct a self-explaining NLP model with spurious correlation and degeneration as key challenges.
Outcome:	The proposed method improves the F1 score by 20.9% compared to state-of-the-art methods.

Look Beyond Feeling: Unveiling Latent Needs from Implicit Expressions for Proactive Emotional Support (2025.emnlp-main)

Copied to clipboard

Xing Fu, Haozhen Li, Bichen Wang, Hao Yang, Yanyan Zhao, Bing Qin

AscendKernelGen: LLM-Driven Kernel Generation for NPUs (2026.findings-acl)

Challenge:	Large language models (LLMs) are gaining popularity as scalable tools for mental health support . however, nearly half of individuals do not receive timely support due to limited selfawareness or reluctance to seek help.
Approach:	They propose a proactive emotional support framework that leverages principles of active listening to uncover implicit user needs.
Outcome:	The proposed model elicits implicit emotional needs and delivers empathetic support compared to baselines .

Copied to clipboard

Xinzi Cao, Jianyang Zhai, Pengfei Li, Zhiheng Hu, Cen Yan, null Mubingxu, Guanghuan Fang, Bin She, Jiayu Li, Yihan Su, Dongyang Tao, Feidiao Yang, Chang-Dong Wang, Yutong Lu, Weicheng Xue, Bin Zhou, Yonghong Tian

Challenge:	Neural Processing Units (NPUs) are critical for AI infrastructure, but their development remains a bottleneck due to vendor-specific Domain-Specific Languages (DSLs).
Approach:	They propose a framework for NPU kernel development that bridges the gap in hardware-specific coding . compiler success on complex Level-2 kernels improves from 0% to 95.5%, they say .
Outcome:	The proposed framework bridges the gap in hardware-specific coding, showing a near-zero success rate on complex kernels.

Retrieved Sequence Augmentation for Protein Representation Learning (2024.emnlp-main)

Copied to clipboard

Chang Ma, Haiteng Zhao, Lin Zheng, Jiayi Xin, Qintong Li, Lijun Wu, Zhihong Deng, Yang Lu, Qi Liu, Sheng Wang, Lingpeng Kong

LegalAgentBench: Evaluating LLM Agents in Legal Domain (2025.acl-long)

Challenge:	Using multiple sequence alignments (MSA) to extract evolutionary knowledge is limited.
Approach:	They propose to use multiple sequence alignments to augment protein representations . they propose to employ Retrieved Sequence Augmentation to enhance protein representation learning .
Outcome:	The proposed method surpasses MSA Transformer by 5% in structural and property prediction tasks while being 373 times faster.

Copied to clipboard

Haitao Li, Junjie Chen, Jingli Yang, Qingyao Ai, Wei Jia, Youfeng Liu, Kai Lin, Yueyue Wu, Guozhi Yuan, Yiran Hu, Wuyue Wang, Yiqun Liu, Minlie Huang

Challenge:	Existing general-domain benchmarks do not capture complexity of real-world judicial cognition and decision-making.
Approach:	They propose a benchmark specifically designed to evaluate LLM Agents in the legal domain.
Outcome:	The proposed benchmark includes 17 corpora from real-world legal scenarios and provides 37 tools for interacting with external knowledge.

Discerning and Resolving Knowledge Conflicts through Adaptive Decoding with Contextual Information-Entropy Constraint (2024.findings-acl)

Copied to clipboard

Xiaowei Yuan, Zhao Yang, Yequan Wang, Shengping Liu, Jun Zhao, Kang Liu

CoMave: Contrastive Pre-training with Multi-scale Masking for Attribute Value Extraction (2023.findings-acl)

Challenge:	Existing decoding methods for large language models (LLMs) are specialized in resolving knowledge conflicts and could inadvertently deteriorate performance in absence of conflicts.
Approach:	They propose an adaptive decoding method to discern whether knowledge conflicts occur and resolve them by a contextual information-entropy constraint decoding technique.
Outcome:	The proposed method improves the model’s faithfulness to conflicting context and maintains high performance among non-conflicting contexts.

Copied to clipboard

Xinnan Guo, Wentao Deng, Yongrui Chen, Yang Li, Mengdi Zhou, Guilin Qi, Tianxing Wu, Dong Yang, Liubin Wang, Yong Pan

Linking Adaptive Structure Induction and Neuron Filtering: A Spectral Perspective for Aspect-based Sentiment Analysis (2024.lrec-main)

Challenge:	Existing methods to extract product features from unstructured text still suffer from problems . e-commerce platforms are focusing on multi-scale values, which can be confusing .
Approach:	They propose a pre-training technique to automatically obtain attribute value pairs from product descriptions to aid e-commerce.
Outcome:	The proposed method improves on the existing token-level masking strategy and achieves state-of-the-art on four benchmarks.

Copied to clipboard

Hao Niu, Maoyi Wang, Yun Xiong, Biao Yang, Xing Jia, Zhonglei Guo

FinMRAGBench: A Realistic and Complex Benchmark for Multi-Modal RAG in Financial Document Analysis (2026.findings-acl)

Challenge:	incorporating structure information can improve the performance of aspect-based sentiment analysis.
Approach:	They propose a method to conduct neuron-level manipulations on word representations in the frequency domain.
Outcome:	The proposed method can achieve or come close to state-of-the-art in ABSA.

Copied to clipboard

Shouqing Yang, Qi Zhang, Yuhang Yang, Ruikang Xu, Yuwei Hou, Zhulin Jia, Lirong Gao, Haobo Wang, Jinglei Chen, Jiexiang Wang, Sheng Guo, Bo Zheng, Gang Chen

InfiMM-WebMath-40B: Advancing Multimodal Pre-Training for Enhanced Mathematical Reasoning (2025.findings-emnlp)

Challenge:	Existing benchmarks for realistic financial analysis fail to capture realistic financial situations involving cross-document retrieval, multi-page evidence integration, and diverse analytical tasks.
Approach:	They propose a multi-modal financial RAG benchmark that evaluates large language models in realistic financial analysis settings.
Outcome:	The proposed framework achieves the strongest overall performance across all models.

Copied to clipboard

Xiaotian Han, Yiren Jian, Xuefeng Hu, Haogeng Liu, Yiqi Wang, Qihang Fan, Yuang Ai, Huaibo Huang, Ran He, Zhenheng Yang, Quanzeng You

GrandGuard: Taxonomy, Benchmark, and Safeguards for Elderly-Chatbot Interaction Safety (2026.findings-acl)

Challenge:	InfiMM-WebMath-40B is a dataset of interleaved image-text documents . it consists of 24 million web pages, 85 million image URLs, and 40 billion text tokens .
Approach:	InfiMM-WebMath-40B is a high-quality dataset of interleaved image-text documents . it contains 24 million web pages, 85 million image URLs, and 40 billion text tokens .
Outcome:	InfiMM-WebMath-40B is a high-quality dataset of interleaved image-text documents . it consists of 24 million web pages, 85 million image URLs, and 40 billion text tokens .

Copied to clipboard

Changxuan Fan, Xi Yang, Yueyuan Zheng, Bin Zhou, Yuanping Wang, Wenbin Hu, Huihao Jing, Ki Sen Hung, Dazhao Du, Haoran Li, Janet Hui-wen Hsiao, Yangqiu Song

Efficient Temporal Extrapolation of Multimodal Large Language Models with Temporal Grounding Bridge (2024.emnlp-main)

Challenge:	a survey of older adults shows that many LLMs mishandle elderly-specific contextual risks.
Approach:	They propose a framework to assess elderly-specific contextual risks in LLM interactions . they use a taxonomy to identify 50 fine-grained risk types across mental well-being, financial, medical, toxicity, and privacy domains .
Outcome:	a new framework assesses elderly-specific contextual risks in LLM interactions . it achieves 96.2% and 90.9% unsafe-prompt detection accuracy, respectively .

Copied to clipboard

Yuxuan Wang, Yueqian Wang, Pengfei Wu, Jianxin Liang, Dongyan Zhao, Yang Liu, Zilong Zheng

IM-TQA: A Chinese Table Question Answering Dataset with Implicit and Multi-type Table Structures (2023.acl-long)

Challenge:	despite advances in multimodal large language models, the challenge of interpreting long-form videos remains a challenge . despite advancements in video-language benchmarks, the inefficiency in temporal grounding and limited pre-trained context window size remains .
Approach:	They propose a framework that bootstraps MLLMs with advanced temporal grounding capabilities and broadens their contextual scope.
Outcome:	The proposed framework significantly enhances the temporal capabilities of existing MLLMs.

Copied to clipboard

Mingyu Zheng, Yang Hao, Wenbin Jiang, Zheng Lin, Yajuan Lyu, QiaoQiao She, Weiping Wang

The Agent’s First Day: Benchmarking Learning, Exploration, and Scheduling in the Workplace Scenarios (2026.findings-acl)

Challenge:	Existing benchmarks only evaluate model performance on tables with explicit table structures, which means headers are explicitly annotated and treated as model input during inference.
Approach:	They propose a new Table Question Answering (TQA) dataset with implicit and multi-type table structures that requires the model to understand tables without directly available header annotations.
Outcome:	The proposed framework outperforms baselines on a dataset with implicit and multi-type table structures and can handle multi-table tables including previously neglected complex tables.

Copied to clipboard

Daocheng Fu, Jianbiao Mei, Rong Wu, Xuemeng Yang, Jia Xu, Ding Wang, Pinlong Cai, Yong Liu, Licheng Wen, Botian Shi

Challenge:	Existing research mainly focuses on performance upper bounds in static environments, overlooking stochastic real-world deployment.
Approach:	They propose a dynamic evaluation environment that simulates a "trainee" agent continuously exploring a novel setting.
Outcome:	The proposed model evaluates agents in a dynamic evaluation environment that simulates a "trainee" agent continuously exploring a novel setting.

ODTQA-FoRe: An Open-Domain Tabular Question Answering Dataset for Future Data Forecasting and Reasoning (2026.findings-acl)

Copied to clipboard

Zhensheng Wang, Xiaole Liu, Wenmian Yang, Kun Zhou, Yiquan Zhang, Weijia Jia

FanChuan: A Multilingual and Graph-Structured Benchmark For Parody Detection and Analysis (2025.findings-acl)

Challenge:	Existing tabular question answering systems cannot perform future-oriented numerical prediction . open-domain tabular questions are a popular approach for QA tasks .
Approach:	They propose a task that covers time-series forecasting and forecast-based reasoning scenarios using real estate data.
Outcome:	The proposed framework decomposes the problem into three collaborative roles that synthesize the results to construct a precise and consistent final answer.

Copied to clipboard

Yilun Zheng, Sha Li, Fangkun Wu, Yang Ziyi, Lin Hongchao, Zhichao Hu, Cai Xinjun, Ziming Wang, Jinxuan Chen, Sitao Luan, Jiahao Xu, Lihui Chen

Decoding Echo Chambers: LLM-Powered Simulations Revealing Polarization in Social Networks (2025.coling-main)

Challenge:	Parody is an emerging phenomenon on social media, where individuals imitate a role or position opposite to their own . limited available data and deficient diversity in current datasets hinder study of parody .
Approach:	They build a dataset of parody users and annotated comments from both English and Chinese corpora to test parody detection and comment sentiment analysis.
Outcome:	The proposed datasets provide richer contextual information, which is lacking in existing datasets.

Copied to clipboard

Chenxi Wang, Zongfang Liu, Dequan Yang, Xiuying Chen

Challenge:	Existing studies on social media echo chambers have been limited to numbers and formulas.
Approach:	They propose an LLM-based simulation for the social opinion network to evaluate and counter polarization phenomena.
Outcome:	The proposed model can simulate opinion dynamics and echo chambers using language-based simulations.

Two Languages Are Better than One: Bilingual Enhancement for Chinese Named Entity Recognition (2022.coling-1)

Copied to clipboard

Jinzhong Ning, Zhihao Yang, Zhizheng Wang, Yuanyuan Sun, Hongfei Lin, Jian Wang

Dissecting Fine-Tuning Unlearning in Large Language Models (2024.emnlp-main)

Challenge:	Existing studies focus on internal features of Chinese named entity recognition, but neglect other lingual modalities.
Approach:	They propose a bilingual enhancement module for Chinese Named Entity Recognition . they integrate rich English information into Chinese representation and use it to learn the interaction between bilinguals and dependent information within Chinese.
Outcome:	The proposed model can learn the interaction of bilinguals and dependent information within Chinese.

Copied to clipboard

Yihuai Hong, Yuelin Zou, Lijie Hu, Ziqian Zeng, Di Wang, Haiqin Yang

The CRECIL Corpus: a New Dataset for Extraction of Relations between Characters in Chinese Multi-party Dialogues (2022.lrec-1)

Challenge:	Existing methods for fine-tuning-based unlearning are ineffective at completely erasing model-embedded knowledge, but their true effectiveness remains unclear.
Approach:	They propose to use activation patching and parameter restoration experiments to examine the limitations of fine-tuning-based unlearning methods for erasing harmful, sensitive, or copyrighted information within large language models.
Outcome:	The proposed methods alter the model’s knowledge retrieval process rather than genuinely erasing the problematic knowledge embedded in the model parameters.

Copied to clipboard

Yuru Jiang, Yang Xu, Yuhang Zhan, Weikai He, Yilin Wang, Zixuan Xi, Meiyun Wang, Xinyu Li, Yu Li, Yanchao Yu

Extending Complex Logical Queries on Uncertain Knowledge Graphs (2025.acl-long)

Challenge:	Existing datasets focus on relation extraction between two entities in one sentence, and some focus on cross-sentence relationships.
Approach:	They propose to use a Chinese multi-party dialogue dataset for automatic extraction of dialogue-based character relationships.
Outcome:	The proposed dataset extracts relationships between 140 entities on the CRECIL corpus and another existing relation extraction corpus.

Copied to clipboard

Weizhi Fei, Zihao Wang, Hang Yin, Yang Duan, Yangqiu Song

Where CoT Reasoning Commits: Entropy Traces Identify Interpretable Attention Heads (2026.findings-acl)

Challenge:	Existing studies on logical queries on knowledge graphs overlook the incompleteness of KGs.
Approach:	They propose an ML-based approach to answer soft queries on uncertain knowledge . they propose to use forward inference and backward calibration to avoid catastrophic errors .
Outcome:	The proposed method ensures there are no catastrophic cascading errors while maintaining the same complexity as state-of-the-art inference algorithms for first-order queries.

Copied to clipboard

Tianhe Zhang, Yonghong Deng, Ping Jian, Zhen Yang, Boyang Wang, Xinyue Zhang

Learning Hierarchy-Aware Quaternion Knowledge Graph Embeddings with Representing Relations as 3D Rotations (2022.coling-1)

Challenge:	a growing body of work suggests a disconnect between the generated rationale and the model's actual choice.
Approach:	They propose a mechanism-aware framework that interprets the evolving "choice state" of attention heads during CoT generation . they identify a set of intervention targets and perform Selective Head Fine-Tuning .
Outcome:	The proposed framework interprets the "choice state" of attention heads during CoT generation . it detects two functional behaviors: Steadfast Heads and Wavering Heads .

Copied to clipboard

Jinfa Yang, Xianghua Ying, Yongjie Shi, Xin Tong, Ruibin Wang, Taiyan Chen, Bowei Xing

High-order Joint Constituency and Dependency Parsing (2024.lrec-main)

Challenge:	Existing knowledge graph embedding models fail to model semantic hierarchies . Existing methods fail to understand the semantic hierarchies of knowledge graphs .
Approach:	They propose a model which embeds entities as pure quaternions and constrains the modulus of entities to make them have hierarchical distributions.
Outcome:	The proposed model can encode symmetry/antisymmetry, inversion, composition, multiple relation patterns and learn semantic hierarchies simultaneously.

Copied to clipboard

Yanggan Gu, Yang Hou, Zhefeng Wang, Xinyu Duan, Zhenghua Li

Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QA (2024.emnlp-main)

Challenge:	Syntactic parsing aims to reveal how sentences are syntactically structured.
Approach:	They propose to produce compatible constituency and dependency trees simultaneously for input sentences . they adopt a much more efficient decoding algorithm and explore joint modeling at training phase .
Outcome:	The proposed model significantly improves matching ratio of whole trees compared to separate models . the proposed model adopts a much more efficient decoding algorithm .

Copied to clipboard

Minzheng Wang, Longze Chen, Fu Cheng, Shengyi Liao, Xinghua Zhang, Bingli Wu, Haiyang Yu, Nan Xu, Lei Zhang, Run Luo, Yunshui Li, Min Yang, Fei Huang, Yongbin Li

HighMATH: Evaluating Math Reasoning of Large Language Models in Breadth and Depth (2025.findings-emnlp)

Challenge:	Existing benchmarks for evaluating long-context language models employ irrelevant noise texts to artificially extend the length of test cases, diverging from the real-world scenarios of long-constituency applications.
Approach:	They propose a long-context benchmark, Loong, aligning with realistic scenarios through extended multi-document question answering (QA) .
Outcome:	The proposed model can scale up the context window of large language models to perform in-depth analysis of multiple long documents.

Copied to clipboard

Yan Liu, Minghui Zhang, Bojian Xiong, Yifan Xiao, Yinong Sun, Yating Mei, Longyu Zeng, Jingchao Yang, Yang Wang, Deyi Xiong

Understanding the Repeat Curse in Large Language Models from a Feature Perspective (2025.findings-acl)

Challenge:	a gap in math models' accuracy has been widened with the development of large language models (LLMs) . a new study aims to bridge this gap by evaluating a set of high-level math reasoning models .
Approach:	They propose to evaluate large language models on existing math benchmarks to bridge this gap . they collect 5,293 problems from Chinese senior high school mathematics exams .
Outcome:	The proposed model is based on o1-like models and a high-level model.

Copied to clipboard

Junchi Yao, Shu Yang, Jianhua Xu, Lijie Hu, Mengdi Li, Di Wang

Diversity Collapse in Multi-Agent LLM Systems: Structural Coupling and Collective Failure in Open-Ended Idea Generation (2026.findings-acl)

Challenge:	Large language models suffer from repetitive text generation, a phenomenon we refer to as the ”Repeat Curse”.
Approach:	They propose a method to induce and analyze the Repeat Curse in large language models by using mechanistic interpretability.
Outcome:	The proposed method induces and analyzes the Repeat Curse in large language models using mechanistic interpretability.

Copied to clipboard

Nuo Chen, Yicheng Tong, Yuzhe Yang, Yufei He, Xueyi Zhang, Zou Qingyun, Qian Wang, Bingsheng He

Challenge:	Multi-agent systems (MAS) are increasingly used for open-ended idea generation . when and why collective interaction expands the solution space remains unclear .
Approach:	They propose to study diversity in multi-agent systems across three bottom-up levels: model intelligence, agent cognition, and system dynamics.
Outcome:	The proposed model yields diminishing diversity despite higher quality . the proposed model fails to expand diversity and causes it to collapse .

CLIP-UP: A Simple and Efficient Mixture-of-Experts CLIP Training Recipe with Sparse Upcycling (2025.findings-emnlp)

Copied to clipboard

Xinze Wang, Chen Chen, Yinfei Yang, Hong-You Chen, Bowen Zhang, Aditya Pal, Xiangxin Zhu, Xianzhi Du

AwarenessBench: Assessing Cognitive Capabilities of Language Models (2026.acl-long)

Challenge:	Mixture-of-Experts (MoE) models are crucial for scaling model capacity while controlling inference costs.
Approach:	They propose an alternative training strategy that converts a dense CLIP model into a sparse MoE architecture.
Outcome:	The proposed training strategy outperforms dense models on COCO and Flickr30k benchmarks.

Copied to clipboard

Xiaojian Li, Rongwu Xu, Tianyun Zhang, Yue Wang, Shuo Chen, Qiner Lyu, Briana Zhang, Peiran Yang, Kyle Xue Chen, Haoyuan Shi, Yu Wang, Wei Xu

Gloss-Free End-to-End Sign Language Translation (2023.acl-long)

Challenge:	Language models exhibit increasingly consciousness-like behaviors, requiring a baseline to evaluate their cognitive abilities.
Approach:	They propose a benchmark to assess the cognitive abilities of language models (LMs) they compare 18 state-of-the-art LMs to human models in metacognition, self-awareness, social awareness and situational awareness .
Outcome:	Evaluating 18 state-of-the-art LMs, they find they consistently surpass baselines . but most models fall short in metacognition and self-awareness, the study finds .

Copied to clipboard

Kezhou Lin, Xiaohan Wang, Linchao Zhu, Ke Sun, Bang Zhang, Yi Yang

Are Gender-Neutral Queries Really Gender-Neutral? Mitigating Gender Bias in Image Search (2021.emnlp-main)

Challenge:	a study of sign language translation without gloss annotations focuses on the problem of gloss annotation . gloss annotation is hard to acquire, especially in large quantities, and limits the domain coverage of translation datasets .
Approach:	They propose a gloss-free end-to-end sign language translation framework to solve this problem . gloss annotations are hard to acquire, especially in large quantities, they argue .
Outcome:	The proposed framework improves sign language translation performance on large-scale datasets . gloss annotations are hard to acquire, especially in large quantities .

Copied to clipboard

Jialu Wang, Yang Liu, Xin Wang

E-Verify: A Paradigm Shift to Scalable Embedding-based Factuality Verification (2025.findings-emnlp)

Challenge:	Extensive experiments on MS-COCO and Flickr30K benchmarks show that our methods significantly reduce the gender bias in image search models.
Approach:	They propose a fair sampling method and a feature clipping method to debias image search models.
Outcome:	The proposed methods significantly reduce gender bias in image search models on MS-COCO and Flickr30K benchmarks.

Copied to clipboard

Zeyang Liu, Jingfeng Xue, Xiuqi Yang, Wenbiao Du, Jiarun Fu, Junbao Chen, Wenjie Guo, Yong Wang

TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use (2025.findings-emnlp)

Challenge:	Existing factuality verification methods follow a Decompose-Then-Verify paradigm, which improves granularity but suffers from poor scalability and efficiency.
Approach:	They propose a Decompose-Embed-Interact paradigm that shifts factuality verification from costly text-level reasoning to efficient alignment in embedding space.
Outcome:	The proposed paradigm shifts factuality verification from costly text-level reasoning to efficient alignment in embedding space .

Copied to clipboard

Junjie Ye, Yilong Wu, Sixian Li, Yuming Yang, Zhiheng Xi, Tao Gui, Qi Zhang, Xuanjing Huang, Peng Wang, Zhongchao Shi, Jianping Fan, Zhengyin Du

Can Multimodal LLMs See Materials Clearly? A Multimodal Benchmark on Materials Characterization (2025.findings-emnlp)

Challenge:	a new approach to training large language models (LLMs) overlooks task-specific characteristics in tool use, leading to performance bottlenecks.
Approach:	They propose a task-feature-based framework that mitigates the effects of suboptimal training data . they use a dataset to train large-scale LLMs and a reward mechanism tailored to error categories .
Outcome:	The proposed framework matches or surpasses open- and closed-source LLMs in tool-use performance using only 1,217 training data points.

Copied to clipboard

Zhengzhao Lai, Youbin Zheng, Zhenyang Cai, Haonan Lyu, Jingpu Yang, Hong-Qing Liang, Yan Hu, Benyou Wang

RiskLab: A Controlled Toolkit for Probing Emergent Risks in LLM-Based Multi-Agent Systems (2026.acl-demo)

Challenge:	characterization imaging data is fundamental to acquiring materials information.
Approach:	a team of researchers develop a benchmark for materials characterization imaging data . the goal is to bridge this gap by addressing 1,500 questions that require expert-level expertise.
Outcome:	a new benchmark for materials characterization imaging data is presented . the benchmark reveals that MLLMs perform poorly when addressing higher-level questions .

Copied to clipboard

Yu Jiang, Wenjie Wang, Yue Huang, Yanbo Wang, Zhenhong Zhou, Xiuying Chen, Yang Liu, Pin-Yu Chen, Wei Wang, Xiangliang Zhang

Text Style Transfer Back-Translation (2023.acl-long)

Challenge:	Recent advances in large language model (LLM) agents have accelerated deployment of multi-agent systems for complex tasks.
Approach:	They propose an open-source toolkit for instantiating, probing, and measuring emergent risks in LLM-based multi-agent systems under controlled conditions.
Outcome:	The proposed toolkit is based on a structured topology–environment–protocol–agent–task quintuple enabling reproducible studies of how communication structure, coordination mechanisms, and incentives shape system-level risks.

Copied to clipboard

Daimeng Wei, Zhanglin Wu, Hengchao Shang, Zongyao Li, Minghan Wang, Jiaxin Guo, Xiaoyu Chen, Zhengzhe Yu, Hao Yang

M3TQA: Massively Multilingual Multitask Table Question Answering (2026.findings-acl)

Challenge:	Current methods require large amount of bilingual training data, which is challenging and sometimes impossible task.
Approach:	They propose a method to modify the style of inputs by modifying the source side of BT data.
Outcome:	The proposed method significantly improves translation quality against popular BT benchmarks on high-resource and low-resourced language pairs.

Copied to clipboard

Daixin Shu, Jian Yang, Zhenhe Wu, Xianjie Wu, Xianfu Cheng, Guan Xiangyuan, Yanghai Wang, Pengfei Wu, Tingyang Yang, Hualei Zhu, Wei Zhang, Ge Zhang, Jiaheng Liu, Zhoujun Li

Proxy-Driven Robust Multimodal Sentiment Analysis with Incomplete Data (2025.acl-long)

Challenge:	Existing multilingual table benchmarks suffer from geolinguistic imbalance - overrepresenting certain languages and lacking sufficient scale for rigorous cross-lingual analysis.
Approach:	They propose a framework for massively multilingual table question answering that includes tables expanded to 97 languages from Chinese and English sources.
Outcome:	Experiments on state-of-the-art LLMs show that synthetically generated training data significantly boosts performance, especially for low-resource languages.

Copied to clipboard

Aoqiang Zhu, Min Hu, Xiaohua Wang, Jiaoyun Yang, Yiming Tang, Ning An

100-LongBench: Are de facto Long-Context Benchmarks Literally Evaluating Long-Context Ability? (2025.findings-acl)

Challenge:	Existing studies focus on optimizing model structures to handle uncertain missingness, but models still face challenges when dealing with uncertain missing data.
Approach:	They propose a data-centric robust multimodal sentiment analysis method, Proxy-Driven Robust Multimodal Fusion, which maps unimodal data to the latent space of Gaussian distributions to capture core features and structure.
Outcome:	The proposed method outperforms existing models in noise resistance and achieves state-of-the-art performance on multiple benchmark datasets.

Copied to clipboard

Van Yang, Hongye Jin, Shaochen Zhong, Song Jiang, Qifan Wang, Vipin Chaudhary, Xiaotian Han

Challenge:	Existing benchmarks for long-context capability are too synthetic and do not represent the real world usage of LLMs.
Approach:	They propose a length-controllable, real-life reflective benchmark that disentangles baseline knowledge from long-context capabilities.
Outcome:	Experiments show that the proposed benchmarks disentangle baseline knowledge from long-context capabilities.

From Query to Logic: Ontology-Driven Multi-Hop Reasoning in LLMs (2026.findings-acl)

Copied to clipboard

Haonan Bian, Yutao Qi, Rui Yang, Yuanxi Che, Jiaqian Wang, Heming Xia, Ranran Zhen

GroupRank: A Groupwise Paradigm for Effective and Efficient Passage Reranking with LLMs (2026.findings-acl)

Challenge:	Large Language Models (LLMs) exhibit limitations in complex multi-hop question answering tasks that necessitate non-linear, structured reasoning.
Approach:	They propose an ontology-driven reasoning and chain framework that combines LLMs’ generative capabilities with the structural benefits of knowledge graphs.
Outcome:	Extensive experiments across a diverse set of models and standard MQA benchmarks demonstrate that the proposed framework achieves competitive performance while producing more interpretable reasoning chains.

Copied to clipboard

Meixiu Long, Duolin Sun, Dan Yang, Yihan Jiao, Lei Liu, Jiahai Wang, Binbin Hu, Yue Shen, Jie Feng, Zhehao Tan, Junjie Wang, Lianzhen Zhong, Jian Wang, Peng Wei, Jinjie Gu

MMLU-ProX: A Multilingual Benchmark for Advanced Large Language Model Evaluation (2025.emnlp-main)

Challenge:	Existing rankers excel in lexical-matching scenarios, while they struggle with complex queries requiring deep reasoning.
Approach:	They propose a new paradigm that balances flexibility and context awareness to unlock the full potential of groupwise reranking.
Outcome:	The proposed approach achieves a state-of-the-art 65.2 NDCG@10 on BRIGHT and surpasses baselines by 2.1 points on R2MED while delivering a 6.4 inference speedup.

Copied to clipboard

Weihao Xuan, Rui Yang, Heli Qi, Qingcheng Zeng, Yunze Xiao, Aosong Feng, Dairui Liu, Yun Xing, Junjue Wang, Fan Gao, Jinghui Lu, Yuang Jiang, Huitao Li, Xin Li, Kunyu Yu, Ruihai Dong, Shangding Gu, Yuekang Li, Xiaofei Xie, Felix Juefei-Xu, Foutse Khomh, Osamu Yoshie, Qingyu Chen, Douglas Teodoro, Nan Liu, Randy Goebel, Lei Ma, Edison Marrese-Taylor, Shijian Lu, Yusuke Iwasawa, Yutaka Matsuo, Irene Li

When LLMs Read Tables Carelessly: Measuring and Reducing Data Referencing Errors (2026.acl-long)

Challenge:	Existing large language model evaluation benchmarks focus on English, while current multilingual tasks lack parallel questions that specifically assess cross-lingual reasoning abilities.
Approach:	They propose a comprehensive benchmark covering 29 languages, built on an English benchmark.
Outcome:	The MMLU-ProX is a comprehensive benchmark covering 29 languages, built on an English benchmark.

Copied to clipboard

Yuqing Yang, Qi Zhu, Zhen Han, Boran Han, Zhengyuan Shen, Shuai Wang, Vassilis N. Ioannidis, Huzefa Rangwala

The Music Maestro or The Musically Challenged, A Massive Music Evaluation Benchmark for Large Language Models (2024.findings-acl)

Challenge:	Large language models (LLMs) perform well on table tasks, but they still make data referencing errors (DREs) prior studies have only offered limited, small-scale analyses.
Approach:	They propose inference-time strategies and lightweight critics to mitigate data referencing errors.
Outcome:	The proposed model achieves an average F1 score of 78.2% in detecting both in-distribution and out-of-difference DREs and assists inference for larger models.

Copied to clipboard

Jiajia Li, Lu Yang, Mingni Tang, Chenchong Chenchong, Zuchao Li, Ping Wang, Hai Zhao

m3P: Towards Multimodal Multilingual Translation with Multimodal Prompt (2024.lrec-main)

Challenge:	Existing benchmarks to evaluate LLMs' capabilities are inadequate for assessing their musical capabilities.
Approach:	They propose to use a large-scale music benchmark specifically designed to evaluate the music-related capabilities of large language models (LLMs).
Outcome:	The proposed framework evaluates 16 large language models in the domain of music.

Copied to clipboard

Jian Yang, Hongcheng Guo, Yuwei Yin, Jiaqi Bai, Bing Wang, Jiaheng Liu, Xinnian Liang, LinZheng Chai, Liqun Yang, Zhoujun Li

CodeContests+: High-Quality Test Case Generation for Competitive Programming (2025.findings-emnlp)

Challenge:	Existing multimodal neural machine translation models focus on bilingual translation, but experimental results show that they outperform the text-only baselines and multilingual multimodal methods by a large margin.
Approach:	They propose a framework to leverage the multimodal prompt to guide the Multimodal Multilingual Neural Machine Translation (m3P) this framework aligns the representations of different languages with the same meaning and generates the conditional vision-language memory for translation.
Outcome:	The proposed framework outperforms previous text-only baselines and multilingual multimodal methods by a large margin.

Copied to clipboard

Zihan Wang, Siyao Liu, Yang Sun, Ming Ding, Hongyan Li

Collective Human Opinions in Semantic Textual Similarity (2023.tacl-1)

Challenge:	Competitive programming has become a key task for training and evaluating large language models . but test cases of competitive programming problems are often difficult to obtain .
Approach:	They propose an LLM-based agent system that creates high-quality test cases for competitive programming problems.
Outcome:	The proposed system improves code tests on a CodeContests dataset with pass/fail labels.

Copied to clipboard

Yuxia Wang, Shimin Tao, Ning Xie, Hao Yang, Timothy Baldwin, Karin Verspoor

Experiential Co-Learning of Software-Developing Agents (2024.acl-long)

Challenge:	Existing benchmarks for semantic textual similarity (STS) use averaged human ratings as gold standard.
Approach:	They propose to use a Chinese sentence-to-sentence dataset to study collective human opinions in semantic textual similarity (STS) neither a scalar nor a single Gaussian fits a set of observed judgments adequately, they argue .
Outcome:	The proposed dataset does not capture disagreements on individual instances, but rather the confidence over the aggregate dataset.

Copied to clipboard

Chen Qian, Yufan Dang, Jiahao Li, Wei Liu, Zihao Xie, YiFei Wang, Weize Chen, Cheng Yang, Xin Cong, Xiaoyin Che, Zhiyuan Liu, Maosong Sun

Enhancing Multilingual Reasoning via Steerable Model Merging (2026.findings-acl)

Challenge:	Recent advances in large language models (LLMs) have brought significant changes to various domains, especially through autonomous agents.
Approach:	They propose a framework that lets agents learn shortcuts from their past tasks and use them for future task execution.
Outcome:	The proposed framework enables agents to tackle unseen software-developing tasks more effectively.

Copied to clipboard

Zhuoran Li, Rui Xu, Jian Yang, Junnan Liu, Zhijun Chen, Qianren Mao, Hongcheng Guo, Jiaheng Liu, Likang Xiao, Ming LI, Xiaojie Wang

V-Oracle: Making Progressive Reasoning in Deciphering Oracle Bones for You and Me (2025.acl-long)

Challenge:	Model merging is an effective technique for composing the capabilities of a multilingual model and a reasoning model.
Approach:	They propose a model merging framework that modulates the contribution of each source model.
Outcome:	Experiments show that the proposed model merging framework outperforms strong baselines on multilingual reasoning benchmarks across 21 different languages.

Copied to clipboard

Runqi Qiao, Qiuna Tan, Guanting Dong, MinhuiWu MinhuiWu, Jiapeng Wang, YiFan Zhang, Zhuoma GongQue, Chong Sun, Yida Xu, Yadong Xue, Ye Tian, Zhimin Bao, Lan Yang, Chen Li, Honggang Zhang

COIG-P: A High-Quality and Large-Scale Chinese Preference Dataset for Alignment with Human Values (2026.findings-eacl)

Challenge:	Deciphering oracle bone scripts using AI technology is not an overnight task due to the evolution of written language over millennia.
Approach:	They propose a framework that utilizes Large Multi-modal Models (LMMs) for interpreting Oracle Bone Script (OBS).
Outcome:	The proposed framework provides quantitative analyses and superior deciphering capability.

Copied to clipboard

Siwei Wu, JinCheng Ren, Xeron Du, Shuyue Guo, Xingwei Qu, Yiming Liang, Jie Liu, Yunwen Li, Tyler Loakman, Tianyu Zheng, Boyu Feng, Huaqing Yuan, Zili Wang, Jiaheng Liu, Wenhao Huang, Chenglin Cai, Haoran Que, Jian Yang, Yuelin Bai, Zekun Moore Wang, Zhouliang Yu, Qunshu Lin, Ding Pan, Yuchen Eleanor Jiang, Tiannan Wang, Wangchunshu Zhou, Shenzhi Wang, Xingyuan Bu, Minghao Liu, Guoyin Wang, Ge Zhang, Chenghua Lin

UniEX: An Effective and Efficient Framework for Unified Information Extraction via a Span-extractive Perspective (2023.acl-long)

Challenge:	Existing Chinese preference datasets suffer from limited scale, restricted domain coverage, and insufficiently rigorous data validation.
Approach:	They propose an LLM-based data annotation pipeline with no human intervention to annotate Chinese preference datasets.
Outcome:	The proposed pipeline outperforms existing Chinese preference datasets on AlignBench and Chinese Reward Benchmark.

Copied to clipboard

Yang Ping, JunYu Lu, Ruyi Gan, Junjie Wang, Yuxiang Zhang, Pingjian Zhang, Jiaxing Zhang

CTR-Guided Generative Query Suggestion in Conversational Search (2025.emnlp-industry)

Challenge:	Existing approaches for information extraction (IE) are limited by the number of subtasks and the isolation of the subtask.
Approach:	They propose a new paradigm for universal information extraction that is compatible with any schema format and applicable to a list of IE tasks.
Outcome:	The proposed framework outperforms generative universal IE models on 14 benchmarks with the supervised setting and the state-of-the-art performance in low-resource scenarios.

Copied to clipboard

Erxue Min, Hsiu-Yuan Huang, Xihong Yang, Min Yang, Xin Jia, Yunfang Wu, Hengyi Cai, Junfeng Wang, Shuaiqiang Wang, Dawei Yin

UniCoder: Scaling Code Large Language Model via Universal Code (2024.acl-long)

Challenge:	Generating effective query suggestions requires aligning model outputs with user click preferences.
Approach:	They propose a generative framework that leverages click modeling to denoise implicit feedback and enables reliable preference optimization for improving real-world user engagement.
Outcome:	The proposed framework outperforms strong baselines in CTR, relevance, diversity and diversity.

Copied to clipboard

Tao Sun, Linzheng Chai, Jian Yang, Yuwei Yin, Hongcheng Guo, Jiaheng Liu, Bing Wang, Liqun Yang, Zhoujun Li

Persuasion for Good: Towards a Personalized Persuasive Dialogue System for Social Good (P19-1)

Challenge:	Experimental results show that UniCoder with the universal code significantly outperforms the previous prompting methods by a large margin.
Approach:	They introduce the universal code (UniCode) as the intermediate representation of algorithm steps using conventions of programming languages.
Outcome:	The proposed model outperforms previous prompting methods by a large margin . the proposed model is based on a dataset of natural-language questions and code solutions .

Copied to clipboard

Xuewei Wang, Weiyan Shi, Richard Kim, Yoojung Oh, Sijia Yang, Jingwen Zhang, Zhou Yu

Improving Neural Machine Translation with Conditional Sequence Generative Adversarial Nets (N18-1)

Challenge:	Persuasion agents are a form of communication that can be used to change people's opinions and actions for social good.
Approach:	They designed an online persuasion task where one participant was asked to persult the other to donate to a specific charity.
Outcome:	The proposed system could change people's opinions and actions for social good.

Copied to clipboard

Zhen Yang, Wei Chen, Feng Wang, Bo Xu

METNet: A Mutual Enhanced Transformation Network for Aspect-based Sentiment Analysis (2020.coling-main)

Challenge:	Experimental results show that the proposed model consistently outperforms the traditional RNNSearch and the newly emerged state-of-the-art Transformer on English-German and Chinese-English translation tasks.
Approach:	They propose an approach for applying GANs to NMT by building a conditional sequence generative adversarial net with two adversarials.
Outcome:	The proposed model outperforms the existing RNNSearch and Transformer on English-German and Chinese-English translation tasks.

Copied to clipboard

Bin Jiang, Jing Hou, Wanyue Zhou, Chao Yang, Shihan Wang, Liang Pang

XMoE: Sparse Models with Fine-grained and Adaptive Expert Selection (2024.findings-acl)

Challenge:	Existing methods for learning complex sentences with multiple aspects are ill-equipped to learn complex sentences .
Approach:	They propose a mutual enhanced transformation network for the ABSA task . it improves representation learning of the aspect with contextual semantic features .
Outcome:	The proposed model improves representation learning of the aspect with contextual semantic features, giving the aspect more abundant information.

Copied to clipboard

Yuanhang Yang, Shiyi Qi, Wenchao Gu, Chaozheng Wang, Cuiyun Gao, Zenglin Xu

EmotionTalk: An Interactive Chinese Multimodal Emotion Dataset With Rich Annotations (2026.findings-acl)

Challenge:	XMoE leverages small experts and a threshold-based router to selectively engage only essential parameters.
Approach:	They propose a novel MoE that leverages small experts to selectively engage only essential parameters.
Outcome:	The proposed model can reduce computation load at MoE layers by over 50% without sacrificing performance.

Copied to clipboard

Haoqin Sun, Jinghua Zhao, Xuechen Wang, Shiwan Zhao, Jiaming Zhou, Hui Wang, Xi Yang, Yequan Wang, Yonghua Lin

SMedBERT: A Knowledge-Enhanced Pre-trained Language Model with Structured Semantics for Medical Text Mining (2021.acl-long)

Challenge:	Existing datasets face issues such as low quality, limited scale, and incomplete modalities, hindering model performance.
Approach:	They propose to use Chinese multimodal datasets to capture authentic emotional interplay from 19 professional actors.
Outcome:	The EmotionTalk dataset spans 23.6 hours of dyadic conversations across diverse scenarios.

Copied to clipboard

Taolin Zhang, Zerui Cai, Chengyu Wang, Minghui Qiu, Bite Yang, Xiaofeng He

SeDev: Structured Semantic Exploration for LLM-Driven Code Generation (2026.acl-long)

Challenge:	Existing knowledge-based PLMs are based on linked-entity information, but they only use linked-enemy information as auxiliary information.
Approach:	They propose to integrate semantic knowledge from neighbours of linked-entity into a medical PLM that integrates heterogeneous-entities into the homogeneously neighbouring entity structure.
Outcome:	Experiments show that SMedBERT outperforms baselines in knowledge-intensive Chinese medical tasks.

Copied to clipboard

Ronghui Yang, Jie Liu, Jiajie Zeng, Jiexin Wang, Jiuchuan Jiang, Bo An, Yi Cai, Mengchen Zhao

Long-tailed Extreme Multi-label Text Classification by the Retrieval of Generated Pseudo Label Descriptions (2023.findings-eacl)

Challenge:	Large Language Models (LLMs) have shown remarkable capabilities in automating code generation, but they suffer from insufficient exploration of the vast solution space.
Approach:	They propose a large-scale LLM-driven code generation framework that efficiently finds high-quality solutions in only a few iterations.
Outcome:	The proposed framework outperforms baselines while maintaining reasonable time and computational costs.

Copied to clipboard

Ruohong Zhang, Yau-Shian Wang, Yiming Yang, Donghan Yu, Tom Vu, Likun Lei

Improving Autoformalization Using Direct Dependency Retrieval (2026.acl-long)

Challenge:	Extreme Multi-label text classification (XMTC) is a tough challenge due to the sheer size of the label spaces and the severe data scarcity problem associated with the long tail of rare labels in highly skewed distributions.
Approach:	They propose to use a trained bag-of-words classifier to generate pseudo label descriptions from a training bag- of-word classifier.
Outcome:	The proposed approach outperforms the existing models in the tail label prediction problem and achieves state-of-the-art (SOTA) performance on XMTC benchmark datasets.

Copied to clipboard

Shaoqi Wang, Lu Yu, Siwei Lou, Feng Yan, Chunjie Yang, Qing Cui, Jun Zhou

Evaluating Mathematical Reasoning of Large Language Models: A Focus on Error Identification and Correction (2024.findings-acl)

Challenge:	Existing methods for hallucinate formal dependencies lack scalability and precision to leverage ever-growing public datasets.
Approach:	They propose a retrieval-augmented framework based on Direct Dependency Retrieval to generate formal dependencies from natural-language mathematical descriptions and verify their existence via an efficient Suffix Array Check (SAC).
Outcome:	The proposed framework outperforms state-of-the-art methods in retrieval precision and recall and can be used to validate formal representations in a public dataset.

Copied to clipboard

Xiaoyuan Li, Wenjie Wang, Moxin Li, Junrong Guo, Yang Zhang, Fuli Feng

Document-level Event Extraction via Parallel Prediction Networks (2021.acl-long)

Challenge:	Existing evaluations focus on problem-solving from examiner perspective, overlooking a dual perspective of examiner regarding error identification and correction.
Approach:	They propose to use an annotated dataset to evaluate large language models from the examiner perspective and to use diverse prompts to evaluate eleven representative LLMs.
Outcome:	The proposed model outperforms all models while LLaMA-2-7B has comparable abilities to closed-source models GPT-3.5 and Gemini Pro.

Copied to clipboard

Hang Yang, Dianbo Sui, Yubo Chen, Kang Liu, Jun Zhao, Taifeng Wang

Prompt Tuning for Unified Multimodal Pretrained Models (2023.findings-acl)

Challenge:	Document-level event extraction (DEE) is indispensable when events are described throughout a document.
Approach:	They propose a document-level event extraction model that can extract structured events from a text in parallel.
Outcome:	The proposed model outperforms current state-of-the-art methods on a document-level event extraction task.

Copied to clipboard

Hao Yang, Junyang Lin, An Yang, Peng Wang, Chang Zhou

Token-level Proximal Policy Optimization for Query Generation (2025.emnlp-main)

Challenge:	Prompt tuning has demonstrated success in natural language pretraining and even vision pretraining.
Approach:	They propose to apply prompt tuning to a unified sequence-to-sequence pretrained model by adding a sequence of learnable embeddings to each layer and finetuning the pretrained models on downstream tasks.
Outcome:	The proposed method outperforms other parameter-efficient tuning methods on multimodal models and is robust against adversarial attacks.

Copied to clipboard

Yichen Ouyang, Lu Wang, Fangkai Yang, Pu Zhao, Chenghua Huang, Jianfeng Liu, Bochen Pang, Yaming Yang, Yuefeng Zhan, Hao Sun, Qingwei Lin, Saravan Rajmohan, Weiwei Deng, Dongmei Zhang, Feng Sun

MetaFill: Text Infilling for Meta-Path Generation on Heterogeneous Information Networks (2022.emnlp-main)

Challenge:	Large Language Models (LLMs) have improved search engines and recommendation systems through their text understanding capabilities.
Approach:	They propose a token-level proximal policy optimization approach to empower LLMs to perform better in query generation through fine-tuning.
Outcome:	The proposed approach outperforms existing LLMs on an open-source and industrial dataset.

Copied to clipboard

Zequn Liu, Kefei Duan, Junwei Yang, Hanwen Xu, Ming Zhang, Sheng Wang

Enhanced Visual Instruction Tuning with Synthesized Image-Dialogue Data (2024.findings-acl)

Challenge:	Existing meta-path generation methods cannot fully exploit rich textual information in HINs.
Approach:	They propose a text-infilling-based approach to generate meta-paths from textual information in HINs.
Outcome:	The proposed approach can classify edges in the zero-shot setting, where existing methods cannot generate meta-paths.

Copied to clipboard

Yanda Li, Chi Zhang, Gang Yu, Wanqi Yang, Zhibin Wang, Bin Fu, Guosheng Lin, Chunhua Shen, Ling Chen, Yunchao Wei

End-to-End Learnable Psychiatric Scale Guided Risky Post Screening for Depression Detection on Social Media (2025.emnlp-main)

Challenge:	OpenAI's GPT-4 has demonstrated remarkable multimodal capabilities, but specific mechanics of GPT4 remain unknown.
Approach:	They propose a data collection methodology that synchronously synthesizes images and dialogues for visual instruction tuning.
Outcome:	The proposed method improves on ten commonly assessed models and provides greater flexibility compared to existing methods.

Copied to clipboard

Bichen Wang, Yuzhe Zi, Yixin Sun, Hao Yang, Yanyan Zhao, Bing Qin

Challenge:	Existing methods to detect depression from social media posting history are limited by frozen screening models and lack of learning.
Approach:	They propose to use a frozen screening model to train a risky post detection model with psychiatric scales to enable a learnable end-to-end learning process.
Outcome:	The proposed model outperforms several strong baseline methods and qualitative analysis confirms that it better captures users’ mental states than others.

Plug-and-Play Data Module for Code RL: Adaptive Ambiguity Replay (2026.findings-acl)

Copied to clipboard

Jianqing Zhang, Wei Xia, Zhezheng Hao, Hong Wang, Hande Dong, Qiang Lin, Yang Liu, Jian Cao, Qiang Yang

Prejudge-Before-Think: Enhancing Large Language Models at Test-Time by Process Prejudge Reasoning (2025.findings-emnlp)

Challenge:	Existing approaches to reinforcement learning (RL) rely on static, in-epoch metrics that overlook training dynamics, often introducing low-utility or outdated data.
Approach:	They propose a plug-and-play module that prioritizes cross-epoch ambiguous samples to neutralize the noise from stale experiences.
Outcome:	Extensive experiments on nine LLMs show that Adaptive Ambiguity Replay outperforms state-of-the-art baselines on real-world code editing tasks.

Copied to clipboard

Jianing Wang, Jin Jiang, Yang Liu, Mengdi Zhang, Xunliang Cai

MM-AVS: A Full-Scale Dataset for Multi-modal Summarization (2021.naacl-main)

Challenge:	Experimental results from competition-level complex reasoning demonstrate that bootstrapping with process prejudge can significantly enhance the reasoning ability of LLMs.
Approach:	They propose a new process prejudge strategy for LLM reasoning that bootstraps with process prejudgment .
Outcome:	The proposed method can be bootstrapped with process prejudge in LLM reasoning . it allows the model to anticipate errors rather than relying on trial and error.

Copied to clipboard

Xiyan Fu, Jun Wang, Zhenglu Yang

Devil’s Advocate: Anticipatory Reflection for LLM Agents (2024.findings-emnlp)

Challenge:	Multimodal summarization materials lacking a holistic organization by integrating resources from various modalities.
Approach:	They propose a multimodal article and video summarization dataset that integrates resources from different modalities.
Outcome:	The proposed dataset validates the important assistance role of external information for multimodal summarization.

Copied to clipboard

Haoyu Wang, Tao Li, Zhiwei Deng, Dan Roth, Yang Li

Split and Merge: Aligning Position Biases in LLM-based Evaluators (2024.emnlp-main)

Challenge:	Introspection-driven approach equips LLM agents with introspection, enhancing consistency and adaptability in solving complex tasks.
Approach:	They propose a zero-shot approach that equips LLM agents with introspection, enhancing consistency and adaptability in solving complex tasks.
Outcome:	The proposed approach improves performance and efficiency by reducing the number of trials and plan revisions by 45%.

Copied to clipboard

Zongjie Li, Chaozheng Wang, Pingchuan Ma, Daoyuan Wu, Shuai Wang, Cuiyun Gao, Yang Liu

EcomScriptBench: A Multi-task Benchmark for E-commerce Script Planning via Step-wise Intention-Driven Product Association (2025.acl-long)

Challenge:	Large language models (LLMs) have shown promise as automated evaluators for assessing the quality of answers generated by AI systems.
Approach:	They propose an alignment-based system that calibrates position bias in a lightweight yet effective manner by taking into account both length and semantics and combining them into a single prompt.
Outcome:	Extensive experiments with six LLMs on 11,520 answer pairs show that PORTIA significantly improves consistency and consistency rates with humans.

Copied to clipboard

Weiqi Wang, Limeng Cui, Xin Liu, Sreyashi Nag, Wenju Xu, Chen Luo, Sheikh Muhammad Sarwar, Yang Li, Hansu Gu, Hui Liu, Changlong Yu, Jiaxin Bai, Yifan Gao, Haiyang Zhang, Qi He, Shuiwang Ji, Yangqiu Song

Mitigating Hallucinations in Large Vision-Language Models without Performance Degradation (2026.acl-long)

Challenge:	Goal-oriented script planning is used by humans to plan for typical activities . however, this capability remains underexplored due to several challenges .
Approach:	They propose a framework that enables product-enriched scripts by associating products with each step based on the semantic similarity between the actions and their purchase intentions.
Outcome:	The proposed framework can generate product-enriched scripts from 2.4 million scripts . human annotations are conducted to provide gold labels for a sampled subset .

Copied to clipboard

Xingyu Zhu, Junfeng Fang, Shuo Wang, Beier Zhu, Zhicai Wang, Yonghui Yang, Xiangnan He

MobileWorld: Benchmarking Autonomous Mobile Agents in Agent-User Interactive and MCP-Augmented Environments (2026.acl-long)

Challenge:	Recent advances in large vision-language models produce hallucinations that compromise output reliability.
Approach:	They propose a dual-stage framework for mitigating hallucinations without performance degradation . they propose semantic-aware component disentanglement and interpretable parameter updates .
Outcome:	The proposed model reduces hallucinations by 23.4% while maintaining 97.4% of general generative capability.

Copied to clipboard

Quyu Kong, Xu Zhang, Zhenyu Yang, Nolan Gao, Chen Liu, Panrong Tong, Chenglin Cai, Hanzhang Zhou, Jianan Zhang, Liangyu Chen, Zhidan Liu, Steven Hoi, Yue Wang

Knowledge Injected Prompt Based Fine-tuning for Multi-label Few-shot ICD Coding (2022.findings-emnlp)

Challenge:	AndroidWorld is the dominant mobile GUI agent evaluation benchmark, but its success rates are low . despite reproducible emulator environment, it lacks key application categories such as e-commerce and enterprise communication.
Approach:	They propose a benchmark for mobile GUI agents that reflects real-world usage through long-horizon, cross-application workflows.
Outcome:	The proposed framework achieves over 90% success rates, while AndroidWorld is the dominant benchmark.

Copied to clipboard

Zhichao Yang, Shufan Wang, Bhanu Pratap Singh Rawat, Avijit Mitra, Hong Yu

Self-Critique Guided Iterative Reasoning for Multi-hop Question Answering (2025.findings-acl)

Challenge:	Existing methods for ICD coding are limited due to the high-dimensional space of multi-label assignment and the long-tail challenge.
Approach:	They propose a prompt-based fine-tuning technique with label semantics to solve this challenge.
Outcome:	The proposed method outperforms state-of-the-art methods on a benchmark dataset of code assignment in 14.5% of cases.

Copied to clipboard

Zheng Chu, Huiming Fan, Jingchang Chen, Qianyu Wang, Mingda Yang, Jiafeng Liang, Zhongjie Wang, Hao Li, Guo Tang, Ming Liu, Bing Qin

Memory-Driven Role-Playing: Evaluation and Enhancement of Persona Knowledge Utilization in LLMs (2026.findings-acl)

Challenge:	Large language models (LLMs) have demonstrated remarkable reasoning capabilities, but they still face challenges in knowledge-intensive multi-hop reasoning.
Approach:	They propose a method that uses self-critique feedback to guide iterative reasoning by enabling iteration and self-evaluation of its intermediate reasoning steps.
Outcome:	The proposed method surpasses the previous SOTA by 8.6% on three multi-hop reasoning datasets.

Copied to clipboard

Kai Wang, Haoyang You, Yang Zhang, Zhongjie Wang

Decoding the Multimodal Mind: Generalizable Brain-to-Text Translation via Multimodal Alignment and Adaptive Routing (2026.findings-acl)

Challenge:	Existing models fail to recall and accurately apply designated persona knowledge without explicit cues . memory-driven role-playing paradigms are attracting significant interest .
Approach:	They propose a memory-driven role-playing paradigm that frames persona knowledge as the LLM's internal memory store and a prompting architecture that guides structured memory retrieval and response generation.
Outcome:	The proposed paradigm provides a comprehensive diagnostic for four-stage role-playing abilities across 12 LLMs.

Copied to clipboard

Chunyu Ye, Yunhao Zhang, Jingyuan Sun, Chong Li, Yang Zhao, Shaonan Wang

A Survey on Detection of LLMs-Generated Content (2024.findings-emnlp)

Challenge:	Current approaches to decoding language from the human brain rely on unimodal representations, neglecting the brain’s inherently multimodal processing.
Approach:	They propose a framework that leverages Multimodal Large Language Models to align brain signals with a shared semantic space encompassing text, images, and audio.
Outcome:	The proposed framework achieves an 8.48% improvement on the most commonly used benchmark on fMRI datasets with textual, visual, and auditory stimuli.

Copied to clipboard

Xianjun Yang, Liangming Pan, Xuandong Zhao, Haifeng Chen, Linda Petzold, William Yang Wang, Wei Cheng

Challenge:	Recent advances in large language models have led to an increase in synthetic content generation . the ability to detect LLMs-generated content has become of paramount importance .
Approach:	They propose to provide a detailed overview of existing detection strategies and benchmarks, scrutinizing their differences and advocating for more adaptable and robust models to enhance detection accuracy.
Outcome:	The proposed model will be able to detect human-written content in real time.

Translationese-index: Using Likelihood Ratios for Graded and Generalizable Measurement of Translationese (2025.emnlp-main)

Copied to clipboard

Yikang Liu, Wanyang Zhang, Yiming Wang, Jialong Tang, Pei Zhang, Baosong Yang, Fei Huang, Rui Wang, Hai Hu

Little Giants: Synthesizing High-Quality Embedding Data at Scale (2025.naacl-long)

Challenge:	Translationese is a linguistic property that is often introduced in the translation process that is different from those of original texts.
Approach:	They propose to use synthesized translations and translations in the wild to evaluate T-index's generalizability in cross-domain settings and its validity against human judgments.
Outcome:	The proposed measure can generalize to unseen genres, authors, and language pairs.

Copied to clipboard

Haonan Chen, Liang Wang, Nan Yang, Yutao Zhu, Ziliang Zhao, Furu Wei, Zhicheng Dou

MuKA: Multimodal Knowledge Augmented Visual Information-Seeking (2025.coling-main)

Challenge:	Synthetic data generation is an increasingly popular way of training models without the need for large, manually labeled datasets.
Approach:	They propose a framework that aligns open-source small models to efficiently generate large-scale embedding data.
Outcome:	The proposed framework outperforms state-of-the-art embedding models by using only 1/10 of the GPT API calls.

Copied to clipboard

Lianghao Deng, Yuchong Sun, Shizhe Chen, Ning Yang, Yunfeng Wang, Ruihua Song

EmoAgent: Assessing and Safeguarding Human-AI Interaction for Mental Health Safety (2025.emnlp-main)

Challenge:	Existing methods for visual information-seeking tasks rely on textual knowledge . existing methods can impair information retrieval and confuse MLLMs .
Approach:	They propose a framework which leverages a multimodal knowledge base to address these limitations.
Outcome:	The proposed framework outperforms state-of-the-art methods on the InfoSeek and E-VQA benchmarks.

Copied to clipboard

Jiahao Qiu, Yinghui He, Xinzhe Juan, Yimin Wang, Yuhan Liu, Zixin Yao, Yue Wu, Xun Jiang, Ling Yang, Mengdi Wang

One Shot Dominance: Knowledge Poisoning Attack on Retrieval-Augmented Generation Systems (2025.findings-emnlp)

Challenge:	EmoAgent evaluates and mitigates mental health hazards in human-AI interactions, especially for vulnerable human users with psychological disorders.
Approach:	EmoAgent is a multi-agent AI framework designed to evaluate and mitigate mental health hazards in human-AI interactions.
Outcome:	EmoAgent evaluates and mitigates mental health hazards in human-AI interactions.

Copied to clipboard

Zhiyuan Chang, Mingyang Li, Xiaojun Jia, Junjie Wang, Yuekai Huang, Ziyou Jiang, Yang Liu, Qing Wang

A Probabilistic Inference Scaling Theory for LLM Self-Correction (2025.emnlp-main)

Challenge:	Existing knowledge poisoning attacks against RAG systems require multiple poisoned documents or can only function effectively on simplistic queries.
Approach:	They propose a more realistic knowledge poisoning attack that poisons only a single document while remaining effective for complex multi-hop questions involving complex relationships between multiple elements.
Outcome:	The proposed attack achieves success by poisoning only a single document while remaining effective for complex multi-hop questions involving complex relationships between multiple elements.

Copied to clipboard

Zhe Yang, Yichang Zhang, Yudong Wang, Ziyao Xu, Junyang Lin, Zhifang Sui

Linguistic Theories

Challenge:	Large Language Models (LLMs) have demonstrated the capability to refine their generated answers through self-correction, enabling continuous performance improvement over multiple rounds.
Approach:	They propose a probabilistic theory to model the dynamics of accuracy change and explain performance improvements observed in multi-round self-correction.
Outcome:	The proposed model can predict accuracy curves and improve accuracy over multiple rounds.

Rationales Are Not Silver Bullets: Measuring the Impact of Rationales on Model Performance and Reliability (2025.findings-acl)

Copied to clipboard

Chiwei Zhu, Benfeng Xu, An Yang, Junyang Lin, Quan Wang, Chang Zhou, Zhendong Mao

Detecting AI-Generated Content on Social Media with Multi-modal Language Models (2026.acl-industry)

Challenge:	Existing studies have shown that training language models with rationales augmentation is beneficial, but this view does not hold consistently.
Approach:	They conduct comprehensive investigations to thoroughly inspect the impact of rationales on model performance and a novel perspective of model reliability.
Outcome:	The proposed method outperforms untrained models in several areas and provides informative regulations on the broad utilization of rationales.

Copied to clipboard

Chenyang Yang, Shen Yan, Yibo Yang, Litao Hu, Yuchen Liu, Yuan Zeng, Hanchao Yu, Yinan Zhu, Sumedha Singla, Brian Vanover, Huijun Qian, Zihao Wang, Fujun Liu, Aashu Singh, Jianyu Wang, Xuewen Zhang

CAP: Controllable Alignment Prompting for Unlearning in LLMs (2026.acl-long)

Challenge:	Existing methods for AI-generated content detection face poor generalization to newer models, reliance on single modalities, and lack of interpretable explanations.
Approach:	They propose a model that curates diverse social media data and trains a vision-language model for detection and explanation.
Outcome:	The proposed model achieves state-of-the-art detection performance on public benchmarks and observes positive downstream impacts on user engagement.

Copied to clipboard

Zhaokun Wang, Jinyu Guo, Jingwen Pu, Hongli Pu, Meng Yang, Xunlei Chen, Jie Ou, Wenyi Li, Guangchun Luo, Wenhong Tian

When 20 Agents Fail to Sort: The Distributed Sorting Benchmark for Scalable Multi-Agent Systems (2026.findings-acl)

Challenge:	Existing methods for modifying parameters are unsystematic and rely on empirical experience.
Approach:	They propose a controllable alignment prompting for unlearning framework that decouples unlearning into a learnable prompt optimization process via reinforcement learning.
Outcome:	The proposed framework achieves precise, controllable unlearning without updating model parameters.

Copied to clipboard

Xin Yang, Junhao Wang, Bintao Tang, Xuxin Cheng, Cao Liu, Ke Zeng, Wenyuan Jiang

Challenge:	MAS-BENCH isolates coordination under explicit communication constraints . CAMOC significantly improves coordination success and efficiency across backends .
Approach:	They propose a distributed-sorting benchmark that isolates coordination under explicit communication constraints.
Outcome:	MAS-BENCH improves coordination success and efficiency across backends . CAMOC significantly improves efficiency under shared-state interaction .

On the Inference Calibration of Neural Machine Translation (2020.acl-main)

Copied to clipboard

Shuo Wang, Zhaopeng Tu, Shuming Shi, Yang Liu

How Likely Do LLMs with CoT Mimic Human Reasoning? (2025.coling-main)

Challenge:	Existing studies show that NMT models trained with label smoothing are well-calibrated on ground-truth training data, but miscalibration remains a challenge during inference due to the discrepancy between training and inference.
Approach:	They propose a graduated label smoothing method that can improve inference calibration and translation performance.
Outcome:	The proposed method improves both inference calibration and translation performance.

Copied to clipboard

Guangsheng Bao, Hongbo Zhang, Cunxiang Wang, Linyi Yang, Yue Zhang

Enhancing Multilingual Capabilities of Large Language Models through Self-Distillation from Resource-Rich Languages (2024.acl-long)

Challenge:	Using chain-of-thought to elicit reasoning capabilities is not always effective and accurate.
Approach:	They compare the reasoning process of LLMs with humans to understand the causal chain . they find that LLM deviates from the ideal causal chain, resulting in spurious correlations .
Outcome:	The proposed method does not improve performance or accurately represent reasoning processes in LLMs.

Copied to clipboard

Yuanchi Zhang, Yile Wang, Zijun Liu, Shuo Wang, Xiaolong Wang, Peng Li, Maosong Sun, Yang Liu

QaRL: Rollout-Aligned Quantization-Aware RL for Fast and Stable Training under Training–Inference Mismatch (2026.findings-acl)

Challenge:	Contemporary large language models (LLMs) are pre-trained on multilingual corpora, but their performance lags behind in most languages compared to a few resource-rich languages.
Approach:	They propose a method that leverages the internal capabilities of large language models on resource-rich languages to enhance multilingual performance.
Outcome:	The proposed method improves multilingual performance while minimizing impact on original performance in resource-rich languages.

Copied to clipboard

Hao Gu, Hao Wang, Jiacheng Liu, Lujun Li, Qiyuan Zhu, Bei Liu, Binxing Xu, Lei Wang, Xintong Yang, Sida Lin, Sirui Han, Yike Guo

Challenge:	Recent work has shown that reinforcement learning with simple rule-based reward functions (RLVR) can induce emergent reasoning behaviors and yield gains in challenging domains such as math problem solving.
Approach:	They propose a rollout-alignment-quantization-aware RL which aligns training-side forward with the quantized rollout to minimize mismatch.
Outcome:	The proposed approach outperforms quantized-rollout training by +5.5 on Qwen3-30B-A3B MoE for math problems while maintaining low-bit throughput.

Cross-lingual Text Classification with Heterogeneous Graph Neural Network (2021.acl-short)

Copied to clipboard

Ziyun Wang, Xuan Liu, Peiji Yang, Shixing Liu, Zhisheng Wang

Boosting LLM Agents with Recursive Contemplation for Effective Deception Handling (2024.findings-acl)

Challenge:	Existing methods for cross-lingual text classification only consider factors beyond semantic similarity, causing performance degradation between some language pairs.
Approach:	They propose a method to incorporate heterogeneous information within and across languages for cross-lingual text classification using graph convolutional networks.
Outcome:	The proposed method significantly outperforms state-of-the-art models on all tasks and achieves consistent performance gain over baselines in low-resource settings.

Copied to clipboard

Shenzhi Wang, Chang Liu, Zilong Zheng, Siyuan Qi, Shuo Chen, Qisen Yang, Andrew Zhao, Chaofei Wang, Shiji Song, Gao Huang

Challenge:	Recent advances in large language models (LLMs) have led to significant success in using LLMs as agents.
Approach:	They propose a cognitive framework that incorporates first-order and second-order perspective transitions into LLMs to enhance their ability to identify and counteract deceptive information.
Outcome:	The proposed framework enhances LLMs’ ability to identify and counteract deceptive information without extra fine-tuning and data.

Safeguarding LLM Fine-tuning via Push-Pull Distributional Alignment (2026.acl-long)

Copied to clipboard

Haozhong Wang, Zhuo Li, Yibo Yang, He Zhao, Hongyuan Zha, Dandan Guo

Improving Text Embeddings with Large Language Models (2024.acl-long)

Challenge:	Existing safety defenses for large language models fail to explicitly repel harmful patterns . Optimal transport (SOT) allows for safe fine-tuning without sacrificing safety .
Approach:	They propose a framework that reframes safe fine-tuning from instance-level filtering challenge to distribution-level alignment task grounded in Optimal Transport.
Outcome:	a new framework improves safety of large language models while maintaining competitive performance . the proposed framework reduces the risk of errors and improves model performance compared to baselines .

Copied to clipboard

Liang Wang, Nan Yang, Xiaolong Huang, Linjun Yang, Rangan Majumder, Furu Wei

QDTSynth: Quality-Driven Formal Theorem Synthesis for Enhancing Proving Performance of LLMs (2025.acl-long)

Challenge:	Existing methods for obtaining text embeddings require complex training pipelines . authors leverage proprietary LLMs to generate diverse synthetic data for text embeds based on 93 languages .
Approach:	They propose a method for obtaining high-quality text embeddings using only synthetic data and less than 1k training steps.
Outcome:	The proposed method achieves strong performance on competitive text embedding benchmarks without using any labeled data.

Copied to clipboard

Lei Wang, Ruobing Zuo, Gaolei He, Jianlin Wang, Zhengfeng Yang

Designing Templates for Eliciting Commonsense Knowledge from Pretrained Sequence-to-Sequence Models (2020.coling-main)

Challenge:	Existing formal languages such as Lean, Coq and Metamath are proving to be useful in formal theorem proving . however, there is a scarcity of high-quality supervised fine-tuning data for formal proofs .
Approach:	They propose a Quality-Driven Theorem S**ynthesis method in Lean4 . they propose diversity screening and the self-assessment method to select theoremas that exhibit diversity and high quality from the initial synthetic statements.
Outcome:	The proposed method significantly improves performance of open-source LLMs in theorem proving tasks.

Copied to clipboard

Jheng-Hong Yang, Sheng-Chieh Lin, Rodrigo Nogueira, Ming-Feng Tsai, Chuan-Ju Wang, Jimmy Lin

ProFit: Leveraging High-Value Signals in SFT via Probability-Guided Token Selection (2026.findings-acl)

Challenge:	Existing approaches to extract implicit knowledge from pretrained models are still unclear.
Approach:	They propose to use a template-based approach to extract implicit knowledge for commonsense reasoning on multiple-choice questions.
Outcome:	The proposed template can be extended to other MC tasks with contexts such as supporting facts in open-book question answering settings.

Copied to clipboard

Tao Liu, Taiqiang Wu, Runming Yang, Shaoning Sun, Junjie Wang, Yujiu Yang

Challenge:	Traditional fine-tuning ignores one-to-many nature of language, leading to overfitting . authors propose a method to fine- tune LLMs by leveraging tokens.
Approach:	They propose a method to fine-tune Large Language Models by leveraging tokens to mask low-probability tokens.
Outcome:	The proposed method outperforms baselines on general reasoning and mathematical benchmarks.

Hidden in Plain Sight: Reasoning in Underspecified and Misspecified Scenarios for Multimodal LLMs (2025.emnlp-main)

Copied to clipboard

Qianqi Yan, Hongquan Li, Shan Jiang, Yang Zhao, Xinze Guan, Ching-Chen Kuo, Xin Eric Wang

Modeling LLM Unlearning as an Asymmetric Two-Task Learning Problem (2026.acl-long)

Challenge:	Multimodal large language models are increasingly deployed in open-ended, real-world environments where inputs are messy, underspecified, and not always trustworthy.
Approach:	They evaluate multimodal large language models in real-world environments where inputs are messy, underspecified, and not always trustworthy.
Outcome:	The proposed models fail to detect hidden issues even when they possess the necessary perceptual and reasoning skills.

Copied to clipboard

Zeguan Xiao, Siqing Li, Yong Wang, Xuetao Wei, Jian Yang, Yun Chen, Guanhua Chen

PolCLIP: A Unified Image-Text Word Sense Disambiguation Model via Generating Multimodal Complementary Representations (2024.acl-long)

Challenge:	Large language models (LLMs) are inherently dual-use and can be leveraged for both beneficial and harmful purposes.
Approach:	They propose a retention-prioritized gradient synthesis framework that decouples task-specific gradient extraction from conflict-aware combination.
Outcome:	The proposed method achieves tighter alignment on WMDP Bio and RWKU benchmarks.

Copied to clipboard

Qihao Yang, Yong Li, Xuelin Wang, Fu Lee Wang, Tianyong Hao

CCG: Rare-Label Prediction via Neural SEM–Driven Causal Game (2025.findings-emnlp)

Challenge:	Existing models for word sense disambiguation lack images or senses in textual and visual datasets.
Approach:	They propose a unified image-text WSD model that uses image-sense complementarity to generate visual representations for word senses and a disambiguation-oriented image-sensor dataset to provide implicit textual representations.
Outcome:	The proposed model achieves 2.53% F1-score increase over state-of-the-art models on Textual-WSD and 2.22% HR@1 improvement on Visual-WSS.

Copied to clipboard

Yijia Fan, Jusheng Zhang, Kaitong Cai, Jing Yang, Keze Wang

Not All Demonstration Examples are Equally Beneficial: Reweighting Demonstration Examples for In-Context Learning (2023.findings-emnlp)

Challenge:	Multi-label classification (MLC) faces persistent challenges from label imbalance, spurious correlations, distribution shifts, especially in rare label prediction.
Approach:	They propose a Causal Cooperative Game framework that models multi-player cooperative process for multi-label classification.
Outcome:	The proposed framework improves rare label prediction and overall robustness compared to baselines.

Copied to clipboard

Zhe Yang, Damai Dai, Peiyi Wang, Zhifang Sui

Text2Mem: A Unified Memory Operation Language for Memory Operating System (2026.findings-acl)

Challenge:	Large Language Models (LLMs) have recently gained the In-Context Learning ability . however, the quality of demonstration examples is usually uneven .
Approach:	They propose to determine optimal weights for demonstration examples and apply them during ICL.
Outcome:	The proposed approach outperforms conventional ICL on 8 classification tasks.

Copied to clipboard

Leo Wang, Lihai Yang, Boyu Chen, Kerun Xu, Gongyi Zou, Bo Tang, Feiyu Xiong, Siheng Chen, Zhiyu li

Challenge:	Existing memory frameworks lack a formal, executable specification for memory control.
Approach:	They propose a unified memory operation language that standardizes translation of natural-language instructions into reliable execution.
Outcome:	The proposed language standardizes translation of natural-language instructions into reliable execution.

Fast Adaptation via Prompted Data: An Efficient Cross-Domain Fine-tuning Method for Large Language Models (2024.lrec-main)

Copied to clipboard

Yiming Zhang, Hantao Yang, Haobo Wang, Jake Zhao

CSI: An Investigative Multi-Agent Framework for Explainable Short Video Fake News Detection (2026.findings-acl)

Challenge:	Large language models (LLMs) have been successful in a variety of natural language understanding tasks, but domain discrepancies between the downstream task and the pre-training corpora may have hindered LLMs to excel further in the vertical applications.
Approach:	They propose a Fast Adaptation method for LLMs via Prompted Data that integrates downstream text corpora, gold labels and external knowledge sources into a highly controllable prompt.
Outcome:	The proposed method bridges the gap between the downstream task and the pre-training corpora and integrates downstream text corpors, gold labels and external knowledge sources into a highly controllable prompt.

Copied to clipboard

Yuxin Wang, Yang Yang, Huaiwen Zhang

Exploring Fine-Grained Human Motion Video Captioning (2025.coling-main)

Challenge:	Existing methods for short video fake news detection rely on black-box MSLMs with poor explainability and superficial understanding or on specific prompt strategies for Multimodal Large Language Models (MLLMs)
Approach:	They propose a multi-agent framework called CSI for short video fake news detection.
Outcome:	The proposed framework provides rigorous explanations while achieving state-of-the-art performance on two real-world datasets.

Copied to clipboard

Bingchan Zhao, Xinyi Liu, Zhuocheng Yu, Tongchen Yang, Yifan Song, Mingyu Jin, Sujian Li, Yizhou Wang

InfiAgent: An Infinite-Horizon Framework for General-Purpose Autonomous Agents (2026.findings-acl)

Challenge:	Existing video captioning models fail to capture nuanced semantics of videos . existing models generate coarse descriptions of human motions, resulting in poor quality .
Approach:	They construct a fine-grained human motion video captioning dataset named BoFiT and a model that generates fine-grain descriptions of human motions via prompting.
Outcome:	The proposed model outperforms existing models on comprehensive metrics.

Copied to clipboard

Chenglin Yu, Yuchen Wang, Songmiao Wang, Hongxia Yang, Li Ming

Peer-Label Assisted Hierarchical Text Classification (2023.acl-long)

Challenge:	Existing LLMs break down on long-horizon tasks due to unbounded context growth and accumulated errors.
Approach:	They propose a framework that externalizes persistent state into a file-centric state abstraction and keeps the agent’s reasoning context strictly bounded regardless of task duration.
Outcome:	Experiments on DeepResearch and an 80-paper literature review show that the proposed framework maintains higher long-horizon coverage than baseline models without task-specific fine-tuning.

Copied to clipboard

Junru Song, Feifei Wang, Yang Yang

Chinese Morpheme-informed Evaluation of Large Language Models (2024.lrec-main)

Challenge:	Existing approaches to hierarchical text classification focus on parent-child relationships . however, some texts with a category hierarchy also have latent relevancy among labels in the same level of the hierarchy.
Approach:	They propose a method to analyze latent relevancy of peer labels and a sample importance learning method to ameliorate the side effects.
Outcome:	The proposed method improves the latent relevancy of peer labels on standard datasets.

Copied to clipboard

Yaqi Yin, Yue Wang, Yang Liu

Towards Dynamic Theory of Mind: Evaluating LLM Adaptation to Temporal Evolution of Human States (2025.acl-long)

Challenge:	Existing evaluations of large language models focused on the perspective of various tasks or abilities.
Approach:	They propose to evaluate large language models from a linguistic perspective and use morpheme to measure morphology and syntax.
Outcome:	The proposed model outperforms ChatGPT in Chinese scenarios with a morpheme-informed benchmark and human exam questions.

Copied to clipboard

Yang Xiao, Jiashuo Wang, Qiancheng Xu, Changhe Song, Chunpu Xu, Yi Cheng, Wenjie Li, Pengfei Liu

Linguistics & Cognitive NLP

Challenge:	Existing benchmarks assess basic Theory of Mind abilities but neglect temporal evolution of mental states in real-world social contexts.
Approach:	They propose a benchmark specifically designed to evaluate Large Language Models' ability to understand and track the temporal progression of mental states across interconnected scenarios.
Outcome:	The proposed benchmarks underperform humans by 44.7% and show that they can model the dynamic nature of human mental states better than existing models.

ODUTQA-MDC: A Task for Open-Domain Underspecified Tabular QA with Multi-turn Dialogue-based Clarification (2026.acl-long)

Copied to clipboard

Zhensheng Wang, ZhanTeng Lin, Wenmian Yang, Kun Zhou, Yiquan Zhang, Weijia Jia

Evaluating Character Understanding of Large Language Models via Character Profiling from Fictional Works (2024.emnlp-main)

Challenge:	Existing approaches to tabular QA are limited to closed-domain scenarios . existing approaches do not solve the core challenge of generating correct answers without user clarification .
Approach:	They propose a benchmark to tackle underspecified or uncertain queries in tabular question answering . they propose ODUTQA-MDC task and a multi-agent framework to detect ambiguities .
Outcome:	The proposed framework excels at detecting ambiguities, clarifying them through dialogue, and refining answers.

Copied to clipboard

Xinfeng Yuan, Siyu Yuan, Yuhan Cui, Tianhe Lin, Xintao Wang, Rui Xu, Jiangjie Chen, Deqing Yang

Unlocking Efficiency in Large Language Model Inference: A Comprehensive Survey of Speculative Decoding (2024.findings-acl)

Challenge:	Recent advances in large language models (LLMs) have catalyzed numerous AI applications, among which role-playing agents (RPAs) are particularly popular.
Approach:	They propose to evaluate LLMs' character understanding capability via the character profiling task, i.e., summarizing character profiles from corresponding materials, a widely adopted yet understudied practice for RPA development.
Outcome:	The proposed model outperforms existing models and literature summarization methods and proves its ability to understand fictional characters in downstream tasks.

Copied to clipboard

Heming Xia, Zhe Yang, Qingxiu Dong, Peiyi Wang, Yongqi Li, Tao Ge, Tianyu Liu, Wenjie Li, Zhifang Sui

Text-like Encoding of Collaborative Information in Large Language Models for Recommendation (2024.acl-long)

Challenge:	Large Language Models (LLMs) have a high inference latency stemming from autoregressive decoding.
Approach:	They propose a novel decoding paradigm that drafts multiple tokens and verifies them in parallel . they aim to provide a catalyst for further research on Speculative Decoding .
Outcome:	The proposed method drafts multiple tokens and verifies them in parallel . it can be used to accelerate inference in large language models.

Copied to clipboard

Yang Zhang, Keqin Bao, Ming Yan, Wenjie Wang, Fuli Feng, Xiangnan He

RARE: Retrieval-Augmented Reasoning Enhancement for Large Language Models (2025.acl-long)

Challenge:	Existing methods to adapt Large Language Models for Recommendation (LLMRec) do not represent collaborative information in a text-like format, which may not align optimally with LLMs.
Approach:	They propose a novel LLMRec method that integrates collaborative information through text-like encoding.
Outcome:	Extensive experiments show that BinLLM integrates collaborative information better with LLMs.

Copied to clipboard

Hieu Tran, Zonghai Yao, Zhichao Yang, Junda Wang, Yifan Zhang, Shuo Han, null Feiyun Ouyang, Hong Yu

Decoding Susceptibility: Modeling Misbelief to Misinformation Through a Computational Approach (2024.emnlp-main)

Challenge:	Existing work aims to improve reasoning accuracy and factual integrity across large language models for knowledge-intensive tasks such as medical and commonsense reasoning.
Approach:	They propose a versatile extension to the mutual reasoning framework (rStar) that enhances reasoning accuracy and factual integrity across large language models.
Outcome:	The proposed extension to the mutual reasoning framework improves reasoning accuracy and factual integrity across large language models for complex, knowledge-intensive tasks.

Copied to clipboard

Yanchen Liu, Mingyu Ma, Wenna Qin, Azure Zhou, Jiaao Chen, Weiyan Shi, Wei Wang, Diyi Yang

Can Large Language Models Identify Implicit Suicidal Ideation? An Empirical Evaluation (2025.findings-emnlp)

Challenge:	Existing studies on susceptibility to misinformation rely on self-reported beliefs, which can be subject to bias, expensive to collect, and challenging to scale for downstream applications.
Approach:	They propose a computational approach to efficiently model users’ latent susceptibility levels by using demographic factors and political ideology as inputs.
Outcome:	The proposed model shows that political leanings and other psychological factors exhibit varying degrees of association with susceptibility to COVID-19 misinformation.

Copied to clipboard

Tong Li, Shu Yang, Junchao Wu, Jiyao Wei, Lijie Hu, Mengdi Li, Derek F. Wong, Joshua R. Oltmanns, Di Wang

FIER: Fine-Grained and Efficient KV Cache Retrieval for Long-context LLM Inference (2025.findings-emnlp)

Challenge:	Existing data on suicidal ideation in private conversations are limited . a new dataset of 1,200 test cases is presented to address this gap .
Approach:	They propose a dataset of 1,200 test cases simulating implicit suicidal ideation in private contexts.
Outcome:	The proposed dataset includes 1,200 test cases simulating implicit suicidal ideation in dialogue scenarios.

Copied to clipboard

Dongwei Wang, Zijie Liu, Song Wang, Yuxin Ren, Jianing Deng, Jingtong Hu, Tianlong Chen, Huanrui Yang

PersonaAgent: Bridging Memory and Action for Personalized LLM Agents (2026.findings-acl)

Challenge:	Key-Value (KV) cache reading latency increases with context lengths hindering LLM inference . important tokens are sparsely distributed across the long context, making existing retrieval inaccurate .
Approach:	They propose a method to retain a small fraction of KV cache based on token importance . important tokens are often sparsely distributed across the long context .
Outcome:	The proposed method reduces decoding latency by 1.2 to 1.5.

Copied to clipboard

Weizhi Zhang, Xinyang Zhang, Chenwei Zhang, Liangwei Yang, Jingbo Shang, Zhepei Wei, Henry Peng Zou, Zijie Huang, Zhengyang Wang, Yifan Gao, Xiaoman Pan, Lian Xiong, Jingguo Liu, Philip S. Yu, Xian Li

PARSE: An Efficient Search Method for Black-box Adversarial Text Attacks (2022.coling-1)

Challenge:	Existing Large Language Model (LLM) enabled agents lack flexibility to respond to users’ varying needs and preferences.
Approach:	They propose a test-time user-preference alignment strategy that optimizes the persona prompt, ensuring real-time preference alignment through textual loss feedback between simulated and ground-truth responses.
Outcome:	The proposed framework outperforms baseline methods in real-time and in real applications.

Copied to clipboard

Pengwei Zhan, Chao Zheng, Jing Yang, Yuxiang Wang, Liming Wang, Yang Wu, Yunjian Zhang

HSCodeComp: A Realistic and Expert-level Agent Benchmark for Hierarchical Rule Application (2026.acl-long)

Challenge:	Neural networks are vulnerable to adversarial examples, i.e., under a black-box scenario.
Approach:	They propose a word-level search algorithm that searches for subareas under dynamic search space following the subarea importance.
Outcome:	The proposed algorithm can achieve comparable success rates to complex search methods while saving numerous queries and time.

Copied to clipboard

Tian Lan, Yiqian Yang, Qianghuai Jia, Li Zhu, Hui Jiang, Hang Zhu, Weihua Luo, Longyue Wang

DaNet: Dual-Aware Enhanced Alignment Network for Multimodal Aspect-Based Sentiment Analysis (2025.findings-acl)

Challenge:	Existing agent benchmarks neglect hierarchical rule application in real-world domains . a critical gap persists in numerous real-life professional domains where decision-making is governed by expert-written rules.
Approach:	They propose a benchmark requiring agents to assign a unique 10-digit Harmonized System (HS) Code to products by aligning their fuzzy attributes with strict tariff classification rules.
Outcome:	The proposed benchmarks lack hierarchical rule application capability in real-world domains . the proposed benchmark is based on e-commerce and is open-source .

Copied to clipboard

Aoqiang Zhu, Min Hu, Xiaohua Wang, Jiaoyun Yang, Yiming Tang, Ning An

Lightweight LLM Agent Memory with Small Language Models (2026.acl-long)

Challenge:	Existing methods assume a direct alignment between images and aspects, matching the entire image with a corresponding aspect. Existing algorithms assume 'direct alignment' between images, introducing noise.
Approach:	They propose a Dual-Aware Enhanced Alignment Network (DaNet) that can enhance fine-grained multimodal aspect-image alignment and denoising.
Outcome:	The proposed system outperforms existing methods in three subtasks and is available on https://github.com/***/DaNet.

Copied to clipboard

Jiaquan Zhang, Chaoning Zhang, Shuxu Chen, Zhenzhen Huang, Pengcheng Zheng, Zhicheng Wang, Ping Guo, Fan Mo, Sung-Ho Bae, Jie Zou, Jiwei Wei, Yang Yang

On-the-Fly VLA Adaptation via Test-Time Reinforcement Learning (2026.acl-long)

Challenge:	Existing external memory systems for LLMs have low online overhead but are unstable in accumulating latency over long interactions.
Approach:	They propose a lightweight memory system for better agent memory driven by Small Language Models . lightmem modularizes memory retrieval, writing, and long-term consolidation . they show consistent gains across model scales and high efficiency .
Outcome:	The proposed system improves agent memory but has low latency and low online overhead . it separates online processing from offline consolidation to enable efficient memory invocation . the proposed system achieves an average F1 improvement of 2.5 over A-MEM on LoCoMo .

Copied to clipboard

Changyu Liu, Yiyang Liu, Taowen Wang, Qiao Zhuang, James Chenhao Liang, Wenhao Yang, Renjing Xu, Qifan Wang, Dongfang Liu, Cheng Han

MAGE: Machine-generated Text Detection in the Wild (2024.acl-long)

Challenge:	Existing vision-language-action models are unsuitable for simulated or physical-world deployments . current methods fail when confronted with inherent real-world dynamic variability.
Approach:	They propose a test-time reinforcement learning framework that enables on-the-fly policy adaptation during inference.
Outcome:	Empirical results show that the proposed framework improves adaptability, stability and task success in dynamic, previously unseen scenarios.

Copied to clipboard

Yafu Li, Qintong Li, Leyang Cui, Wei Bi, Zhilin Wang, Longyue Wang, Linyi Yang, Shuming Shi, Yue Zhang

FARSS: Fisher-Optimized Adaptive Low-Rank and Singular-Vector Selection for Knowledge-Preserving Fine-Tuning (2026.findings-acl)

Challenge:	Existing research has focused on evaluating detection methods for specific domains or language models.
Approach:	They build a testbed to detect texts from diverse human writings and LLMs using different detection methods.
Outcome:	Empirical results show that the top performing detector can identify 84.12% out-of-domain texts generated by a new LLM, indicating the feasibility for application scenarios.

Copied to clipboard

Renxing Chen, Ziwei Xiang, Peisong Wang, Hongjian Fang, Meng Li, Fanhu Zeng, Yanan Zhu, Peipei Yang, Xu-Yao Zhang, Jian Cheng

Beyond Static Rules: Automated Discovery of Latent Vulnerabilities in Text-to-SQL (2026.findings-acl)

Challenge:	Low-rank adaptation methods for large language models have limitations in preserving world knowledge and limiting updates to preserve world knowledge.
Approach:	They propose a Fisher-optimized adaptive low Rank and Singular-VectorSelection framework for knowledge-preserving fine-tuning that allows efficient and task-sensitive updates.
Outcome:	The proposed framework outperforms existing methods for knowledge-preserving fine-tuning.

Copied to clipboard

Hanqing Wang, Yongdong Chi, Jian Yang, Lei Yang, Jiehui Zhao, Yun Chen, Guanhua Chen

AROMA: Autonomous Rank-one Matrix Adaptation (2025.emnlp-main)

Challenge:	Large Language Models (LLMs) have been successful in Text-to-SQL tasks, but their deployment in real-world environments is hindered by latent reliability issues.
Approach:	They propose a framework to autonomously uncover latent failure patterns in LLM-based Text-to-SQL generation.
Outcome:	The proposed framework uncovers a substantial number of failure cases on state-of-the-art open-source LLMs.

Copied to clipboard

Hao Nan Sheng, Zhi-Yong Wang, Hing Cheung So, Mingrui Yang

Implicit Cross-Lingual Rewarding for Efficient Multilingual Preference Alignment (2025.findings-acl)

Challenge:	Low-rank adaptation (LoRA) and adaptive low-rank adaption (AdaLoRa) are effective for large language models but are expensive as model sizes escalate into hundreds of billions of parameters.
Approach:	They propose a framework that automatically builds up rank-one components with very few trainable parameters that gradually diminish to zero.
Outcome:	The proposed framework significantly reduces parameters compared to LoRA and AdaLoRA while maintaining subspace independence.

Copied to clipboard

Wen Yang, Junhong Wu, Chen Wang, Chengqing Zong, Jiajun Zhang

Progressive Self-Training with Discriminator for Aspect Term Extraction (2021.emnlp-main)

Challenge:	Existing approaches to align English LLMs with human preferences rely on expensive human annotations or advanced multilingual preference alignment models.
Approach:	They propose a method that captures learned preferences from English models by implicit rewards . they annotate preference relations in cross-lingual instruction-following pairs using English .
Outcome:	The proposed approach captures learned preferences from well-aligned English models by implicit rewards and transfers them to other languages through iterative training.

Copied to clipboard

Qianlong Wang, Zhiyuan Wen, Qin Zhao, Min Yang, Ruifeng Xu

PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference (2025.acl-long)

Challenge:	Existing approaches to extract aspect terms from review sentences are limited due to lack of annotated data.
Approach:	They propose to refine conventional self-training to progressive self-teaching to reduce noise . they use a discriminator to filter the noisy pseudo-labels.
Outcome:	The proposed model outperforms baseline models and achieves state-of-the-art performance on four SemEval datasets.

Copied to clipboard

Jiaming Ji, Donghai Hong, Borong Zhang, Boyuan Chen, Josef Dai, Boren Zheng, Tianyi Alex Qiu, Jiayi Zhou, Kaile Wang, Boxun Li, Sirui Han, Yike Guo, Yaodong Yang

Challenge:	Using large-scale annotation data, large language models can generate noise, errors and biases, leading to unexpected behaviours.
Approach:	They propose a dataset to promote safety alignment in large language models . they separate helpfulness and harmlessness annotations for question-answering pairs .
Outcome:	The proposed dataset provides 44.6k prompts and 265k question-answer pairs with safety meta-labels for 19 harm categories and three severity levels, with answers generated by Llama-family models.

SeaLLMs - Large Language Models for Southeast Asia (2024.acl-demos)

Copied to clipboard

Xuan-Phi Nguyen, Wenxuan Zhang, Xin Li, Mahani Aljunied, Zhiqiang Hu, Chenhui Shen, Yew Ken Chia, Xingxuan Li, Jianyu Wang, Qingyu Tan, Liying Cheng, Guanzheng Chen, Yue Deng, Sen Yang, Chaoqun Liu, Hang Zhang, Lidong Bing

Sheep’s Skin, Wolf’s Deeds: Are LLMs Ready for Metaphorical Implicit Hate Speech? (2025.acl-long)

Challenge:	Existing large language models favor high-resource languages, such as English, at the expense of low-resourced and regional languages.
Approach:	They propose a series of language models that specifically focuses on Southeast Asian languages.
Outcome:	SeaLLM models outperform ChatGPT-3.5 in non-Latin languages by large margins . linguistic disparity impedes access to state-of-the-art AI technologies for non-English-speaking populations .

Copied to clipboard

Jingjie Zeng, Liang Yang, Zekun Wang, Yuanyuan Sun, Hongfei Lin

DenseSSM: State Space Models with Dense Hidden Connection for Efficient Large Language Models (2025.naacl-long)

Challenge:	specialized models fail to detect implicit hate speech due to its indirectly expressed hateful intent . advanced LLMs often misinterpret metaphorical implicit hate content, resulting in its propagation .
Approach:	They propose a Jailbreaking strategy and Energy-based Constrained Decoding techniques to detect implicit hate speech in large language models.
Outcome:	The proposed model can generate metaphorical implicit hate speech, but it fails to detect it effectively.

Copied to clipboard

Wei He, Kai Han, Yehui Tang, Chengcheng Wang, Yujie Yang, Tianyu Guo, Yunhe Wang

DiMo-GUI: Advancing Test-time Scaling in GUI Grounding via Modality-Aware Visual Reasoning (2025.emnlp-main)

Challenge:	Large language models (LLMs) face excessive computational and memory requirements due to the commonly used Transformer architecture.
Approach:	They propose a method to enhance the flow of hidden information between layers in large language models by selectively integrating shallow-layer hidden states into deeper layers.
Outcome:	The proposed method maintains parallelizability and inference efficiency of SSMs while significantly boosting performance on public benchmarks.

Copied to clipboard

Hang Wu, Hongkai Chen, Yujun Cai, Chang Liu, Qingwen Ye, Ming-Hsuan Yang, Yiwei Wang

Data-to-Text Generation with Style Imitation (2020.findings-emnlp)

Challenge:	DiMo-GUI is a training-free framework for GUI grounding that splits input into textual elements and iconic elements, allowing the model to reason over each modality independently using general-purpose vision-language models.
Approach:	They propose a training-free framework for GUI grounding that leverages two core strategies: dynamic visual grounding and modality-aware optimization.
Outcome:	The proposed framework splits the input into textual elements and iconic elements, allowing the model to reason over each modality independently using general-purpose vision-language models.

Copied to clipboard

Shuai Lin, Wentao Wang, Zichao Yang, Xiaodan Liang, Frank F. Xu, Eric Xing, Zhiting Hu

Explicit and Implicit Data Augmentation for Social Event Detection (2025.acl-long)

Challenge:	Recent approaches to data-to-text generation focus on improving content fidelity, but lack explicit control over writing styles.
Approach:	They propose a way to control writing styles by using existing sentences as "soft" templates . they conduct experiments in restaurants and sports domains to test their approach .
Outcome:	The proposed approach achieves stronger performance than a range of comparison methods.

Copied to clipboard

Congbo Ma, Yuxia Wang, Jia Wu, Jian Yang, Jing Du, Zitai Qiu, Qing Li, Hu Wang, Preslav Nakov

Knowledge-Infused Prompting: Assessing and Advancing Clinical Text Data Generation with Large Language Models (2024.findings-acl)

Challenge:	Social event detection relies on labeled data, but annotation is costly and labor-intensive.
Approach:	They propose a plug-and-play dual augmentation framework that combines explicit text-based and implicit feature-space augmentation to enhance data diversity and model robustness.
Outcome:	The proposed framework outperforms the best baseline model by 17.67% on the Twitter2012 dataset and 15.57% on the twitter2018 dataset in terms of the average F1 score.

Copied to clipboard

Ran Xu, Hejie Cui, Yue Yu, Xuan Kan, Wenqi Shi, Yuchen Zhuang, May Dongmei Wang, Wei Jin, Joyce Ho, Carl Yang

Render-of-Thought: Rendering Textual Chain-of-Thought as Images for Visual Latent Reasoning (2026.acl-long)

Challenge:	Clinical natural language processing (NLP) is a subfield that requires the extraction, analysis, and interpretation of unstructured clinical text.
Approach:	They propose a model which infuses knowledge into clinical text generation with LLMs for clinical NLP tasks.
Outcome:	The proposed model improves performance across 8 clinical NLP tasks and 18 datasets by 7.7%-8.7% on average.

Copied to clipboard

Yifan Wang, Shiyu Li, Peiming Li, Xiaochen Yang, Zheng Wei, Yang Tang

RAFT: Realistic Attacks to Fool Text Detectors (2024.emnlp-main)

Challenge:	Recent work on Chain-of-Thought prompting imposes substantial computational overhead . lack of supervision obscures the analyzability of the latent reasoning chain.
Approach:	They propose a framework to render latent reasoning chain into images, making latent rationale explicit and traceable.
Outcome:	The proposed framework achieves 3-4 token compression and substantial inference acceleration compared to explicit CoT prompting.

Copied to clipboard

James Wang, Ran Li, Junfeng Yang, Chengzhi Mao

PEDNet: A Persona Enhanced Dual Alternating Learning Network for Conversational Response Generation (2020.coling-main)

Challenge:	Large language models (LLMs) have exhibited remarkable fluency across tasks, but their unethical applications are unclear.
Approach:	They propose a grammar error-free black-box attack that exploits LLM embeddings at the word-level while preserving original text quality.
Outcome:	The proposed attack compromises all detectors across domains and is transferable across source models.

Copied to clipboard

Bin Jiang, Wanyue Zhou, Jingxu Yang, Chao Yang, Shihan Wang, Liang Pang

RAM-EHR: Retrieval Augmentation Meets Clinical Predictions on Electronic Health Records (2024.acl-short)

Challenge:	Existing persona-based dialogue models generate personalized responses using predefined persona information, but they lack personality.
Approach:	They propose a persona-based dual Alternating Learning Network that generates personalized responses using predefined persona information.
Outcome:	The proposed method produces more personalized responses than baseline methods.

Copied to clipboard

Ran Xu, Wenqi Shi, Yue Yu, Yuchen Zhuang, Bowen Jin, May Dongmei Wang, Joyce Ho, Carl Yang

Evaluating the Expressive Appropriateness of Speech in Rich Contexts (2026.acl-long)

Challenge:	Existing deep learning models for EHRs rely on knowledge from a single source and do not capture the semantic information for medical codes.
Approach:	They propose a Retrieval AugMentation pipeline to augment clinical prediction on EHRs . they use multiple knowledge sources to convert them into text and use consistency regularization to capture complementary information from patient visits and summarized knowledge.
Outcome:	Experiments on two EHR datasets show that RAM-EHR improves clinical prediction tasks.

Copied to clipboard

Tianrui Wang, Ziyang Ma, Yizhou Peng, Haoyu Wang, Zhikang Niu, Zikang Huang, Yihao Wu, Yi-Wen Chao, Yu Jiang, Yuheng Lu, Guanrou Yang, Xuanchen Li, Hexin Liu, Chunyu Qiang, Cheng Gong, Yifan Yang, Tianchi Liu, Junyu Wang, Nana Hou, Meng Ge, Fuming You, Yang Wei, Zhongqian Sun, Hu Haifeng, Xiaobao Wang, Eng Siong Chng, Xie Chen, Longbiao Wang, Jianwu Dang

Speech & Audio in NLP

Challenge:	Existing methods for evaluating expressive speech focus on word accuracy, naturalness, signal quality, or emotional intensity at the utterance level.
Approach:	They propose a framework for Evaluating Expressive Appropriateness in speech that assesses whether a speech sample aligns with the underlying communicative intent implied by its discourse-level narrative context.
Outcome:	The proposed framework outperforms existing speech evaluation and analysis systems on a human-annotated test set.

RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models (2024.findings-acl)

Copied to clipboard

Noah Wang, Z.y. Peng, Haoran Que, Jiaheng Liu, Wangchunshu Zhou, Yuhan Wu, Hongcheng Guo, Ruitong Gan, Zehao Ni, Jian Yang, Man Zhang, Zhaoxiang Zhang, Wanli Ouyang, Ke Xu, Wenhao Huang, Jie Fu, Junran Peng

TSPO: Breaking the Double Homogenization Dilemma in Multi-turn Search Policy Optimization (2026.findings-acl)

Challenge:	Large Language Models (LLMs) have paved the way for complex tasks such as role-playing.
Approach:	They propose a framework to benchmark, elicit, and enhance role-playing abilities in Large Language Models.
Outcome:	The proposed framework improves role-playing abilities with 168,093 samples.

Copied to clipboard

Shichao Ma, Zhiyuan Ma, Ming Yang, Xiaofan Li, Xing Wu, Jintao Du, Yu Cheng, Weiqiang Wang, Qiliang Liu, Zhengyang Zhou, Yang Wang

Exploiting Contrastive Learning and Numerical Evidence for Confusing Legal Judgment Prediction (2023.findings-emnlp)

Challenge:	Large Language Models (LLMs) can solve complex tasks through iterative information retrieval.
Approach:	They propose a turn-level stage-aware policy optimization approach to solve this problem . they introduce a first-occurrence latent reward mechanism to allocate partial rewards .
Outcome:	Experiments show that TSPO outperforms state-of-the-art models on Qwen2.5-3B and 7B models.

Copied to clipboard

Leilei Gan, Baokui Li, Kun Kuang, Yating Zhang, Lei Wang, Anh Luu, Yi Yang, Fei Wu

InsCL: A Data-efficient Continual Learning Paradigm for Fine-tuning Large Language Models with Instructions (2024.naacl-long)

Challenge:	Existing studies fail to distinguish different classification errors with a standard cross-entropy classification loss and ignore the numbers in the fact description for predicting the term of penalty.
Approach:	They propose to extract crime amounts from fact description and use them to learn distinguishable representations to exploit the numbers in the fact description for predicting the term of penalty.
Outcome:	The proposed method achieves state-of-the-art results on real-world datasets and ablation studies demonstrate the effectiveness of each component.

Copied to clipboard

Yifan Wang, Yafei Liu, Chufan Shi, Haoling Li, Chen Chen, Haonan Lu, Yujiu Yang

Combating Label Sparsity in Short Text Topic Modeling via Nearest Neighbor Augmentation (2024.findings-acl)

Challenge:	In order to perform downstream tasks, Large Language Models (LLMs) need continual adaptation without catastrophic forgetting.
Approach:	They propose a new paradigm that allows for continual adaptation without catastrophic forgetting . they propose to replay previous data based on task similarity with instructions .
Outcome:	The proposed method improves performance over 16 tasks with different training orders.

Copied to clipboard

Yang Lin, Xinyu Ma, Xin Gao, Ruiqing Li, Yasha Wang, Xu Chu

Identifying and Mitigating Spurious Correlations for Improving Robustness in NLP Models (2022.findings-naacl)

Challenge:	Existing topic models suffer from poor performance when applied to short text contents due to the limited length of a single topic.
Approach:	They propose a neural short text topic model that augments reconstruction labels with k-nearest documents to complement relevant but unobserved words.
Outcome:	The proposed model outperforms the state-of-the-art models on multiple public short-text datasets and can derive high-quality topics and document representations.

Copied to clipboard

Tianlu Wang, Rohit Sridhar, Diyi Yang, Xuezhi Wang

AEGIS: A Holistic Benchmark for Evaluating Forensic Analysis of AI-Generated Academic Images (2026.acl-long)

Challenge:	Existing work identifies task-specific shortcuts via human priors or error analyses, which requires extensive expertise and efforts.
Approach:	They propose to automatically identify spurious correlations in NLP models at scale by using existing interpretability methods to extract tokens that significantly affect model’s decision process.
Outcome:	The proposed method can identify spurious correlations in NLP models at scale and mitigate these leads to more robust models in multiple applications.

Copied to clipboard

Bo Zhang, Tzu-Yen Ma, Zichen Tang, Junpeng Ding, Zirui Wang, Yizhuo Zhao, Peilin Gao, Zijie Xi, Zixin Ding, Haiyang Sun, Haocheng Gao, Yuan Liu, Liangjia Wang, Yiling Huang, Yujie Wang, Yuyue Zhang, Ronghui Xi, Yuanze Li, Jiacheng Liu, Zhongjun Yang, Haihong E

Efficient Federated Learning on Knowledge Graphs via Privacy-preserving Relation Embedding Aggregation (2022.findings-emnlp)

Challenge:	AEGIS examines whether current models can effectively audit AI-generated images in academic papers.
Approach:	They propose a holistic benchmark for forensic analysis of AI-Generated academic ImageS that reveals limitations in academic image forensics.
Outcome:	AEGIS compared with existing benchmarks on seven academic categories and features key advances in forensic analysis.

Copied to clipboard

Kai Zhang, Yu Wang, Hongyi Wang, Lifu Huang, Carl Yang, Xun Chen, Lichao Sun

Benchmarking Robustness of Machine Reading Comprehension Models (2021.findings-acl)

Challenge:	Existing frameworks that share entity embeddings of knowledge graphs (KGs) would incur a severe privacy leakage.
Approach:	They propose a new attack method that aims to recover the original embedding information based on the known entity embeddables of FedE.
Outcome:	The proposed framework can be used to infer whether a specific relation exists in a private client.

Copied to clipboard

Chenglei Si, Ziqing Yang, Yiming Cui, Wentao Ma, Ting Liu, Shijin Wang

Code Reffix: A Benchmark for Reflection-Guided Code Repair with Large Language Models (2026.findings-acl)

Challenge:	Existing benchmarks only evaluate models' robustness under test-time perturbations or adversarial attacks.
Approach:	They propose a model-agnostic benchmark to evaluate models' robustness under adversarial attacks.
Outcome:	The proposed model-agnostic benchmark evaluates models under four different types of adversarial attacks.

Copied to clipboard

Zaiyuan Di, Jianting Chen, Yunxiao Yang, Xiaoying Gao, Li Yang, Zhihao Wang, Yang Xiang

Multimodal Inconsistency Reasoning (MMIR): A New Benchmark for Multimodal Reasoning Models (2025.findings-acl)

Challenge:	Existing benchmarks focus on the repair generation capability of LLMs, lacking fine-grained evaluation of reflection.
Approach:	They propose a benchmark with oracle reflections and a dual-task protocol to decouple evaluation of reflection from repair.
Outcome:	The proposed benchmarks show that underperforming reflection capabilities remain a bottleneck for code repair.

Copied to clipboard

Qianqi Yan, Yue Fan, Hongquan Li, Shan Jiang, Yang Zhao, Xinze Guan, Ching-Chen Kuo, Xin Eric Wang

SimLM: Pre-training with Representation Bottleneck for Dense Passage Retrieval (2023.acl-long)

Challenge:	Existing Multimodal Large Language Models (MLLMs) are predominantly trained on consistent visual-textual inputs, leaving open the question of whether they can handle semantic mismatches in layout-rich content.
Approach:	They propose to use multimodal inconsistency reasoning to assess MLLMs' ability to reason about semantic mismatches in webpages, presentation slides, and posters.
Outcome:	The proposed model outperforms open-source models in detecting inconsistencies in webpages, presentation slides, and posters while remaining vulnerable to inconsistent errors.

Copied to clipboard

Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, Furu Wei

Enhancing Machine Translation with Self-Supervised Preference Data (2025.acl-long)

Challenge:	SimLM uses a simple bottleneck architecture that learns to compress the passage information into a dense vector through self-supervised pre-training.
Approach:	They propose a simple yet effective pre-training method for dense passage retrieval that learns to compress the passage information into a dense vector through self-supervised pre-tuning.
Outcome:	The proposed method outperforms multi-vector approaches on large-scale passage retrieval datasets and shows significant improvements over baselines.

Copied to clipboard

Haoxiang Sun, Ruize Gao, Pei Zhang, Baosong Yang, Rui Wang

CLIPErase: Efficient Unlearning of Visual-Textual Associations in CLIP (2025.acl-long)

Challenge:	Current approaches to constructing preference data rely on human annotations.
Approach:	They propose a framework which efficiently constructs translation preference data for iterative training.
Outcome:	The proposed framework improves translation preference data on large language models.

Copied to clipboard

Tianyu Yang, Lisen Dai, Xiangqi Wang, Minhao Cheng, Yapeng Tian, Xiangliang Zhang

Raccoon: Prompt Extraction Benchmark of LLM-Integrated Applications (2024.findings-acl)

Challenge:	MU has gained significant attention as a means to remove the influence of specific data from a trained model without requiring full retraining.
Approach:	They propose a novel approach that disentangles and selectively forgets both visual and textual associations, ensuring that unlearning does not compromise model performance.
Outcome:	Experiments on CIFAR-100, Flickr30K, and Conceptual 12M show that CLIPErase effectively removes designated associations from multimodal samples in downstream tasks while preserving model performance on retain set.

Copied to clipboard

Junlin Wang, Tianyi Yang, Roy Xie, Bhuwan Dhingra

Semi-Supervised Disfluency Detection (C18-1)

Challenge:	Recent advances in Large Language Models (LLMs) have markedly shifted the landscape of AI, enabling these models to tackle complex, real-world tasks through natural language instructions.
Approach:	They propose a benchmark which evaluates a model's susceptibility to prompt extraction attacks by employing a dual approach to evaluate the effectiveness of existing defenses and the resilience of the models.
Outcome:	The proposed benchmark assesses models under both defenseless and defended scenarios, employing a dual approach to evaluate the effectiveness of existing defenses and the resilience of the models.

Copied to clipboard

Feng Wang, Wei Chen, Zhen Yang, Qianqian Dong, Shuang Xu, Bo Xu

Learning Transition Patterns by Large Language Models for Sequential Recommendation (2025.coling-main)

Challenge:	Detecting disfluency can be difficult because of the flexible nature of reparandum structure and the lack of a nested structure.
Approach:	They propose a semi-supervised approach which extracts hidden features from self-attention without any Recurrent Neural Network (RNN) or Convolutional Neural Net (CNN).
Outcome:	The proposed approach improves over baselines by using unlabelled data . identifying and removing non-fluent factors would help to improve spontaneous speech quality .

Copied to clipboard

Jianyang Zhai, Zi-Feng Mai, Dongyi Zheng, Chang-Dong Wang, Xiawu Zheng, Hui Li, Feidiao Yang, Yonghong Tian

Cognitive Alpha Mining via LLM-Driven Code-Based Evolution (2026.acl-long)

Challenge:	Extensive experiments on six real-world datasets show our approach outperforms the best baselines by 7.33% in NDCG@10, 4.65% in Recall@10 and 8.42% in MRR.
Approach:	They propose a framework for mapping sequential item texts to sequential item IDs that incorporates multi-query input and item linear projection to model conditional probability distribution of items.
Outcome:	The proposed framework outperforms baseline models on six real-world datasets by 7.33% and 4.65% respectively.

Copied to clipboard

Fengyuan Liu, Yi Huang, Sichun Luo, Yuqi Wang, Yazheng Yang, Xinye Li, Zefa Hu, Junlan Feng, Qi Liu

Speech Discrete Tokens or Continuous Features? A Comparative Analysis for Spoken Language Understanding in SpeechLLMs (2025.emnlp-main)

Challenge:	Existing approaches to finding effective predictive signals from financial data are limited by their complexity and low signal-to-noise ratio.
Approach:	They propose a framework that combines code-level alpha representation with LLM-driven reasoning and evolutionary search.
Outcome:	The proposed framework combines code-level alpha representation with LLM-driven reasoning and evolutionary search.

Copied to clipboard

Dingdong Wang, Junan Li, Mingyu Cui, Dongchao Yang, Xueyuan Chen, Helen M. Meng

AdaPrompt: Adaptive Model Training for Prompt-based NLP (2022.findings-emnlp)

Challenge:	Speech Large Language Models (SpeechLLMs) have emerged as dominant speech processing approaches.
Approach:	They compare self-supervised learning-based discrete and continuous features . they compare performance across six spoken language understanding-related tasks .
Outcome:	The proposed models outperform discrete tokens and continuous features in six spoken language understanding-related tasks.

Copied to clipboard

Yulong Chen, Yang Liu, Li Dong, Shuohang Wang, Chenguang Zhu, Michael Zeng, Yue Zhang

RACC: Regret-Aware Confidence Calibration for Consistent Masked Discrete Diffusion Decoding (2026.findings-acl)

Challenge:	Prompt-based learning can tackle zero-shot and few-shot NLP tasks . authors propose a method that makes use of pre-trained language models .
Approach:	They propose to map NLP tasks into natural language prompts, which are then filled by pre-trained language models.
Outcome:	The proposed method outperforms standard prompt-based methods in few-shot settings.

Copied to clipboard

Qinglin Zeng, Jusheng Zhang, Jing Yang, Ningyuan Liu, Keze Wang

On the Language Coverage Bias for Neural Machine Translation (2021.findings-acl)

Challenge:	Masked Discrete Diffusion Models (MDMs) enable parallel generation via iterative refinement, but their current decoding paradigms are static and myopic.
Approach:	They propose a Regret-Aware Confidence Calibration framework that aligns decoding decisions with the model’s latent self-correction capabilities.
Outcome:	The proposed framework aligns decoding decisions with model’s latent self-correction capabilities.

Copied to clipboard

Shuo Wang, Zhaopeng Tu, Zhixing Tan, Shuming Shi, Maosong Sun, Yang Liu

An Iterative Associative Memory Model for Empathetic Response Generation (2024.acl-long)

Challenge:	Language coverage bias is important for neural machine translation because of the target-original training data.
Approach:	They propose two approaches to alleviate the language coverage bias problem by explicitly distinguishing between the source-and target-original training data.
Outcome:	The proposed methods improve translation tasks on both back-and forward-translation and their tagged variants.

Copied to clipboard

Zhou Yang, Zhaochun Ren, Wang Yufeng, Haizhou Sun, Chao Chen, Xiaofei Zhu, Xiangwen Liao

Small Models are Valuable Plug-ins for Large Language Models (2024.findings-acl)

Challenge:	Existing methods for empathetic response generation ignore the associated words between dialogue utterances.
Approach:	They propose an iterative associative memory model to capture associated words between dialogue utterances and situations, dialogue history, and a memory module for storing associated words.
Outcome:	The proposed model captures key words between dialogue utterances and situations, dialogue history, and a memory module, thereby accurately and nuancedly comprehending the utterables.

Copied to clipboard

Canwen Xu, Yichong Xu, Shuohang Wang, Yang Liu, Chenguang Zhu, Julian McAuley

Gold-Medal-Level Olympiad Geometry Solving with Efficient Heuristic Auxiliary Constructions (2026.acl-long)

Challenge:	Large-scale pre-trained language models are difficult to fine-tune due to their huge weights and limited context length.
Approach:	They propose an approach which allows black-box LLMs to work with locally fine-tuned smaller models, resulting in superior performance on supervised tasks.
Outcome:	The proposed approach overcomes the challenges of poor performance and instability of In-Context Learning (ICL) while reducing the complexity of in-context learning.

Copied to clipboard

Boyan Duan, Xiao Liang, Shuai Lu, Yaoxiang Wang, Yelong Shen, Kai-Wei Chang, Ying Nian Wu, Mao Yang, Weizhu Chen, Yeyun Gong

PibE-MPP: A Play-it-by-Ear Masking Performance Plug-in for LLMs (2026.findings-acl)

Challenge:	Existing methods for geometry theorem proving in Euclidean geometry are challenging and require a neural network to perform.
Approach:	They propose a method for adding auxiliary points in geometry that runs on CPUs without relying on neural network-based inference.
Outcome:	The proposed method achieves silver-medal-level human performance on IMO-30 benchmark.

Copied to clipboard

Mengwei Wang, Simin Niu, Xun Liang, Yuefeng Ma, Sensen Zhang, Jiawei Yang, Shichao Song, Hanyu Wang, Huayi Lai

KG-FLIP: Knowledge-guided Fashion-domain Language-Image Pre-training for E-commerce (2023.acl-industry)

Challenge:	Random masking is a widely adopted classic baseline in large language models (LLMs).
Approach:	They propose a play-it-by-ear masking performance plug-in which enables LLMs to adaptively select masking target combinations for each task.
Outcome:	The proposed performance plug-in retains the advantages and mitigates the drawbacks of random masking in large language models.

Copied to clipboard

Qinjin Jia, Yang Liu, Daoping Wu, Shaoyuan Xu, Huidong Liu, Jinmiao Fu, Roland Vollgraf, Bryan Wang

MR-ALIGN: Meta-Reasoning Informed Factuality Alignment for Large Reasoning Models (2026.findings-acl)

Challenge:	Various visionlanguage pre-training (VLP) models learn cross-modal alignment from large-scale well-aligned image-text datasets without leveraging external knowledge.
Approach:	They propose a knowledge-guided fashion-domain language-image pre-training framework that learns fine-grained representations in e-commerce domain and utilizes external knowledge to improve the pre-train efficiency.
Outcome:	The proposed framework outperforms state-of-the-art models on Amazon and Fashion-Gen datasets by large margins.

Copied to clipboard

Xinming Wang, Jian Xu, Bin Yu, Sheng Lian, yi Chen, Boran Wang, Yingjian Zhu, Hongzhu Yi, Hong-Ming Yang, Han Hu, Cheng-Lin Liu, Xu-Yao Zhang

Learning to Generate Question by Asking Question: A Primal-Dual Approach with Uncommon Word Generation (2022.emnlp-main)

Challenge:	Large reasoning models (LRMs) show strong capabilities in complex reasoning, yet their marginal gains on evidence-dependent factual questions are limited.
Approach:	They propose a Meta-Reasoning informed alignment framework that quantifies state-transition probabilities along the model’s thinking process and constructs a transition-aware implicit reward that reinforces beneficial reasoning patterns while suppressing defective ones at the atomic thinking segments.
Outcome:	Empirical evaluations of four factual QA datasets and one long-form factuality benchmark show that MR-ALIGN consistently improves accuracy and truthfulness while reducing misleading reasoning.

Copied to clipboard

Qifan Wang, Li Yang, Xiaojun Quan, Fuli Feng, Dongfang Liu, Zenglin Xu, Sinong Wang, Hao Ma

OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models (2025.acl-long)

Challenge:	Existing automatic question generation methods focus on encoding passage and answer to generate question.
Approach:	They propose an automatic question generation approach which integrates question generation with its dual problem, question answering, into a unified primal-dual framework.
Outcome:	The proposed approach outperforms existing methods on SQuAD and HotpotQA benchmarks.

Copied to clipboard

Siming Huang, Tianhao Cheng, Jason Klein Liu, Weidi Xu, Jiaran Hao, Liuyihan Song, Yang Xu, Jian Yang, Jiaheng Liu, Chenchen Zhang, Linzheng Chai, Ruifeng Yuan, Xianzhen Luo, Qiufeng Wang, YuanTao Fan, Qingfu Zhu, Zhaoxiang Zhang, Yang Gao, Jie Fu, Qian Liu, Houyi Li, Ge Zhang, Yuan Qi, Xu Yinghui, Wei Chu, Zili Wang

Filling the Image Information Gap for VQA: Prompting Large Language Models to Proactively Ask Questions (2023.findings-emnlp)

Challenge:	Code LLMs lack reproducible data pipelines and training protocols for reproducible advancements in code intelligence.
Approach:	They propose a top-tier code LLM that releases model weights and inference code . reproducible data pipelines, rigorous experimental ablation results and training protocols are included .
Outcome:	The proposed model achieves comparable performance to leading models and serves as an "open cookbook" reproducible training data, rigorous experimental ablation results, and detailed training protocols are also included in the model.

Copied to clipboard

Ziyue Wang, Chi Chen, Peng Li, Yang Liu

Chinese MentalBERT: Domain-Adaptive Pre-training on Social Media for Chinese Mental Health Text Analysis (2024.findings-acl)

Challenge:	Large Language Models (LLMs) demonstrate impressive reasoning ability and the maintenance of world knowledge in natural language tasks.
Approach:	They propose a framework that enables LLMs to ask relevant questions to uncover more details in the image, along with filters for refining the generated information.
Outcome:	The proposed framework boosts the performance of baseline methods by 2.15% on OK-VQA and achieves consistent improvements across different LLMs.

Copied to clipboard

Wei Zhai, Hongzhi Qi, Qing Zhao, Jianqiang Li, Ziqi Wang, Han Wang, Bing Yang, Guanghui Fu

LOTUS: A Leaderboard for Detailed Image Captioning from Quality to Societal Bias and User Preferences (2025.acl-industry)

Challenge:	Existing models for language analysis are inadequate for specialized domains like psychology.
Approach:	They have enriched a Chinese social media database with psychological lexicons to enhance its applicability to psychological text analysis.
Outcome:	The proposed model performed better on six public datasets and provided relevant predictions given the masked sentences.

Copied to clipboard

Yusuke Hirota, Boyi Li, Ryo Hachiuma, Yueh-Hua Wu, Boris Ivanovic, Marco Pavone, Yejin Choi, Yu-Chiang Frank Wang, Yuta Nakashima, Chao-Han Huck Yang

Customizing In-context Learning for Dynamic Interest Adaption in LLM-based Recommendation (2025.findings-acl)

Challenge:	Large Vision-Language Models (LVLMs) have transformed image captioning . existing evaluations lack standardized criteria and a standardized evaluation framework .
Approach:	They propose a leaderboard for evaluating detailed captions that addresses three main gaps in existing evaluations: lack of standardized criteria, bias-aware assessments, and user preference considerations.
Outcome:	The proposed model evaluates caption quality, descriptiveness, risks, and societal biases while tailoring criteria to user preferences.

Copied to clipboard

Keqin Bao, Ming Yan, Yang Zhang, Jizhi Zhang, Wenjie Wang, Fuli Feng, Xiangnan He

SafeConf: A Confidence-Calibrated Safety Self-Evaluation Method for Large Language Models (2025.findings-emnlp)

Challenge:	Existing Large Language Model (LLM)-based recommender systems face challenges to adapt to dynamic user interests without any model-level updates.
Approach:	They propose a framework that establishes recommendation-oriented in-context learning by structuring recent user interactions and current inputs into ICL formats.
Outcome:	The proposed model adapts to dynamic user interests without model updates without any model updates and is available online at https://anonymous.4open.science/r/RecICL-8003.

Copied to clipboard

Bo Zhang, Cong Gao, Linkang Yang, Bingxu Han, Minghao Hu, Zhunchen Luo, Guotong Geng, Xiaoying Bai, Jun Zhang, Wen Yao, Zhong Wang

Revisiting Weak-to-Strong Generalization in Theory and Practice: Reverse KL vs. Forward KL (2025.findings-acl)

Challenge:	Large language models (LLMs) have many advantages but they also pose significant safety risks.
Approach:	They propose a method to enhance the safety self-evaluation capability of LLMs . they perform semantic mutations on the original safety evaluation questions .
Outcome:	The proposed method improves safety self-evaluation accuracy by 5.86% and 7.79% over baseline methods on Chinese and English datasets.

Copied to clipboard

Wei Yao, Wenkai Yang, Ziqiao Wang, Yankai Lin, Yong Liu

Linguistics & Cognitive NLP

Challenge:	Weak-to-strong generalization is a promising approach to guide stronger systems, but its effectiveness is constrained by the inherent imperfections of weak model supervision.
Approach:	They propose a theoretically grounded approach that replaces forward KL divergence with reverse KL, which prioritizes high-confidence predictions.
Outcome:	The proposed approach replaces forward KL divergence with reverse KL, reducing the influence of unreliable weak supervision.

Rethinking Word-Level Auto-Completion in Computer-Aided Translation (2023.emnlp-main)

Copied to clipboard

Xingyu Chen, Lemao Liu, Guoping Huang, Zhirui Zhang, Mingming Yang, Shuming Shi, Rui Wang

TemplateGEC: Improving Grammatical Error Correction with Detection Template (2023.acl-long)

Challenge:	Existing models for word-level auto-completion (WLAC) do not meet the criterion of good auto-completes.
Approach:	They propose a measurable criterion to address the question: what kind of words are good auto-completions? they propose an approach to enhance WLAC performance by promoting adherence to the cri-terion.
Outcome:	The proposed approach outperforms the top-performing system submitted to the WLAC shared tasks in WMT2022 while using significantly smaller model sizes.

Copied to clipboard

Yinghao Li, Xuebo Liu, Shuo Wang, Peiyuan Gong, Derek F. Wong, Yang Gao, Heyan Huang, Min Zhang

How do Visual Attributes Influence Web Agents? A Comprehensive Evaluation of User Interface Design Factors (2026.findings-acl)

Challenge:	Existing methods for grammatical error correction (GEC) have been developed.
Approach:	They propose a method which integrates the detection labels from a Seq2Edit model to construct a template as the input.
Outcome:	The proposed method can perform human-in-the-loop error correction tasks.

Copied to clipboard

Kuai Yu, Naicheng Yu, Han Wang, Rui Yang, Huan Zhang

Mixup Decoding for Diverse Machine Translation (2021.findings-emnlp)

Challenge:	Existing studies on the effect of environmental variation on web agents have focused on robustness to adversarial attacks with less attention to agents’ preferences in benign scenarios.
Approach:	They propose a controlled evaluation pipeline to quantify how visual attributes influence web-agent decision-making by comparing variants and browsing interactions.
Outcome:	Extensive experiments on 8 variant families, 5 real-world websites and 4 representative web agents show that background color contrast, item size, position, and card clarity have a strong influence on agents’ actions, whereas font styling, text color, and item image clarity exhibit minor effects.

Copied to clipboard

Jicheng Li, Pengzhi Gao, Xuanfu Wu, Yang Feng, Zhongjun He, Hua Wu, Haifeng Wang

GRV-KBQA: A Three-Stage Framework for Knowledge Base Question Answering with Decoupled Logical Structure, Semantic Grounding and Structure-Aware Validation (2025.findings-emnlp)

Challenge:	Existing methods for generating multiple translations for source and target languages neglect the one-to-many mapping between the source and the target languages.
Approach:	They propose a method to generate different translations for the input sentence by linearly interpolating it with different sentence pairs sampled from the training corpus during decoding.
Outcome:	Experiments on WMT’16 en-ro, WMT'14 en de, and WMT ‘17 zh-en show that the proposed method outperforms all previous diverse machine translation methods.

Copied to clipboard

Yuhang Tian, Pan Yang, Dandan Song, Zhijing Wu, Hao Wang

DenseLoRA: Dense Low-Rank Adaptation of Large Language Models (2025.acl-long)

Challenge:	Existing methods for Knowledge Base Question Answering generate non-executable queries and inefficiencies in query execution.
Approach:	a framework that decouples logical structure generation from semantic grounding is proposed . the framework explicitly enforces KB constraints to improve alignment between generated logical forms and KB structures.
Outcome:	GRV-KBQA decouples logical structure generation from semantic grounding and incorporates structure-aware validation to enhance accuracy.

Copied to clipboard

Lin Mu, Xiaoyu Wang, Li Ni, Yang Li, Zhize Wu, Peiquan Jin, Yiwen Zhang

WebSynthesis: World Model-Guided Monte Carlo Tree Search for Efficient WebAgent Trajectory Synthesis (2026.acl-long)

Challenge:	Low-rank adaptation (LoRA) is an efficient approach for adapting large language models (LLMs) but many of the weights in these matrices are redundant, leading to inefficiencies in parameter utilization.
Approach:	They propose a low-rank adaptation approach that fine-tunes two low-ranked matrices and adapts them through a dense low-Rank matrix, improving parameter utilization and adaptation efficiency.
Outcome:	The proposed approach achieves 83.8% accuracy with only 0.01% of trainable parameters compared to LoRA's 80.8% with 0.70% of trainability parameters on LLaMA3-8B.

Copied to clipboard

Yifei Gao, Junhong Ye, Yifan Yang, Jiaqi Wang, Yi Zhang, Zhang Ruichen, Jitao Sang

Large Language Models Can Be Contextual Privacy Protection Learners (2024.emnlp-main)

Challenge:	Recent advances in large language models have enabled increasingly capable web agents . however, training such agents at scale still relies on high-quality interaction trajectories that are difficult to obtain at scale.
Approach:	They propose a framework for scalable trajectory synthesis that simulates state transitions without network dependencies and integrates Monte Carlo Tree Search to enable reversible exploration over the simulated state space.
Outcome:	Experiments on WebArena, WebVoyager, and Mind2Web-Online show that agents trained exclusively on synthesized trajectories outperform those trained on real-world data.

Copied to clipboard

Yijia Xiao, Yiqiao Jin, Yushi Bai, Yue Wu, Xianjun Yang, Xiao Luo, Wenchao Yu, Xujiang Zhao, Yanchi Liu, Quanquan Gu, Haifeng Chen, Wei Wang, Wei Cheng

PlaM: Training-Free Plateau-Guided Model Merging for Better Visual Grounding in MLLMs (2026.findings-acl)

Challenge:	Large Language Models (LLMs) have demonstrated remarkable linguistic comprehension and generation capability, but when applied to specialized industries, they face challenges such as hallucination, insufficient domain knowledge, and failing to incorporate the latest domain knowledge.
Approach:	They propose a paradigm for fine-tuning LLMs that effectively injects domain-specific knowledge while safeguarding inference-time data privacy.
Outcome:	The proposed model protects private data while enhancing the model's knowledge.

Copied to clipboard

Zijing Wang, YongKang Liu, Mingyang Wang, Ercong Nie, Deyuan Chen, Zhengjie Zhao, Shi Feng, Daling Wang, Xiaocui Yang, Yifei Zhang, Hinrich Schuetze

MUG: Interactive Multimodal Grounding on User Interfaces (2024.findings-eacl)

Challenge:	Multimodal instruction fine-tuning degrades textual reasoning capability, undermining multimodal performance.
Approach:	They propose a plateau-guided model merging method that selectively injects base language model parameters into MLLMs to mitigate this degradation.
Outcome:	The proposed framework reduces multimodal instruction fine-tuning degradation by incorporating a plateau-guided model merging method into MLLMs.

Copied to clipboard

Tao Li, Gang Li, Jingjie Zheng, Purple Wang, Yang Li

Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization (2024.acl-long)

Challenge:	Prior studies modeled multimodal UI grounding in one round, but such an interaction is inherently iterative.
Approach:	They propose a task where a user and an agent collaborate on an interface screen . they use a dataset of 77,820 sequences of human user-agent interaction on mobile interfaces .
Outcome:	The proposed task improves the absolute task completion by 18% over the entire test set and 31% over the challenging split.

Copied to clipboard

Zhexin Zhang, Junxiao Yang, Pei Ke, Fei Mi, Hongning Wang, Minlie Huang

Aligning Large Multimodal Models with Factually Augmented RLHF (2024.findings-acl)

Challenge:	Despite the success of jailbreaking attacks, there is a lack of effort in defending against them.
Approach:	They propose to integrate goal prioritization at both training and inference stages to counteract this conflict between the goals of being helpful and ensuring safety.
Outcome:	The proposed approach reduces the Attack Success Rate (ASR) of jailbreaking from 66.4% to 3.6% for ChatGPT and reduces it from 71.0% to 6.6% for Llama2-13B.

Copied to clipboard

Zhiqing Sun, Sheng Shen, Shengcao Cao, Haotian Liu, Chunyuan Li, Yikang Shen, Chuang Gan, Liangyan Gui, Yu-Xiong Wang, Yiming Yang, Kurt Keutzer, Trevor Darrell

Inference Compute-Optimal Video Vision Language Models (2025.acl-long)

Challenge:	Large Multimodal Models (LMMs) are built across modalities and the misalignment between two modality can result in "hallucination" . developing LMMs faces challenges such as a lack of data and a limited number of data sets.
Approach:	They propose a new algorithm that augments the reward model with additional factual information such as image captions and ground-truth multi-choice options.
Outcome:	The proposed approach improves on the LLaVA-Bench dataset with the 96% performance level of the text-only GPT-4 and an improvement of 60% on MMHAL-BENCH over other baselines.

Copied to clipboard

Peiqi Wang, ShengYun Peng, Xuewen Zhang, Hanchao Yu, Yibo Yang, Lifu Huang, Fujun Liu, Qifan Wang

DiffPO: Diffusion-styled Preference Optimization for Inference Time Alignment of Large Language Models (2025.acl-long)

Challenge:	Using video vision language models, inference costs are often more expensive than finetuning.
Approach:	They investigate the optimal allocation of inference compute across three key scaling factors in video vision language models.
Outcome:	The proposed model configurations are based on three key scaling factors . the results can be applied to real-world tasks and tasks with fixed inference budgets.

Copied to clipboard

Ruizhe Chen, Wenhao Chai, Zhifei Yang, Xiaotian Zhang, Ziyang Wang, Tony Quek, Joey Tianyi Zhou, Soujanya Poria, Zuozhu Liu

Untie the Knots: An Efficient Data Augmentation Strategy for Long-Context Pre-Training in Language Models (2025.acl-long)

Challenge:	Inference-time alignment approaches still face limitations due to policy-specific value functions and latency during the inference phase.
Approach:	They propose an efficient and policy-agnostic preference optimization method that avoids time latency associated with token generation.
Outcome:	The proposed method achieves a favorable trade-off between alignment quality and inference-time latency.

Copied to clipboard

Junfeng Tian, Da Zheng, Yang Chen, Rui Wang, Colin Zhang, Debing Zhang

Enhancing Event Causality Identification with Event Causal Label and Event Pair Interaction Graph (2023.findings-acl)

Challenge:	Large language models (LLMs) have prioritized expanding the context window from which they can incorporate more information.
Approach:	They propose a data augmentation strategy to enable large language models to gain long-context capabilities without the need to modify existing data mixture.
Outcome:	The proposed model outperforms existing models on 20 billion tokens and achieves 75% and 84.5% accuracy on RULER at 128K context length.

Copied to clipboard

Ruili Pu, Yang Li, Suge Wang, Deyu Li, Jianxing Zheng, Jian Liao

LTRS: Improving Word Sense Disambiguation via Learning to Rank Senses (2025.coling-main)

Challenge:	Existing methods for event causality identification (ECI) do not consider event causal label information and interaction information between event pairs.
Approach:	They propose a framework to enrich the representation of event pairs by introducing the event causal label information and the interaction information between event pairs.
Outcome:	The proposed framework outperforms state-of-the-art methods on two benchmark datasets.

Copied to clipboard

Hansi Wang, Yue Wang, Qiliang Liang, Yang Liu

Entity Resolution in Open-domain Conversations (2021.naacl-industry)

Challenge:	Conventional training strategies only consider predefined senses for target words and learn each of them from relatively limited instances, neglecting the influence of similar ones.
Approach:	They propose a method to rank senses to improve the task of word Sense Disambiguation (WSD) by ranking an expanded list of sense definitions.
Outcome:	The proposed method achieves a SOTA F1 score of 79.6% in Chinese WSD and shows faster convergence than previous methods.

Copied to clipboard

Mingyue Shang, Tong Wang, Mihail Eric, Jiangning Chen, Jiyang Wang, Matthew Welch, Tiantong Deng, Akshay Grewal, Han Wang, Yue Liu, Yang Liu, Dilek Hakkani-Tur

CIRAG: Construction–Integration Retrieval and Adaptive Generation for Multi-hop Question Answering (2026.acl-long)

Challenge:	Recent work on incorporating external knowledge into the response generation models has attracted great interest.
Approach:	They propose a neural entity linking approach to incorporate external knowledge into the response generation models to improve the relevancy of retrieved knowledge.
Outcome:	The proposed approach outperforms the baseline model by 62.8% relative to the baseline.

Copied to clipboard

Zili Wei, Yilin Wang, Xiaocui Yang, Shi Feng, Weidong Bao, Daling Wang, Zihan Wang, Yifei Zhang

How Is LLM Reasoning Distracted by Irrelevant Context? An Analysis Using a Controlled Benchmark (2025.emnlp-main)

Challenge:	Existing methods for iterative retrieval-augmented generation (iRAG) suffer from greedy single-path expansion and granularity–demand mismatch .
Approach:	They propose a model that constructs candidate triples and history-conditionally integrates them to distill core triples to generate the next-hop query.
Outcome:	The proposed model mitigates the greedy single-path expansion and granularity–demand mismatch by preserving multiple plausible evidence chains.

Copied to clipboard

Minglai Yang, Ethan Huang, Liang Zhang, Mihai Surdeanu, William Yang Wang, Liangming Pan

SportQA: A Benchmark for Sports Understanding in Large Language Models (2024.naacl-long)

Challenge:	Prior work has not explored the mechanisms underlying this sensitivity.
Approach:	They propose a synthetic benchmark to evaluate Large Language Models’ reasoning robustness against systematically controlled irrelevant context (IC).
Outcome:	The proposed model improves in-distribution and out-of-disttribution scenarios while training with strong distractors.

Copied to clipboard

Haotian Xia, Zhengbang Yang, Yuqing Wang, Rhys Tracy, Yun Zhao, Dongdong Huang, Zezhi Chen, Yan Zhu, Yuan-fang Wang, Weining Shen

Bridging the Gap between Pre-Training and Fine-Tuning for Commonsense Generation (2023.findings-eacl)

Challenge:	SportQA is a benchmark specifically designed for evaluating Large Language Models (LLMs) sports knowledge is characterized by its fast pace, variety of types, abundance of strategies, and rich player narratives .
Approach:	They propose a benchmark specifically designed for evaluating Large Language Models in the context of sports understanding.
Outcome:	The proposed benchmark aims to bridge the gap between existing and specialized benchmarks in sports understanding.

Copied to clipboard

Haoran Yang, Yan Wang, Piji Li, Wei Bi, Wai Lam, Chen Xu

TAKE: Topic-shift Aware Knowledge sElection for Dialogue Generation (2022.coling-1)

Challenge:	Existing methods focusing on this task usually concatenate the concatened concepts words as the inputs of a pre-trained language model (PLM) however, in pre-training, the input is often corrupted sentences with correct word order.
Approach:	They propose a two-stage framework to improve the ability of pre-trained language models to deal with masked sentences with incorrect word order and a special token to make the input distribution more similar to the one used in pre-training.
Outcome:	The proposed method is able to generate a sentence containing all given concepts and correctly describe the relations between concepts.

Copied to clipboard

Chenxu Yang, Zheng Lin, Jiangnan Li, Fandong Meng, Weiping Wang, Lanrui Wang, Jie Zhou

UltraLink: An Open-Source Knowledge-Enhanced Multilingual Supervised Fine-tuning Dataset (2024.acl-long)

Challenge:	Recent work finds that realizing who holds the initiative can help select knowledge . however, there is a strong semantic transition between two rounds, probably leading to initiative misjudgment .
Approach:	They propose a topic-shift Aware Knowledge sElector(TAKE) model which locates relevant parts from dialogue history to improve knowledge selection.
Outcome:	The proposed model outperforms baseline models on the WoW.

Copied to clipboard

Haoyu Wang, Shuo Wang, Yukun Yan, Xujia Wang, Zhiyu Yang, Yuzhuang Xu, Zhenghao Liu, Liner Yang, Ning Ding, Xu Han, Zhiyuan Liu, Maosong Sun

In-context Learning for Few-shot Multimodal Named Entity Recognition (2023.findings-emnlp)

Challenge:	Open-source large language models (LLMs) have gained strength across diverse fields, but the majority of studies focus on English.
Approach:	They propose a knowledge-grounded data augmentation approach to elicit more language-specific knowledge of LLMs by enhancing their ability to serve users from different countries.
Outcome:	The proposed method can prune the language-agnostic supervised fine-tuning dataset without any performance degradation.

Copied to clipboard

Chenran Cai, Qianlong Wang, Bin Liang, Bing Qin, Min Yang, Kam-Fai Wong, Ruifeng Xu

Noise Robust Named Entity Understanding for Voice Assistants (2021.naacl-industry)

Challenge:	Existing methods for named entity recognition are time-consuming and laborintensive.
Approach:	They propose a few-shot multimodal named entity recognition task that uses few examples to locate and identify named entities for a text-image pair.
Outcome:	The proposed framework outperforms baselines under several few-shot settings.

Copied to clipboard

Deepak Muralidharan, Joel Ruben Antony Moniz, Sida Gao, Xiao Yang, Justine Kao, Stephen Pulman, Atish Kothari, Ray Shen, Yinying Pan, Vivek Kaul, Mubarak Seyed Ibrahim, Gang Xiang, Nan Dun, Yidan Zhou, Andy O, Yuan Zhang, Pooja Chitkara, Xuan Wang, Alkesh Patel, Kushal Tayal, Roger Zheng, Peter Grasch, Jason D Williams, Lin Li

Optimizing NLU Reranking Using Entity Resolution Signals in Multi-domain Dialog Systems (2021.naacl-industry)

Challenge:	Named Entity Recognition and Entity Linking are challenging for voice assistants . utterances are relatively short, so there is not much context to help disambiguate .
Approach:	They propose a Named Entity Understanding system that combines NER and EL in a joint reranking module.
Outcome:	The proposed framework improves NER accuracy by up to 3.13% and EL accuracy by 3.6% in F1 score . it also leads to better accuracies in other natural language understanding tasks .

Copied to clipboard

Tong Wang, Jiangning Chen, Mohsen Malmir, Shuyan Dong, Xin He, Han Wang, Chengwei Su, Yue Liu, Yang Liu

A Probabilistic Toolkit for Multi-grained Word Segmentation in Chinese (2025.coling-demos)

Challenge:	In dialog systems, the Natural Language Understanding component makes the interpretation decision before the mentioned entities are resolved.
Approach:	They propose to leverage Entity Resolution (ER) features in NLU reranking to learn model weights . they propose a score distribution matching method to ensure the models are calibrated .
Outcome:	The proposed approach outperforms the baseline model on multiple domain evaluations.

Copied to clipboard

Xi Ma, Yang Hou, Xuebin Wang, Zhenghua Li

SeedBench: A Multi-task Benchmark for Evaluating Large Language Models in Seed Science (2025.acl-long)

Challenge:	Existing tools for word segmentation are based on different linguistic theories or target different scenarios.
Approach:	They propose a probabilistic toolkit for multi-grained word segmentation in Chinese . they adopt semi-Markov CRF for single-grain word segmenting (SWS) .
Outcome:	The proposed approach can produce marginal probabilities of words during inference and significantly improve performance in the cross-domain scenario.

Copied to clipboard

Jie Ying, Zihong Chen, Zhefan Wang, Wanli Jiang, Chenyang Wang, Zhonghang Yuan, Haoyang Su, Huanjun Kong, Fan Yang, Nanqing Dong

Modelling Long-distance Node Relations for KBQA with Global Dynamic Graph (2020.coling-main)

Challenge:	Seed science is essential for modern agriculture, but its application in seed science remains limited due to a shortage of experts and limited availability of online resources.
Approach:	They evaluate 26 leading large language models and compare them against a set of benchmarks . they find that there is a gap between the power of LLMs and real-world seed science problems .
Outcome:	The new seed benchmark highlights the gap between the power of large language models and real-world seed science problems.

Copied to clipboard

Xu Wang, Shuai Zhao, Jiale Han, Bo Cheng, Hao Yang, Jianchang Ao, Zhenzi Li

Weights-Rotated Preference Optimization for Large Language Models (2025.emnlp-main)

Challenge:	Existing studies rely on deep graph neural networks (GNNs) to capture rich structural information, but they lack the structural information needed for QA.
Approach:	They propose a framework which captures structural information from KBs and models long-distance node relations from two perspectives.
Outcome:	The proposed framework models long-distance node relations from two perspectives . it is based on two widely used multi-hop KBQA datasets .

Copied to clipboard

Chenxu Yang, Ruipeng Jia, Mingyu Zheng, Naibin Gu, Zheng Lin, Siyuan Chen, Weichong Yin, Hua Wu, Weiping Wang

Benchmarking the Fine-Grained Discriminability in Image-Text Retrieval via Controlled Contrastive Differences (2026.findings-acl)

Challenge:	Existing methods to align large language models with high reward hacking are limited by the complexity of the parameter space and the complexity.
Approach:	They propose a weights-rotated preference optimization algorithm that constrains the output layer logits with the KL divergence inherited from DPO and fine-tunes the intermediate hidden states.
Outcome:	The proposed algorithm achieves a 3.27-point improvement on AlpacaEval 2 and surpasses the best baseline by 6.2 to 7.5 points on MT-Bench with merely 0.015% of the trainable parameters.

Copied to clipboard

Zhen Wang, Xi Zhou, Yating Yang, Bo Ma, Lei Wang, Rui Dong, Azmat Anwar, Siru Miao

What Have We Achieved on Text Summarization? (2020.emnlp-main)

Challenge:	Existing cross-modal image-text retrieval models often retrieve samples with inconsistent details.
Approach:	They propose two fine-grained image-text retrieval benchmarks that incorporate extensive contrastive samples with one controlled contrastive difference from its anchor.
Outcome:	Extensive experiments show that contrastive samples can significantly degrade retrieval performance.

Copied to clipboard

Dandan Huang, Leyang Cui, Sen Yang, Guangsheng Bao, Kun Wang, Jun Xie, Yue Zhang

ABC-Bench: Benchmarking Agentic Backend Coding in Real-World Development (2026.findings-acl)

Challenge:	Existing methods for text summarization have been investigated, but there are still gaps between them and human professionals.
Approach:	They analyze 8 major sources of errors on 10 representative summarization models manually.
Outcome:	Aiming to gain more understanding of summarization systems with respect to their strengths and limitations on a fine-grained syntactic and semantic level, we use 8 major sources of errors on 10 representative summarizing models.

Copied to clipboard

Jie Yang, Honglin Guo, Li Ji, Jiazheng Zhou, Rui Zheng, Zhikai Lei, Shuo Zhang, Zhiheng Xi, Shichun Liu, Yuxin Wang, Bo Wang, Yining Zheng, Tao Gui, Xipeng Qiu

SciAgent: Tool-augmented Language Models for Scientific Reasoning (2024.emnlp-main)

Challenge:	Large Language Models (LLMs) have redefined the role of AI in software engineering . current benchmarks focus on localized code generation, but neglect dynamic, full-process requirements of real-world engineering.
Approach:	They propose a benchmark to evaluate agentic backend coding within a realistic, executable workflow.
Outcome:	The ABC-Bench benchmark evaluates agentic backend coding within a realistic, executable workflow.

Copied to clipboard

Yubo Ma, Zhibin Gou, Junheng Hao, Ruochen Xu, Shuohang Wang, Liangming Pan, Yujiu Yang, Yixin Cao, Aixin Sun

GaLa: Hypergraph-Guided Visual Language Models for Procedural Planning (2026.findings-acl)

Challenge:	SciAgent surpasses other LLMs with the comparable size by more than 8.0% in absolute accuracy.
Approach:	They propose a tool-augmented scientific reasoning setting that supplements LLMs with scalable toolsets and builds a benchmark to evaluate LLM’s abilities with tool assistance.
Outcome:	The proposed setting augments LLMs with scalable toolsets and shifts the focus from pursuing an omniscient problem solver to a proficient tool-user.

Copied to clipboard

Kun Wang, Li Yiming, Mingcheng Qu, Aqiang Zhang, Guang Yang, Tonghua Su

Self-Knowledge Guided Retrieval Augmentation for Large Language Models (2023.findings-emnlp)

Challenge:	Existing methods for procedural planning over-rely on visual inputs and lack structured semantic information.
Approach:	They propose a vision–language framework for multimodal procedural planning that exploits implicit spatial relations and deep semantics encoded in object attributes.
Outcome:	The proposed framework outperforms existing methods in terms of execution success rate, LCS, and planning correctness.

Copied to clipboard

Yile Wang, Peng Li, Maosong Sun, Yang Liu

TInR: Exploring Tool-Internalized Reasoning in Large Language Models (2026.acl-long)

Challenge:	Large language models (LLMs) have shown superior performance without task-specific fine-tuning due to the computational costs.
Approach:	They propose a method which lets LLMs refer to the questions they have previously encountered and adaptively call for external resources when dealing with new questions.
Outcome:	The proposed method outperforms chain-of-thought based and fully retrieval-based methods on multiple datasets and outperformed chain- of-though, chatGPT and InstructGPT.

Copied to clipboard

Qiancheng Xu, Yongqi Li, Fan Liu, Hongru Wang, Min Yang, Wenjie Li

Aligning Agents via Planning: A Benchmark for Trajectory-Level Reward Modeling (2026.acl-long)

Challenge:	Existing methods rely on external tool documentation during reasoning, leading to tool mastery difficulty, tool size constraints, and inference inefficiency.
Approach:	They propose a tool-internalized reasoning framework for unified reasoning and tool usage that integrates external tools into Large Language Models (LLMs) to address these issues, they propose 'tool-internet-based' reasoning.
Outcome:	The proposed method achieves superior performance across in-domain and out-of-domain settings, highlighting its effectiveness and efficiency.

Copied to clipboard

Jiaxuan Wang, Yulan Hu, Wenjin Yang, Zheng Pan, Xin Li, Lan-Zhe Guo

Challenge:	Large Language Models (LLMs) evolve into agentic systems capable of autonomous tool invocation and complex reasoning.
Approach:	They propose a trajectory-level preference benchmark to evaluate judges' ability to distinguish preferred versus distractor agent trajectories in tool-integrated environments.
Outcome:	The proposed benchmark evaluates how well judges distinguish preferred versus distractor agent trajectories in complex tool-using scenarios.

“I Know Who You Are”: Character-Based Features for Conversational Humor Recognition in Chinese (2022.findings-emnlp)

Copied to clipboard

Wenbo Shang, Jiangjiang Zhao, Zezhong Wang, Binyang Li, Fangchun Yang, Kam-Fai Wong

TinyAlign: Boosting Lightweight Vision-Language Models by Mitigating Modal Alignment Bottlenecks (2026.findings-acl)

Challenge:	a recent study has focused on how to recognize punchlines from dialogues, but has neglected character information.
Approach:	They propose a character-fusion conversational humor recognition model that uses character information to recognize punchlines from dialogue.
Outcome:	The proposed model improves performance on Chinese sitcoms corpus and punchline identification.

Copied to clipboard

Yuanze Hu, Xinyu Wang, Zhichao Yang, Gen Li, Ye Qiu, Zhaoxin Fan, Yifan Sun, Wenjun wu, Jin Dong, Xiaotie Deng

EngiBench: A Benchmark for Evaluating Large Language Models on Engineering Problem Solving (2026.findings-acl)

Challenge:	Lightweight Vision-Language Models (VLMs) are indispensable for resource-constrained applications.
Approach:	They propose a framework that retrieves context from a memory bank to enhance alignment . they propose EMI-based approach to align vision and language models .
Outcome:	The proposed framework reduces training loss, accelerates convergence, and enhances task performance with negligible computational overhead.

Copied to clipboard

Xiyuan Zhou, Xinlei Wang, Yirui He, Ruixi Zou, Yang Wu, Yuheng Cheng, Yulu Xie, Wenxuan Liu, Huan Zhao, Yan Xu, Jinjin Gu, Junhua Zhao