Papers by Zhu Wang

Discovering Better Model Architectures for Medical Query Understanding (2021.naacl-industry)

Challenge:	High-quality post-training data is the primary engine driving LLM capabilities . datasets are often treated as isolated artifacts, overlooking their true developmental context .
Approach:	They propose a framework to reconstruct the evolutionary graph of dataset development using data lineage.
Outcome:	The proposed framework characterizes domain-specific structural patterns in Math-oriented datasets and general-domain corpora.

Copied to clipboard

Wei Zhu, Yuan Ni, Xiaoling Wang, Guotong Xie

Challenge:	Neural architecture search (NAS) has attracted intense attention in computer vision and NLP.
Approach:	They propose to use neural architecture search to optimize model architectures for medical questions . they propose to modify the ENAS method to accelerate and stabilize the search results .
Outcome:	The proposed approach outperforms baseline models on two medical questions . it is compared with other NAS methods and shows that it provides the best results .

Rhetorical Device-Aware Sarcasm Detection with Counterfactual Data Augmentation (2025.findings-acl)

Copied to clipboard

Qingqing Hong, Dongyu Zhang, Jiayi Lin, Dapeng Yin, Shuyue Zhu, Junli Wang

Text-to-Distribution Prediction with Quantile Tokens and Neighbor Context (2026.acl-long)

Challenge:	Sarcasm is a complex form of sentiment expression widely used in human daily life.
Approach:	They propose a device-aware sarcasm dataset with counterfactually augmented data to capture its complexity.
Outcome:	The proposed dataset shows that it is more balanced than zero-shot models.

Copied to clipboard

Yilun Zhu, Yuan Zhuang, Nikhita Vedula, Dushyanta Dhyani, Shaoyuan Xu, Mohsen Bayati, Bryan Wang, Shervin Malmasi

Challenge:	Existing methods for text regression lack local grounding and rely on shared representations.
Approach:	They propose a distributional regression model with quantile tokens that insert dedicated quantiles into the input sequence.
Outcome:	The proposed method outperforms baseline models on the inside Airbnb and StackSample datasets.

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

Copied to clipboard

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

Step-level Verifier-guided Hybrid Test-Time Scaling for Large Language Models (2025.emnlp-main)

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

Kaiyan Chang, Yonghao Shi, Chenglong Wang, Hang Zhou, Chi Hu, Xiaoqian Liu, Yingfeng Luo, Yuan Ge, Tong Xiao, JingBo Zhu

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

Challenge:	Recent training-based TTS methods, such as continued reinforcement learning, have surged in popularity, while training-free TTS approaches are gradually fading from prominence.
Approach:	They propose a fine-grained sequential scaling method guided by process verification that integrates training-free TTS methods with other classical parallel scaling methods at the step level.
Outcome:	Experiments on five instruction-tuned large language models (LLMs) show that training-free TTS methods can extend reasoning performance boundaries.

Copied to clipboard

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

Adaptive Spatial and Temporal Redundancy Optimization for Efficient Reasoning in Large Language Models (2026.acl-long)

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

Tianle Chen, Pengyu Cheng, Qiyuan Zhu, Jiacheng Wang, Bei Liu, Hao Gu, Ruijie Shen, Xiaofeng Hou, Sirui Han, Jiacheng Liu

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

Challenge:	Existing research to improve CoT efficiency falls into three categories, each with distinct limitations.
Approach:	They propose a training-free framework that addresses both dimensions of CoT reasoning by applying a progressive precision reduction strategy coupled with an entropy-based confidence mechanism for adaptive termination.
Outcome:	Empirical results show that the proposed framework achieves 11.3 efficiency gain without compromising accuracy.

Copied to clipboard

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

CAN-NER: Convolutional Attention Network for Chinese Named Entity Recognition (N19-1)

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

Yuying Zhu, Guoxin Wang

ScaleBox: Enabling High-Fidelity and Scalable Code Verification for Large Language Models (2026.acl-demo)

Challenge:	Named entity recognition (NER) in Chinese is essential but difficult because of the lack of natural delimiters.
Approach:	They propose to use a Chinese Named Entity Recognition (NER) model that uses a character-based convolutional neural network and a gated recurrent unit to capture the information from adjacent characters and sentence contexts.
Outcome:	The proposed model outperforms existing models on Weibo, MSRA and Chinese Resume datasets.

Copied to clipboard

Jiasheng Zheng, Xin Zheng, Boxi Cao, Pengbo Wang, Zhengzhao Ma, Qiming Zhu, Jiazhen Jiang, Yaojie Lu, Hongyu Lin, Xianpei Han, Le Sun

Syntax-guided Localized Self-attention by Constituency Syntactic Distance (2022.findings-emnlp)

Challenge:	Existing code sandboxes fail to provide accurate verification and efficiency under high-concurrency workloads.
Approach:	They propose a high-fidelity code verification system that provides sandbox feedback for RL training and evaluation.
Outcome:	The proposed system outperforms heuristic-matching baselines on LiveCodeBench and training stability on high-concurrency workloads.

Copied to clipboard

Shengyuan Hou, Jushi Kai, Haotian Xue, Bingyu Zhu, Bo Yuan, Longtao Huang, Xinbing Wang, Zhouhan Lin

Doc2SoarGraph: Discrete Reasoning over Visually-Rich Table-Text Documents via Semantic-Oriented Hierarchical Graphs (2024.lrec-main)

Challenge:	Recent studies have shown that Transformers is implicitly learning syntactic information from data, albeit is highly dependent on the quality and scale of the training data.
Approach:	They propose a syntax-guided localized self-attention model that allows directly incorporating grammar structures from an external constituency parser.
Outcome:	The proposed model improves translation performance on a variety of datasets, from small to large datasets and with different source languages.

Copied to clipboard

Fengbin Zhu, Chao Wang, Fuli Feng, Zifeng Ren, Moxin Li, Tat-Seng Chua

Slot Attention with Value Normalization for Multi-Domain Dialogue State Tracking (2020.emnlp-main)

Challenge:	Existing work on document visual question answering fails to capture the differences and correlations between elements of a document and associated questions.
Approach:	They propose a document-visual question-answering challenge that exploits element-level semantics and employs hierarchical Graph structures to capture differences and correlations between elements.
Outcome:	The proposed model surpasses the state-of-the-art method and large language model in terms of Exact Match (EM) metric, demonstrating exceptional effectiveness.

Copied to clipboard

Yexiang Wang, Yi Guo, Siqi Zhu

Learn and Review: Enhancing Continual Named Entity Recognition via Reviewing Synthetic Samples (2022.findings-acl)

Challenge:	Existing dialogue state tracking approaches rely on ontology already defined, where all slots and their possible values are given.
Approach:	They propose a new architecture to exploit domain ontology by using Slot Attention and Value Normalization . they supplement the annotation of supporting span for MultiWOZ 2.1, which is the shortest span in utterances to support the labeled value.
Outcome:	The proposed architecture exploits ontology and can convert supporting spans to values.

Copied to clipboard

Yu Xia, Quan Wang, Yajuan Lyu, Yong Zhu, Wenhao Wu, Sujian Li, Dai Dai

End-to-End Synthetic Data Generation for Domain Adaptation of Question Answering Systems (2020.emnlp-main)

Challenge:	Existing methods for named entity recognition classify mentions into fixed set of predefined entity types but in many real-world scenarios, new entity types are incrementally involved.
Approach:	They propose a two-stage framework Learn-and-Review for continual named entity recognition to alleviate inter-type confusion.
Outcome:	The proposed framework outperforms the state-of-the-art method on CoNLL-03 and OntoNotes-5.0.

Copied to clipboard

Siamak Shakeri, Cicero Nogueira dos Santos, Henghui Zhu, Patrick Ng, Feng Nan, Zhiguo Wang, Ramesh Nallapati, Bing Xiang

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

Challenge:	Existing approaches for synthetic QA data generation have limited or no success in improving the downstream Reading Comprehension task.
Approach:	They propose an end-to-end approach for synthetic QA data generation using a transformer-based encoder-decoder network that is trained end- to-end to generate both answers and questions.
Outcome:	The proposed model outperforms current state-of-the-art methods in the domain adaptation of QA models.

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

CORD: Bridging the Audio–Text Reasoning Gap via Weighted On-policy Cross-modal Distillation (2026.findings-acl)

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

Hu Jing, Danxiang Zhu, Xianlong Luo, Dan Zhang, Shuwei He, Yishu Lei, Shikun Feng, Hai-Tao Zheng, Jingzhou HE, Yu Sun, Hua Wu, Haifeng Wang

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

Challenge:	Large Audio Language Models (LALMs) exhibit a degradation in knowledge and reasoning capabilities . empirical results show that CORD significantly bridges the audio–text performance gap .
Approach:	They propose a framework that performs online cross-modal self-distillation to bridge the acoustic-semantic gap between LALMs and text-based models.
Outcome:	The proposed framework bridges the acoustic-semantic gap between LALMs and text-based models . it employs on-policy reverse KL divergence with importance-aware weighting .

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

HiCoLoRA: Addressing Context-Prompt Misalignment via Hierarchical Collaborative LoRA for Zero-Shot DST (2026.findings-acl)

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

Shuyu Zhang, Yifan Wei, Xinru Wang, Yanmin Zhu, Yangfan He, Yixuan Weng, Yujie Liu, Bin Li

Retrieval Augmentation for Commonsense Reasoning: A Unified Approach (2022.emnlp-main)

Challenge:	Existing approaches to zero-shot Dialog State Tracking (zs-DST) are inadequate to generalize to new domains without extensive training.
Approach:	They propose a framework that enhances zero-shot slot inference through robust prompt alignment.
Outcome:	Experiments on multi-domain datasets show that HiCoLoRA outperforms baselines, achieving SOTA in zs-DST.

Copied to clipboard

Wenhao Yu, Chenguang Zhu, Zhihan Zhang, Shuohang Wang, Zhuosheng Zhang, Yuwei Fang, Meng Jiang

Sharing, Teaching and Aligning: Knowledgeable Transfer Learning for Cross-Lingual Machine Reading Comprehension (2023.findings-emnlp)

Challenge:	Existing methods for retrieving encyclopedic knowledge lack a large corpus and effective commonsense retriever.
Approach:	They propose a framework for retrieval-augmented commonsense reasoning with a large commonsensense corpus and a commonseense retriever.
Outcome:	The proposed framework outperforms existing methods on commonsense reasoning tasks.

Copied to clipboard

Tingfeng Cao, Chengyu Wang, Chuanqi Tan, Jun Huang, Jinhui Zhu

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

Challenge:	X-STA is a new approach for cross-lingual machine reading comprehension . the variation of answer span positions in different languages makes it difficult to transfer knowledge across languages.
Approach:	They propose a method that leverages an attentive teacher to subtly transfer the answer spans of the source language to the answer output space of the target.
Outcome:	The proposed method outperforms state-of-the-art approaches on three multi-lingual datasets.

Copied to clipboard

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

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

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

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

Mirroring Users: Towards Building Preference-aligned User Simulator with User Feedback in Recommendation (2026.acl-long)

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

Tianjun Wei, Huizhong Guo, Yingpeng Du, Zhu Sun, Huang Chen, Dongxia Wang, Jie Zhang

CodeScope: An Execution-based Multilingual Multitask Multidimensional Benchmark for Evaluating LLMs on Code Understanding and Generation (2024.acl-long)

Challenge:	Large Language Models lack specific task alignment and large-scale simulations are challenging due to their ambiguity, noise and massive volume.
Approach:	They propose a framework that leverages user feedback in RSs with advanced LLM capabilities to generate high-quality simulation data.
Outcome:	The proposed framework boosts the alignment with human preferences and in-domain reasoning capabilities of the fine-tuned LLMs.

Copied to clipboard

Weixiang Yan, Haitian Liu, Yunkun Wang, Yunzhe Li, Qian Chen, Wen Wang, Tingyu Lin, Weishan Zhao, Li Zhu, Hari Sundaram, Shuiguang Deng

HTML: Hierarchical Topology Multi-task Learning for Semantic Parsing in Knowledge Base Question Answering (2025.findings-acl)

Challenge:	Existing benchmarks for evaluating the code understanding and generation capacities of Large Language Models are insufficient . existing benchmarks focus on a narrow range of popular programming languages and specific tasks .
Approach:	They propose an execution-based, multilingual, multitask evaluation benchmark for LLMs . they evaluate coding performance from three dimensions: length, difficulty, efficiency .
Outcome:	The proposed benchmark covers 43 programming languages and eight coding tasks.

Copied to clipboard

Aziguli Wulamu, Lyu Zhengyu, Kaiyuan Gong, Yu Han, Zewen Wang, Zhihong Zhu, Bowen Xing

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

Challenge:	Existing approaches struggle with mapping questions to precise logical forms . Existing frameworks struggle with complex mapping of questions to logical form .
Approach:	They propose a framework that leverages a hierarchical multi-task learning paradigm to enhance the performance of logical form generation.
Outcome:	The proposed framework outperforms supervised fine-tuning methods and training-free ones on large language models.

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.

An Information Bottleneck Perspective for Effective Noise Filtering on Retrieval-Augmented Generation (2024.acl-long)

Copied to clipboard

Kun Zhu, Xiaocheng Feng, Xiyuan Du, Yuxuan Gu, Weijiang Yu, Haotian Wang, Qianglong Chen, Zheng Chu, Jingchang Chen, Bing Qin

Reasoning-to-Defend: Safety-Aware Reasoning Can Defend Large Language Models from Jailbreaking (2025.emnlp-main)

Challenge:	Experimental results show that retrieval-augmented generation improves accuracy and relevance of large language models.
Approach:	They propose to introduce the information bottleneck theory into retrieval-augmented generation by maximizing mutual information between compression and ground output while minimizing mutual information .
Outcome:	The proposed approach improves accuracy and correctness of answer generation and conciseness with 2.5% compression rate.

Copied to clipboard

Junda Zhu, Lingyong Yan, Shuaiqiang Wang, Dawei Yin, Lei Sha

Leveraging Unit Language Guidance to Advance Speech Modeling in Textless Speech-to-Speech Translation (2025.findings-acl)

Challenge:	Large Reasoning Models (LLMs) have demonstrated impressive performances across diverse domains, but how their safety benefits from enhanced reasoning capabilities against jailbreak queries remains unexplored.
Approach:	They propose a safety-aware reasoning paradigm that integrates a pivot token-based safety-based reasoning mechanism into LLMs’ generation process.
Outcome:	The proposed model improves the safety of large language models against jailbreak queries while minimizing attacks and maintaining the original performance.

Copied to clipboard

Yuhao Zhang, Xiangnan Ma, Kaiqi Kou, Peizhuo Liu, Weiqiao Shan, Benyou Wang, Tong Xiao, Yuxin Huang, Zhengtao Yu, JingBo Zhu

Weight Distillation: Transferring the Knowledge in Neural Network Parameters (2021.acl-long)

Challenge:	Existing textless speech-to-speech translation models have two main challenges: 1) learning cross-modal features and 2) learning alignment of difference languages in long sequences.
Approach:	They propose a unit language to overcome two main modeling challenges . they propose task prompt modeling to utilize the unit language in guiding the modeling process.
Outcome:	The proposed language improves over a strong baseline and achieves comparable performance to models trained with text.

Copied to clipboard

Ye Lin, Yanyang Li, Ziyang Wang, Bei Li, Quan Du, Tong Xiao, Jingbo Zhu

Large Language Models are not Fair Evaluators (2024.acl-long)

Challenge:	Knowledge distillation is an effective method for model acceleration and compression.
Approach:	They propose to use parameters to distill knowledge from large neural networks to small ones . they propose to do this by using a parameter generator to transfer the knowledge to a small neural network .
Outcome:	The proposed method learns a small network 1.88 2.94x faster than the large network but with competitive BLEU points.

Copied to clipboard

Peiyi Wang, Lei Li, Liang Chen, Zefan Cai, Dawei Zhu, Binghuai Lin, Yunbo Cao, Lingpeng Kong, Qi Liu, Tianyu Liu, Zhifang Sui

CoRanking: Collaborative Ranking with Small and Large Ranking Agents (2025.findings-emnlp)

Challenge:	Existing evaluation frameworks that use large language models as referees are insufficient for accurately assessing their alignment with human intent.
Approach:	They propose a calibration framework to address positional bias in large language models as evaluators by manually annotating the “win/tie/lose” outcomes of responses from ChatGPT and Vicuna-13B in the Vicun A Benchmark’s question prompt.
Outcome:	The proposed framework alleviates evaluation bias, resulting in closer alignment with human judgments.

Copied to clipboard

Wenhan Liu, Xinyu Ma, Yutao Zhu, Lixin Su, Shuaiqiang Wang, Dawei Yin, Zhicheng Dou

Disentangling Logic: The Role of Context in Large Language Model Reasoning Capabilities (2025.findings-acl)

Challenge:	Listwise ranking based on Large Language Models (LLMs) has achieved state-of-the-art performance in Information Retrieval (IR) however, their effectiveness often depends on LLMs with massive parameter scales and computationally expensive sliding window processing, leading to substantial efficiency bottlenecks.
Approach:	They propose a Collaborative Ranking framework (CoRanking) for LLM-based listwise ranking based on large language models with massive parameter scales and computationally expensive sliding window processing.
Outcome:	The proposed framework reduces ranking latency by approximately 70% while improving effectiveness compared to the standalone large reranker.

Copied to clipboard

Wenyue Hua, Kaijie Zhu, Lingyao Li, Lizhou Fan, Mingyu Jin, Shuhang Lin, Haochen Xue, Zelong Li, Jindong Wang, Yongfeng Zhang

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

Challenge:	Using large language models, large language model models can be used to evaluate reasoning abilities in context-rich scenarios.
Approach:	They construct datasets for both propositional logic and abductive logic reasoning with four difficulty levels across 12 distinct domains based on Wikipedia categorization and those with purely abstract variables.
Outcome:	The proposed model can be used to benchmark LLMs in real-world scenarios, but not in context-rich scenarios.

Copied to clipboard

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

What Makes AI Research Replicable? Executable Knowledge Graphs as Scientific Knowledge Representations (2026.acl-short)

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

Yujie Luo, Zhuoyun Yu, Xuehai Wang, Yuqi Zhu, Ningyu Zhang, Lanning Wei, Lun Du, Da Zheng, Huajun Chen

Format-Adapter: Improving Reasoning Capability of LLMs by Adapting Suitable Format (2026.findings-acl)

Challenge:	Existing approaches to replicate AI research are limited by insufficient background knowledge and the limitations of retrieval-augmented generation methods.
Approach:	They propose a pluggable, paper-centric knowledge base that integrates code snippets and technical insights extracted from scientific literature into a verifiable, executable representation.
Outcome:	The proposed knowledge base shows significant performance gains on paperBench when integrated into three agent frameworks with two different LLMs.

Copied to clipboard

Dingzirui Wang, Xuanliang Zhang, Rongyu Cao, Longxu Dou, Xianzhen Luo, Yingwei MA, Qingfu Zhu, Binhua Li, Fei Huang, Yongbin Li

v-HUB: A Benchmark for Video Humor Understanding from Vision and Sound (2026.acl-long)

Challenge:	Prior work showed that multiple reasoning formats outperform a single format when generating multiple answers.
Approach:	They propose a method to measure reasoning error when generating multiple answers . they propose 'formatadapter' which generates and selects suitable reasoning formats .
Outcome:	The proposed method achieves a 4.3% performance improvement over previous works on math and commonsense reasoning tasks.

Copied to clipboard

Zhengpeng Shi, Yanpeng Zhao, Jianqun Zhou, Yuxuan Wang, Qinrong Cui, Wei Bi, Song-Chun Zhu, Bo Zhao, Zilong Zheng

Layer-wise Importance Matters: Less Memory for Better Performance in Parameter-efficient Fine-tuning of Large Language Models (2024.findings-emnlp)

Challenge:	Humor enriches our daily lives and appears in many forms, from jokes and cartoons to comedies and viral videos.
Approach:	They introduce a video humor understanding benchmark to test their ability to understand humor from visual cues.
Outcome:	The proposed video humor understanding benchmark is based on a collection of short videos . it features rich annotations and a study of environmental sound that can enhance humor .

Copied to clipboard

Kai Yao, Penglei Gao, Lichun Li, Yuan Zhao, Xiaofeng Wang, Wei Wang, Jianke Zhu

MURRE: Multi-Hop Table Retrieval with Removal for Open-Domain Text-to-SQL (2025.coling-main)

Challenge:	Parameter-Efficient Fine-Tuning (PEFT) methods have gained popularity for adapting pre-trained Large Language Models (LLMs) to downstream tasks.
Approach:	They propose a method to optimize the importance of full layers with layer-wise importance scoring by leveraging the estimated importance scores.
Outcome:	The proposed method is compatible with PEFT methods that operate on a per-layer basis and achieves better performance.

Copied to clipboard

Xuanliang Zhang, Dingzirui Wang, Longxu Dou, Qingfu Zhu, Wanxiang Che

Distilled Dual-Encoder Model for Vision-Language Understanding (2022.emnlp-main)

Challenge:	Existing multi-hop retrieval of open-domain text-to-SQL tasks is not applicable due to the tendency to retrieve tables similar to those already retrieved but irrelevant to the question.
Approach:	They propose a multi-hop table retrieval with removal task to retrieve unretrieved tables from open-domain text-to-SQL databases.
Outcome:	The proposed method improves performance 5.7% over the previous state-of-the-art methods on open-domain text-to-SQL datasets.

Copied to clipboard

Zekun Wang, Wenhui Wang, Haichao Zhu, Ming Liu, Bing Qin, Furu Wei

NavRAG: Generating User Demand Instructions for Embodied Navigation through Retrieval-Augmented LLM (2025.findings-acl)

Challenge:	Experimental results show that the proposed cross-modal attention distillation is crucial to the success of our framework.
Approach:	They propose a framework that distills knowledge of fusion-encoder teacher into dual-encoding student model.
Outcome:	The proposed model is competitive with the fusion-encoder teacher model in performance, but suffers from a lack of deep cross-modal interactions.

Copied to clipboard

Zihan Wang, Yaohui Zhu, Gim Hee Lee, Yachun Fan

RAGEval: Scenario Specific RAG Evaluation Dataset Generation Framework (2025.acl-long)

Challenge:	High-performance vision-and-language navigation models require large amounts of training data, the high cost of manual annotating has seriously hindered this field.
Approach:	They propose a retrieval-augmented generation framework that generates user demand instructions for vision-and-language navigation.
Outcome:	The proposed model achieves SOTA performance on the REVERIE benchmark.

Copied to clipboard

Kunlun Zhu, Yifan Luo, Dingling Xu, Yukun Yan, Zhenghao Liu, Shi Yu, Ruobing Wang, Shuo Wang, Yishan Li, Nan Zhang, Xu Han, Zhiyuan Liu, Maosong Sun

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

Challenge:	Existing evaluation metrics for RAG systems are lacking due to high costs of data construction and lack of factual accuracy.
Approach:	They propose a framework to evaluate RAG systems in specialized scenarios . they propose three new metrics to evaluate LLM-generated responses .
Outcome:	The proposed framework outperforms zero-shot and one-shot methods in terms of clarity, safety, conformity, and richness of generated samples.

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

IFlyEA: A Chinese Essay Assessment System with Automated Rating, Review Generation, and Recommendation (2021.acl-demo)

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

Jiefu Gong, Xiao Hu, Wei Song, Ruiji Fu, Zhichao Sheng, Bo Zhu, Shijin Wang, Ting Liu

LoRAMoE: Alleviating World Knowledge Forgetting in Large Language Models via MoE-Style Plugin (2024.acl-long)

Challenge:	Automated Essay Assessment (AEA) aims to judge students’ writing proficiency in an automatic way.
Approach:	They propose to use Chinese AEA system IFlyEssayAssess to evaluate essays written by native Chinese students from primary and junior schools.
Outcome:	The proposed system provides application services for essay scoring, review generation, recommendation, and explainable analytical visualization.

Copied to clipboard

Shihan Dou, Enyu Zhou, Yan Liu, Songyang Gao, Wei Shen, Limao Xiong, Yuhao Zhou, Xiao Wang, Zhiheng Xi, Xiaoran Fan, Shiliang Pu, Jiang Zhu, Rui Zheng, Tao Gui, Qi Zhang, Xuanjing Huang

LIFTED: Multimodal Clinical Trial Outcome Prediction via Large Language Models and Mixture-of-Experts (2025.findings-emnlp)

Challenge:	Experimental results show that, as the instruction data increases, LoRAMoE can significantly improve the ability to process downstream tasks, while maintaining the world knowledge stored in the LLM.
Approach:	They propose a framework that introduces several low-rank adapters and integrates them by using a router network to freeze the backbone model and force a portion of LoRAs to focus on leveraging world knowledge to solve downstream tasks.
Outcome:	The proposed framework freezes the backbone model and forces a portion of LoRAs to focus on leveraging world knowledge to solve downstream tasks, to alleviate world knowledge forgetting.

Copied to clipboard

Wenhao Zheng, Liaoyaqi Wang, Dongshen Peng, Hongxia Xu, Yun Li, Hongtu Zhu, Tianfan Fu, Huaxiu Yao

From Heart to Words: Generating Empathetic Responses via Integrated Figurative Language and Semantic Context Signals (2025.findings-acl)

Challenge:	Clinical trials are costly and pivotal processes that require substantial expenses . a new approach to integrate multimodal data for clinical outcome prediction is needed .
Approach:	a proposed framework transforms modality-specific data into natural language descriptions . a sparse Mixture-of-Experts mechanism then identifies shared patterns across modalities .
Outcome:	a proposed framework outperforms baseline methods in predicting clinical trial outcomes . it transforms modality-specific data into natural language descriptions, encoded via unified encoders .

Copied to clipboard

Gyeongeun Lee, Zhu Wang, Sathya N. Ravi, Natalie Parde

GAML-BERT: Improving BERT Early Exiting by Gradient Aligned Mutual Learning (2021.emnlp-main)

Challenge:	Existing research on empathy generation focuses on understanding the emotions of the speaker rather than on how the responder conveys empathy.
Approach:	They propose to use figurative language and causal semantic context to facilitate targeted empathy generation in a mental health support domain.
Outcome:	The proposed approach achieves 7.6% improvement in BLEU, 36.7% reduction in Perplexity, and 7.6% increase in lexical diversity.

Copied to clipboard

Wei Zhu, Xiaoling Wang, Yuan Ni, Guotong Xie

PopAlign: Diversifying Contrasting Patterns for a More Comprehensive Alignment (2025.acl-long)

Challenge:	Existing approaches to improve the early exiting of natural language processing (NLP) are notoriously gigantic and slow in both training and inference.
Approach:	They propose a framework for improving the early exiting of BERT by asking each exit to distill knowledge from each other.
Outcome:	The proposed framework outperforms the state-of-the-art (SOTA) BERT early exiting methods on the GLUE benchmark.

Copied to clipboard

Zekun Moore Wang, Shenzhi Wang, King Zhu, Jiaheng Liu, Ke Xu, Jie Fu, Wangchunshu Zhou, Wenhao Huang

Challenge:	Typical approaches to training large language models rely on limited contrasting patterns . contrasting data is limited and models are susceptible to harmful response tendencies .
Approach:	They propose a framework that integrates contrasting patterns across the prompt, model, and pipeline levels.
Outcome:	The proposed framework outperforms existing methods in the comparison of RQ1 and RQ2 . the proposed framework significantly outperformed existing methods, leading to more comprehensive alignment.

RepoDebug: Repository-Level Multi-Task and Multi-Language Debugging Evaluation of Large Language Models (2025.findings-emnlp)

Copied to clipboard

Jingjing Liu, Zeming Liu, Zihao Cheng, Mengliang He, Xiaoming Shi, Yuhang Guo, Xiangrong Zhu, Yuanfang Guo, Yunhong Wang, Haifeng Wang

ACR: Adaptive Context Refactoring via Context Refactoring Operators for Multi-Turn Dialogue (2026.findings-acl)

Challenge:	Large Language Models (LLMs) have exhibited significant proficiency in code debugging, especially in automatic program repair.
Approach:	They propose a repository-level code debugging dataset with 22 subtypes of errors that supports 8 commonly used programming languages and 3 debug tasks.
Outcome:	The proposed dataset supports 8 commonly used programming languages and 3 debugging tasks.

Copied to clipboard

Jiawei Shen, Jia Zhu, Hanghui Guo, Weijie Shi, Yue Cui, Qingyu Niu, Guoqing Ma, Jingjiang Liu, Yidan Liang, Yilin Wang, Shimin Di, Jiajie Xu

Enhancing Model Privacy in Federated Learning with Random Masking and Quantization (2025.findings-emnlp)

Challenge:	Existing approaches to multi-turn dialogues lack contextual consistency and dependencies, and models struggle to maintain factual faithfulness as interaction turns increase.
Approach:	They propose an adaptive context refactoring framework that monitors and reshapes the interaction history to mitigate contextual inertia and state drift.
Outcome:	The proposed model outperforms baselines while reducing token consumption.

Copied to clipboard

Zhibo Xu, Zhu JianHao, Jingwen Xu, Changze Lv, Zhenghua Wang, Zisu Huang, Xiaohua Wang, Muling Wu, Qi Qian, Xiaoqing Zheng, Xuanjing Huang

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

Challenge:	federated learning approaches are limited by the complexity of large language models and the need for specialized expertise to protect intellectual property.
Approach:	They propose a federated learning approach that leverages random masking to obscure a subnetwork of model parameters and applies quantization to the remaining parameters.
Outcome:	The proposed approach maintains strong model performance in federated learning settings and achieves enhanced protection of model parameters compared to baseline methods.

Copied to clipboard

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

Explainability & Interpretability in NLP

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.

Learning When to Translate for Streaming Speech (2022.acl-long)

Copied to clipboard

Qian Dong, Yaoming Zhu, Mingxuan Wang, Lei Li

OmniEvent: A Comprehensive, Fair, and Easy-to-Use Toolkit for Event Understanding (2023.emnlp-demo)

Challenge:	Existing methods waiting-and-translating for a fixed duration break speech acoustic units . Existing models waiting-for a set duration and generating partial sentences are not effective .
Approach:	They propose a monotonic segmentation module inside an encoder-decoder model to detect proper speech unit boundaries for a streaming speech input.
Outcome:	The proposed method outperforms existing methods on a speech translation dataset and achieves the best trade-off between translation quality and latency.

Copied to clipboard

Hao Peng, Xiaozhi Wang, Feng Yao, Zimu Wang, Chuzhao Zhu, Kaisheng Zeng, Lei Hou, Juanzi Li

Enhancing LLM Knowledge Learning through Generalization (2025.findings-emnlp)

Challenge:	Event understanding is fundamental for humans to understand the world.
Approach:	They propose an event understanding toolkit called OmniEvent that is comprehensive and fair . it supports mainstream modeling paradigms and the processing of 15 widely-used datasets .
Outcome:	The toolkit supports mainstream modeling paradigms and the processing of 15 widely-used English and Chinese datasets.

Copied to clipboard

Mingkang Zhu, Xi Chen, Zhongdao Wang, Bei Yu, Hengshuang Zhao, Jiaya Jia

AgentBank: Towards Generalized LLM Agents via Fine-Tuning on 50000+ Interaction Trajectories (2024.findings-emnlp)

Challenge:	Continued pre-training on paraphrased data has shown empirical promise for enhancing knowledge acquisition, but this approach is costly and unreliable as it relies on external models or manual effort for rewriting.
Approach:	They propose formatting-based data augmentation which diversifies documents conveying the same knowledge by altering document formats rather than their content.
Outcome:	The proposed methods improve generalization to diverse paraphrased contexts and enhance pre-training and instruction tuning.

Copied to clipboard

Yifan Song, Weimin Xiong, Xiutian Zhao, Dawei Zhu, Wenhao Wu, Ke Wang, Cheng Li, Wei Peng, Sujian Li

ActionStudio: A Lightweight Framework for Data and Training of Large Action Models (2025.emnlp-main)

Challenge:	Existing studies focus on specialized agents designed for particular tasks.
Approach:	They propose to scale annotated interaction trajectories and fine-tune LLMs on AgentBank to get a series of agent models, Samoyed.
Outcome:	The proposed model can scale to get generalized agent capabilities.

Copied to clipboard

Jianguo Zhang, Thai Quoc Hoang, Ming Zhu, Zuxin Liu, Shiyu Wang, Tulika Manoj Awalgaonkar, Akshara Prabhakar, Haolin Chen, Weiran Yao, Zhiwei Liu, Juntao Tan, Juan Carlos Niebles, Shelby Heinecke, Huan Wang, Silvio Savarese, Caiming Xiong

Challenge:	Existing infrastructure for efficient agentic data processing and model training remains underdeveloped.
Approach:	They propose a lightweight and extensible data and training framework for large action models . they propose to unify diverse agent trajectories using Unified Format 2.0 .
Outcome:	The proposed framework shows 9 higher throughput than existing frameworks and performs well across public and realistic agent benchmarks.

DAC: Decomposed Automation Correction for Text-to-SQL (2025.findings-emnlp)

Copied to clipboard

Dingzirui Wang, Longxu Dou, Xuanliang Zhang, Qingfu Zhu, Wanxiang Che

ExpertIVS: Sociological Expert Driven Individual Value Simulation in Large Language Models (2026.findings-acl)

Challenge:	Existing methods to improve text-to-SQL performance are hard to detect errors in SQL directly.
Approach:	They propose to use decomposed correction to improve text-to-SQL performance . they first detect errors based on decompose subtasks, then use it to correct them .
Outcome:	The proposed method improves text-to-SQL performance by 1.4% compared with previous methods .

Copied to clipboard

Zhen Wang, Yuqi Ren, Yuehan Cui, Hongxiang Wang, Jianxiang Peng, Zhaoxia Zhang, Bingkun Zhu, Tongxuan Zhang, Dezhi Tong, Deyi Xiong

ChartVerse: Scaling Chart Reasoning via Reliable Programmatic Synthesis from Scratch (2026.acl-long)

Challenge:	Existing methods for social simulations mechanically stitch survey responses into prompts, which suffer from semantic fragmentation, failing to capture the internal coherence of human value systems.
Approach:	They propose a framework employing 14 Sociological Expert Agents to interpret World Values Survey responses through structured professional perspectives rather than direct responses concatenation.
Outcome:	Experiments on 480 individuals from 12 countries show that ExpertIVS outperforms baselines in value generalization and significantly outperfies the existing methods.

Copied to clipboard

Zheng Liu, Honglin Lin, Xiaoyang Wang, Xin Gao, Yu Li, Mengzhang Cai, Yun Zhu, Zhanping Zhong, Qizhi Pei, Zhuoshi Pan, Xiaoran Shang, Conghui He, Bin Cui, Wentao Zhang, Lijun Wu

Bridging the Capability Gap: Joint Alignment Tuning for Harmonizing LLM-based Multi-Agent Systems (2025.findings-emnlp)

Challenge:	Existing open-source vision language models lack high-quality training data for chart reasoning . current models are simplistic and repetitive, while associated QA pairs are prone to hallucinations .
Approach:	They propose a framework to synthesize complex charts and reliable reasoning data from scratch.
Outcome:	Experimental results show that ChartVerse-8B surpasses existing models in QA and difficulty . lack of high-quality training data hampers development of open-source models .

Copied to clipboard

Minghang Zhu, Zhengliang Shi, Zhiwei Xu, Shiguang Wu, Lingjie Wang, Pengjie Ren, Zhaochun Ren, Zhumin Chen

Challenge:	Existing methods for fine-tuning agents are often inadequate . a multi-agent system can solve complex tasks by dividing responsibilities among specialized agents .
Approach:	a new framework is proposed to improve agents collaboration through iterative alignment.
Outcome:	The proposed framework outperforms state-of-the-art benchmarks on held-in and held-out tasks.

The Illusion of Specialization: Unveiling the Domain-Invariant "Standing Committee" in Mixture-of-Experts Models (2026.acl-long)

Copied to clipboard

Yan Wang, Yitao Xu, Nanhan Shen, Jinyan Su, Jimin Huang, Zining Zhu

Challenge:	Mixture of Experts models are widely assumed to achieve domain specialization through sparse routing.
Approach:	They propose a framework that analyzes routing behavior at the level of expert groups rather than individual experts.
Outcome:	The proposed framework analyzes routing behavior at the level of expert groups rather than individual experts.

AutoMedEval: Harnessing Language Models for Automatic Medical Capability Evaluation (2025.acl-long)

Copied to clipboard

Xiechi Zhang, Zetian Ouyang, Linlin Wang, Gerard De Melo, Zhu Cao, Xiaoling Wang, Ya Zhang, Yanfeng Wang, Liang He

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

Challenge:	Existing evaluation methods based on large language models (LLMs) are expensive and lack expertise due to limitations in human expertise.
Approach:	They propose an open-source automatic evaluation model with 13B parameters specifically engineered to measure the question-answering proficiency of medical LLMs.
Outcome:	The proposed model surpasses baselines in terms of correlation with human judgments.

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

MADial-Bench: Towards Real-world Evaluation of Memory-Augmented Dialogue Generation (2025.naacl-long)

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

Junqing He, Liang Zhu, Rui Wang, Xi Wang, Gholamreza Haffari, Jiaxing Zhang

LlmLink: Dual LLMs for Dynamic Entity Linking on Long Narratives with Collaborative Memorisation and Prompt Optimisation (2025.coling-main)

Challenge:	Existing evaluation metrics for memory-augmented dialogue systems lack practical value . current evaluation methods only consider passive memory retrieval while ignoring diverse memory recall with rich triggering factors.
Approach:	They propose to use long-term memory to create human-like dialogues using chatbots.
Outcome:	The proposed benchmark covers memory retrieval and memory recognition tasks with both passive and proactive memory recall data.

Copied to clipboard

Lixing Zhu, Jun Wang, Yulan He

A Simple and Effective Approach to Robust Unsupervised Bilingual Dictionary Induction (2020.coling-main)

Challenge:	Existing methods focus on supervised fine-tuning or limited to one-off prediction, which poses a challenge where the context is long.
Approach:	They propose a dynamic approach to CoREFerence resolution in chunked long narratives by deploying dual Large Language Models.
Outcome:	The proposed model achieves performance gains over existing models and fine-tuning approaches on long narrative datasets, significantly reducing the resources required for inference and training.

Copied to clipboard

Yanyang Li, Yingfeng Luo, Ye Lin, Quan Du, Huizhen Wang, Shujian Huang, Tong Xiao, Jingbo Zhu

Bridging Local Details and Global Context in Text-Attributed Graphs (2024.emnlp-main)

Challenge:	Recent work has questioned the robustness of unsupervised bilingual dictionary induction methods on distant language pairs.
Approach:	They propose an iterative dimension reduction method to bridge this gap . they propose a method that initializes and self-learning and inducing a dictionary .
Outcome:	The proposed method achieves 13.64 55.53% accuracy between English and four distant languages.

Copied to clipboard

Yaoke Wang, Yun Zhu, Wenqiao Zhang, Yueting Zhuang, Liyunfei Liyunfei, Siliang Tang

CrowdAgent: Multi-Agent Managed Multi-Source Annotation System (2025.emnlp-demos)

Challenge:	Existing studies focus on combining different information levels but overlook interconnections, i.e., contextual textual information among nodes.
Approach:	They propose a framework that bridges local and global perspectives by leveraging contextual textual information.
Outcome:	The proposed framework achieves state-of-the-art performance while reducing tokens significantly.

Copied to clipboard

Maosheng Qin, Renyu Zhu, Mingxuan Xia, null Chenchenkai, Zhen Zhu, Minmin Lin, Junbo Zhao, Lu Xu, Changjie Fan, Runze Wu, Haobo Wang

Interesting Culture: Social Relation Recognition from Videos via Culture De-confounding (2025.findings-emnlp)

Challenge:	Recent approaches to annotate data focus on labeling, but lack holistic process control . a novel system that integrates task assignment, data annotation, and quality/cost management is needed .
Approach:	They propose a multi-agent system that integrates task assignment, data annotation, and quality/cost management.
Outcome:	The proposed system automates human management by using a collaborative multi-agent system.

Copied to clipboard

Yuxuan Zhang, Yangfu Zhu, Haorui Wang, Bin Wu

Unified Demonstration Retriever for In-Context Learning (2023.acl-long)

Challenge:	a culturally-specific cultural context can be used to train relationship recognition models . cultural confounding factors can be learned, limiting ability to recognize social relationships in different cultures.
Approach:	They propose a culturally-based model that mitigates the influence of culture . they also construct a video social relation recognition dataset to facilitate discussion .
Outcome:	The proposed model surpasses state-of-the-art methods on several datasets.

Copied to clipboard

Xiaonan Li, Kai Lv, Hang Yan, Tianyang Lin, Wei Zhu, Yuan Ni, Guotong Xie, Xiaoling Wang, Xipeng Qiu

Importance of Synthesizing High-quality Data for Text-to-SQL Parsing (2023.findings-acl)

Challenge:	In-context learning is a new learning paradigm where a language model conditions on a few input-output pairs (demonstrations) and a test input, and directly outputs the prediction.
Approach:	They propose a single model to retrieve demonstrations for a wide range of tasks by combining training signals from various tasks into a unified list-wise ranking formulation by language model’s feedback.
Outcome:	The proposed model outperforms baselines on 30+ tasks across 13 task families and multiple data domains.

Copied to clipboard

Yiqun Hu, Yiyun Zhao, Jiarong Jiang, Wuwei Lan, Henghui Zhu, Anuj Chauhan, Alexander Hanbo Li, Lin Pan, Jun Wang, Chung-Wei Hang, Sheng Zhang, Jiang Guo, Mingwen Dong, Joseph Lilien, Patrick Ng, Zhiguo Wang, Vittorio Castelli, Bing Xiang

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

Challenge:	Existing text-to-SQL parsers lack the data to perform well with augmented synthetic data.
Approach:	They propose a framework that imposes strong typing constraints and incorporates key relationships from schema.
Outcome:	The proposed framework improves on the high-quality synthesized SQL and natural language question (NLQ) models have significant accuracy boosts and achieve new state-of-the-art performance on spider.

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

I2E: From Image Pixels to Actionable Interactive Environments for Text-Guided Image Editing (2026.acl-long)

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

Jinghan Yu, Junhao Xiao, Chenyu Zhu, Jiaming Li, Jia Li, HanMing Deng, Xirui Wang, Guoli Jia, Jianjun Li, Xiang Bai, Bowen Zhou, Zhiyuan Ma

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

Challenge:	Existing text-guided image editing methods rely on end-to-end pixel-level inpainting paradigm . existing models lack such intermediate representations and Reasoning-then-action process .
Approach:	They propose a "Decompose-then-Action" paradigm that revisits image editing as an actionable interaction process within a structured environment.
Outcome:	The proposed paradigm outperforms existing methods in compositional editing tasks.

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

DetectRL-X: Towards Reliable Multilingual and Real-World LLM-Generated Text Detection (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

Junchao Wu, Yefeng Liu, Chenyu Zhu, Hao Zhang, Zeyu Wu, Tianqi Shi, Yichao Du, Longyue Wang, Weihua Luo, Jinsong Su, Derek F. Wong

One Battle After Another: Probing LLMs’ Limits on Multi-Turn Instruction Following with a Benchmark Evolving Framework (2026.acl-long)

Challenge:	Existing detectors are limited in their ability to detect large language models generated content in multilingual environments.
Approach:	They propose a multilingual benchmark to evaluate advanced detectors across 8 dimensions to better align with real-world applications.
Outcome:	The proposed benchmark encompasses 8 languages commonly used in commercial contexts and collects human-written texts from 6 domains highly susceptible to LLM misuse.

Copied to clipboard

Qi Jia, Ye Shen, Xiujie Song, Kaiwei Zhang, Shibo Wang, Dun Pei, Xiangyang Zhu, Guangtao Zhai

A Self-supervised Joint Training Framework for Document Reranking (2022.findings-naacl)

Challenge:	Existing benchmarks for instruction-following in multi-topic dialogues are limited to a fixed number of turns, susceptible to saturation and failing to account for users’ interactive experience.
Approach:	They propose a framework featuring a three-layer tracking mechanism and a query synthesis agent to mimic sequential user behaviors.
Outcome:	The proposed framework outperforms existing benchmarks in the evaluation of instruction following in multi-topic dialogues and demonstrates deficiencies in failure recovery and fine-grained instruction following.

Copied to clipboard

Xiaozhi Zhu, Tianyong Hao, Sijie Cheng, Fu Lee Wang, Hai Liu

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

Challenge:	Pretrained language models have been successfully applied to a wide range of tasks . however, the pretraining tasks were based on the context of documents .
Approach:	They propose a self-supervised joint training framework with a method called Masked Query Prediction to establish semantic relations between given queries and positive documents.
Outcome:	The proposed framework outperforms existing models on document reranking tasks without further pre-training . it uses a self-supervised method to establish semantic relations between given queries and positive documents.

Copied to clipboard

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

Beyond Triplet: Leveraging the Most Data for Multimodal Machine Translation (2023.findings-acl)

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

Yaoming Zhu, Zewei Sun, Shanbo Cheng, Luyang Huang, Liwei Wu, Mingxuan Wang

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

Challenge:	Multimodal machine translation (MMT) aims to improve translation quality by incorporating information from other modalities, such as vision.
Approach:	They propose a framework for multimodal machine translation that utilizes large-scale non-triple data and a multimodal translation dataset.
Outcome:	The proposed method can significantly improve translation performance with more non-triple data.

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

End-to-end Dense Video Captioning as Sequence Generation (2022.coling-1)

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

Wanrong Zhu, Bo Pang, Ashish V. Thapliyal, William Yang Wang, Radu Soricut

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

Challenge:	Existing methods for dense video captioning use a two-stage generative process . but, more complex tasks are not able to fully utilize this powerful paradigm .
Approach:	They propose to model two subtasks of dense video captioning as one sequence generation task and predict the events and the corresponding descriptions.
Outcome:	Experiments on YouCook2 and ViTT show that the proposed model can be used on any video platform.

Copied to clipboard

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

Modeling Multi-Dimensional Cognitive States in Large Language Models under Cognitive Crowding (2026.findings-acl)

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

Lin Zhong, Siyu Zhu, Zizhen Yuan, Jinhao Cui, Xinyang Zhao, Lingzhi Wang, Hao Chen, Qing Liao

LaMP-Val: Large Language Models Empower Personalized Valuation in Auction (2025.findings-emnlp)

Challenge:	Existing Large Language Models (LLMs) mainly address isolated tasks such as emotion analysis or stance detection.
Approach:	They propose a large-scale model that combines large-level annotations with hyperbolic space to model human cognitive states.
Outcome:	The proposed model outperforms baseline models on cognitive dimensions on single dimension tasks while retaining strong hierarchical structure.

Copied to clipboard

Jie Sun, Tianyu Zhang, Houcheng Jiang, Kexin Huang, Xiang Shu, Zhibo Zhu, Lintao Ma, Xingyu Lu, Jun Zhou, Junkang Wu, Chi Luo, An Zhang, Jiancan Wu, Xiang Wang

Abacus-SQL: A Text-to-SQL System Empowering Cross-Domain and Open-Domain Database Retrieval (2025.acl-demo)

Challenge:	Currently, most research focuses on the bidding algorithms used within auction mechanisms.
Approach:	They propose a personalized valuation framework that integrates Large Language Models to incorporate personalized semantic preference into users valuation process.
Outcome:	The proposed framework incorporates Large Language Models to incorporate personalized semantic preference into users valuation process.

Copied to clipboard

Keyan Xu, Dingzirui Wang, Xuanliang Zhang, Qingfu Zhu, Wanxiang Che

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

Challenge:	Existing text-to-SQL systems often lack retrieval capabilities for open-domain databases, requiring users to manually filter relevant databases.
Approach:	They propose to use database retrieval technology to locate the required databases in an open-domain database environment and enhance system cross-domain transferability through data augmentation methods.
Outcome:	The proposed system performs excellently in multi-turn text-to-SQL tasks, validating the proposed approach’s effectiveness.

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

Granular Entity Mapper: Advancing Fine-grained Multimodal Named Entity Recognition and Grounding (2024.findings-emnlp)

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

Ziqi Wang, Chen Zhu, Zhi Zheng, Xinhang Li, Tong Xu, Yongyi He, Qi Liu, Ying Yu, Enhong Chen

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

Challenge:	Existing methods for fine-grained content extraction are limited by long-tailed distribution of textual entity categories and performance of object detectors.
Approach:	They propose a multi-granularity entity recognition module and a reranking module to integrate hierarchical information of entity categories, visual cues, and external textual resources collectively.
Outcome:	The proposed framework achieves state-of-the-art on the fine-grained content extraction task.

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

SOTOPIA-π: Interactive Learning of Socially Intelligent Language Agents (2024.acl-long)

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

Ruiyi Wang, Haofei Yu, Wenxin Zhang, Zhengyang Qi, Maarten Sap, Yonatan Bisk, Graham Neubig, Hao Zhu

Adaptive and Representative Multi-Interest Modeling for Recommendation with Large Language Model (2026.findings-acl)

Challenge:	Existing studies on building language agents have not addressed this social learning gap.
Approach:	They propose an interactive learning method that improves the social intelligence of language agents by using behavior cloning and self-reinforcement based training on filtered social interaction data.
Outcome:	The proposed method allows a 7B LLM to reach the social goal completion ability of an expert model (GPT-4-based agent) without the loss of more generic abilities, such as the ability to answer knowledge-based questions.

Copied to clipboard

Ziyan Wang, Yingpeng Du, Tianjun Wei, Haoyan Chua, Jieyi Bi, Jie Zhang, Zhu Sun

AutoRAN: Automated Hijacking of Safety Reasoning in Large Reasoning Models (2026.acl-long)

Challenge:	Existing methods for multi-interest analysis of users rely on heuristic assumptions . however, the granularity of raw generation of LLMs is agnostic, leading to overly fine or coarse interest grouping.
Approach:	They propose an LLM-driven adaptive and representative multi-interest modeling framework that exploits the agnostic granularity of LLMs for multi-interest analysis.
Outcome:	The proposed model outperforms baselines on real-world datasets.

Copied to clipboard

Jiacheng Liang, Tanqiu Jiang, Yuhui Wang, Rongyi Zhu, Fenglong Ma, Ting Wang

The Microsoft Toolkit of Multi-Task Deep Neural Networks for Natural Language Understanding (2020.acl-demos)

Challenge:	Large reasoning models (LRMs) generate coherent reasoning paths before conclusions, but they introduce new vulnerabilities.
Approach:	They propose a framework that leverages a weaker but less-aligned model to simulate execution reasoning for initial hijacking attempts and iteratively refines attacks by exploiting reasoning patterns leaked through the target LRM’s refusals.
Outcome:	The proposed framework achieves 100% success rate within one or few turns, neutralizing reasoning-based defenses even when evaluated by robustly aligned external models.

Copied to clipboard

Xiaodong Liu, Yu Wang, Jianshu Ji, Hao Cheng, Xueyun Zhu, Emmanuel Awa, Pengcheng He, Weizhu Chen, Hoifung Poon, Guihong Cao, Jianfeng Gao

HiPrune: Hierarchical Attention for Efficient Token Pruning in Vision-Language Models (2026.findings-acl)

Challenge:	MT-DNN is an open-source natural language understanding toolkit . it allows researchers and developers to train customized deep learning models .
Approach:	They present MT-DNN, an open-source natural language understanding toolkit . it is designed to facilitate rapid customization for a broad spectrum of NLU tasks . MT supports multi-task knowledge distillation, which can substantially compress a deep neural model without significant performance drop.
Outcome:	The proposed model can significantly compress a large model without significant performance drop.

Copied to clipboard

Jizhihui Liu, Guangdao Zhu, Feiyi Du, Niu Lian, Jun Li, Bin Chen, Weili Guan, Yaowei Wang

3DS: Medical Domain Adaptation of LLMs via Decomposed Difficulty-based Data Selection (2025.emnlp-main)

Challenge:	Existing methods for visual token pruning lack insight into the intrinsic property of the vision encoder . et al., 2017: 99.3% of task accuracy with only 1/3 of the tokens.
Approach:	They propose a model-agnostic token pruning method that trains without training . they propose 'HiPrune' method which prunes visual tokens according to their attention .
Outcome:	The proposed method achieves 99.3% of task accuracy with only 1/3 of the tokens . it reduces inference FLOPs by 58.7% and maintains 99.99% accuracy with 2/9 tokens.

Copied to clipboard

Hongxin Ding, Yue Fang, Runchuan Zhu, Xinke Jiang, Jinyang Zhang, Yongxin Xu, Weibin Liao, Xu Chu, Junfeng Zhao, Yasha Wang

Meta-Reflection: A Feedback-Free Reflection Learning Framework (2025.acl-long)

Challenge:	Effective domain adaptation typically involves supervised fine-tuning on carefully selected instruction-tuned data.
Approach:	They propose a model-centric data selection framework that aligns data selection with the model’s knowledge distribution to improve model performance.
Outcome:	The proposed framework outperforms existing methods by up to 2.97% accuracy in the healthcare domain.

Copied to clipboard

Yaoke Wang, Yun Zhu, XintongBao XintongBao, Wenqiao Zhang, Suyang Dai, Kehan Chen, Wenqiang Li, Gang Huang, Siliang Tang, Yueting Zhuang

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

Challenge:	Existing approaches to improve large language models' ability to understand and reason are limited by external feedback.
Approach:	They propose a feedback-free reflection mechanism that requires only a single inference pass without external feedback.
Outcome:	The proposed method is based on an industrial e-commerce benchmark and public datasets.

Copied to clipboard

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

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

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

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

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

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

BTC-LLM: Efficient Sub-1-Bit LLM Quantization via Learnable Transformation and Binary Codebook (2026.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

Hao Gu, Lujun Li, Hao Wang, Lei Wang, Zheyu Wang, Bei Liu, Jiacheng Liu, Qiyuan Zhu, Sirui Han, Yike Guo

Text Clustering

Challenge:	Recent sparsity-aware binarization approaches can achieve sub-1-bit compression, but they face performance degradation, mask-management overhead, and limited hardware compatibility.
Approach:	They propose a binary quantization framework that leverages binary pattern clustering and weight transformation to overcome performance degradation and mask-management overhead.
Outcome:	The proposed framework achieves state-of-the-art compression (1.11–0.7 bits) it maintains high performance with only a 3.1% accuracy drop in zero-shot benchmarks while delivering a 1.6 speedup over FP16.

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

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

LLM×MapReduce-V3: Enabling Interactive In-Depth Survey Generation through a MCP-Driven Hierarchically Modular Agent System (2025.emnlp-demos)

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

Yu Chao, Siyu Lin, Xiaorong Wang, Zhu Zhang, Zihan Zhou, Haoyu Wang, Shuo Wang, Jie Zhou, Zhiyuan Liu, Maosong Sun

Challenge:	Generating high-quality long-form survey articles poses significant challenges to AI Agent systems.
Approach:	They propose a hierarchically modular agent system for long-form survey generation . they use atomic models to implement skeleton initialization, digest construction, and skelet refinement . human evaluations demonstrate system surpasses representative baselines .
Outcome:	The proposed system surpasses representative baselines in both content depth and length, highlighting the strength of MCP-based modular planning.

Self-Error-Instruct: Generalizing from Errors for LLMs Mathematical Reasoning (2025.acl-long)

Copied to clipboard

Erxin Yu, Jing Li, Ming Liao, Qi Zhu, Boyang Xue, Minghui Xu, Baojun Wang, Lanqing Hong, Fei Mi, Lifeng Shang

InquireMobile: Teaching VLM-based Mobile Agent to Request Human Assistance via Reinforcement Fine-Tuning (2026.acl-long)

Challenge:	Existing approaches to learning from errors synthesize training data by extrapolating from isolated bad cases, thereby failing to generalize the extensive patterns inherent within these cases.
Approach:	They propose a framework that synthesizes more generalized training data from isolated bad cases by extrapolating from isolated cases.
Outcome:	The proposed framework synthesizes more generalized training data to address these model weaknesses.

Copied to clipboard

Qihang Ai, Pi Bu, Yue Cao, Yingyao Wang, Jihao Gu, Jingxuan Xing, Zekun Zhu, Wei Jiang, Zhicheng Zheng, Jun Song, Yuning Jiang

Counterfactual Adversarial Learning with Representation Interpolation (2021.findings-emnlp)

Challenge:	Recent advances in Vision-Language Models (VLMs) have enabled mobile agents to perceive and interact with real-world mobile environments based on human instructions.
Approach:	They propose a vision-language model that actively seeks human confirmation at critical decision points and a model inspired by reinforcement learning.
Outcome:	The proposed model achieves an improvement of 46.8% in inquiry success rate and the best overall success rate among existing baselines on InquireBench.

Copied to clipboard

Wei Wang, Boxin Wang, Ning Shi, Jinfeng Li, Bingyu Zhu, Xiangyu Liu, Rong Zhang

Generalization Differences between End-to-End and Neuro-Symbolic Vision-Language Reasoning Systems (2022.findings-emnlp)

Challenge:	Existing models with statistical bias are prone to memorized correlations . large pre-trained models such as BERT have revolutionized the model development paradigm in natural language processing .
Approach:	They propose a framework to tackle the problem from a causal perspective using a latent space interpolation approach.
Outcome:	Extensive experiments show that CAT achieves substantial performance improvement over SOTA across different downstream tasks, including sentence classification, natural language inference and question answering.

Copied to clipboard

Wang Zhu, Jesse Thomason, Robin Jia

Human Bias in the Face of AI: Examining Human Judgment Against Text Labeled as AI Generated (2025.findings-acl)

Challenge:	Widely used multi-modal pretrained models generalize poorly to out-of-distribution data, suggesting shortcomings in the VLE2E pipeline.
Approach:	They develop a segment-combine test for multi-image queries and contrast set for cross-benchmark transfer.
Outcome:	The proposed method shows that it is possible to train both neural and neuro-symbolic models in the same way.

Copied to clipboard

Tiffany Zhu, Iain Weissburg, Kexun Zhang, William Yang Wang

Challenge:	Prior research on AI mistrust focused primarily on AI's bias towards different human pop-ups.
Approach:	They examine how bias shapes the perception of AI versus human generated content . they found that raters favored content labeled "Human Generated" even when labels were deliberately swapped .
Outcome:	The findings highlight the limitations of human judgment in interacting with AI and offer a foundation for improving human-AI collaboration.

SPAGBias: Uncovering and Tracing Structured Spatial Gender Bias in Large Language Models (2026.acl-long)

Copied to clipboard

Binxian Su, Haoye Lou, Shucheng Zhu, Weikang Wang, Ying Liu, Dong Yu, Pengyuan Liu

Enhancing Numerical Reasoning with the Guidance of Reliable Reasoning Processes (2024.acl-long)

Challenge:	Large language models (LLMs) are being used in urban planning but there is concern that they reproduce or amplify such biases.
Approach:	They propose a framework to evaluate spatial gender bias in large language models . they use a taxonomy of 62 urban micro-spaces, a prompt library and three diagnostic layers .
Outcome:	The proposed framework identifies structured gender-space associations that go beyond the public-private divide, forming nuanced micro-level mappings.

Copied to clipboard

Dingzirui Wang, Longxu Dou, Xuanliang Zhang, Qingfu Zhu, Wanxiang Che

Aligning Large Language Models with Human Preferences through Representation Engineering (2024.acl-long)

Challenge:	Numerical reasoning is an essential ability for NLP systems to handle numeric information.
Approach:	They propose a numerical reasoning method that generates reliable reasoning processes by decomposing the answer formula and aim to train models to generate the process with synthesized data.
Outcome:	The proposed method improves on all five datasets with an average improvement of 1.8% compared with baselines and gpt-3.5-turbo.

Copied to clipboard

Wenhao Liu, Xiaohua Wang, Muling Wu, Tianlong Li, Changze Lv, Zixuan Ling, Zhu JianHao, Cenyuan Zhang, Xiaoqing Zheng, Xuanjing Huang

Data Efficient RLVR via Off-Policy Influence Guidance (2026.acl-long)

Challenge:	Existing methods for achieving this alignment involve employing reinforcement learning from human feedback (RLHF) Existing approaches involve using RLHF to fine-tune LLMs based on human labels . however, RLRF is susceptible to instability during fine- tuning and presents challenges in implementation.
Approach:	They propose to use reinforcement learning from human feedback to fine-tune large language models with human preferences to achieve precise control of model behavior.
Outcome:	Experiments show that RAHF can be used to capture and manipulate representations to align with a broad spectrum of human preferences or values rather than being confined to a single concept or function.

Copied to clipboard

Erle Zhu, Dazhi Jiang, Yuan Wang, Xujun Li, Jiale Cheng, Yuxian Gu, Yilin Niu, Aohan Zeng, Jie Tang, Minlie Huang, Hongning Wang

A Confidence-based Partial Label Learning Model for Crowd-Annotated Named Entity Recognition (2023.findings-acl)

Challenge:	Existing data selection methods for RLVR are heuristic-based, lacking theoretical guarantees and generalizability.
Approach:	They propose an off-policy influence estimation method that approximates data influence using offline trajectories.
Outcome:	The proposed method reduces the computational cost of policy rollouts and improves storage and computation efficiency.

Copied to clipboard

Limao Xiong, Jie Zhou, Qunxi Zhu, Xiao Wang, Yuanbin Wu, Qi Zhang, Tao Gui, Xuanjing Huang, Jin Ma, Ying Shan

KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation (2021.tacl-1)

Challenge:	Existing models for named entity recognition (NER) are based on large-scale labeled datasets, which always obtain using crowdsourcing.
Approach:	They propose a CONfidence-based partial Label Learning method to integrate prior and posterior confidences for crowd-annotated named entity recognition models.
Outcome:	The proposed model improves on real-world and synthetic datasets compared with baselines.

Copied to clipboard

Xiaozhi Wang, Tianyu Gao, Zhaocheng Zhu, Zhengyan Zhang, Zhiyuan Liu, Juanzi Li, Jian Tang

Knowledge-Selective Pretraining for Attribute Value Extraction (2023.findings-emnlp)

Challenge:	Existing language representation models (PLMs) cannot capture factual knowledge from text.
Approach:	They propose a unified model for Knowledge Embedding and Pre-trained LanguagERepresentation which integrates factual knowledge into PLMs and produces effective text-enhanced KE with the strong PLM.
Outcome:	The proposed model improves on existing pre-trained language representation models and improves their performance on various NLP tasks.

Copied to clipboard

Hui Liu, Qingyu Yin, Zhengyang Wang, Chenwei Zhang, Haoming Jiang, Yifan Gao, Zheng Li, Xian Li, Chao Zhang, Bing Yin, William Wang, Xiaodan Zhu

BigVideo: A Large-scale Video Subtitle Translation Dataset for Multimodal Machine Translation (2023.findings-acl)

Challenge:	Existing methods for AVE are limited on rare attributes due to poor generalization ability.
Approach:	They propose to leverage pretraining and transfer learning to address weaknesses in existing methods.
Outcome:	The proposed method achieves new state-of-the-art performance without pretraining on rare attributes with limited training resources.

Copied to clipboard

Liyan Kang, Luyang Huang, Ningxin Peng, Peihao Zhu, Zewei Sun, Shanbo Cheng, Mingxuan Wang, Degen Huang, Jinsong Su

A Survey of Pun Generation: Datasets, Evaluations and Methodologies (2025.findings-emnlp)

Challenge:	Existing datasets focus on captions describing images or videos, which are not large and diverse enough.
Approach:	They propose a large-scale video subtitle translation dataset to facilitate multi-modality machine translation.
Outcome:	The proposed dataset is 10 times larger than the widely used How2 and VaTeX datasets.

Copied to clipboard

Yuchen Su, Yonghua Zhu, Ruofan Wang, Zijian Huang, Diana Benavides-Prado, Michael J. Witbrock

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

Challenge:	Pun generation aims to modify linguistic elements in text to produce humour or evoke double meanings.
Approach:	They propose to review pun generation datasets and methods across different stages . pun generation aims to produce humour or evoke double meanings .
Outcome:	This paper summarises both automated and human evaluation metrics used to assess the quality of pun generation.

Copied to clipboard

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

BPP-Search: Enhancing Tree of Thought Reasoning for Mathematical Modeling Problem Solving (2025.acl-long)

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

Teng Wang, Wing Yin Yu, Zhenqi He, Zehua Liu, HaileiGong HaileiGong, Han Wu, Xiongwei Han, Wei Shi, Ruifeng She, Fangzhou Zhu, Tao Zhong

Chain-of-Questions Training with Latent Answers for Robust Multistep Question Answering (2023.emnlp-main)

Challenge:	Existing datasets in operations research domain lack detailed annotations of the modeling process, focusing only on objective values.
Approach:	They propose an annotation-based tree-of-thought tree-based reasoning algorithm that integrates reinforcement learning into a tree- of-though.
Outcome:	The proposed algorithm outperforms state-of-the-art methods on StructuredOR, NL4OPT, and MAMO-ComplexLP datasets.

Copied to clipboard

Wang Zhu, Jesse Thomason, Robin Jia

QiMeng-PRepair: Precise Code Repair via Edit-Aware Reward Optimization (2026.acl-long)

Challenge:	Existing methods for multistep question answering have shown promise in generating multistep solutions, but they lack robustness.
Approach:	They propose a framework that trains a model to robustly answer multistep questions by generating and answering sub-questions.
Outcome:	The proposed framework outperforms neuro-symbolic methods on a DROP contrast set and GPT-3.5 on QA adversarial sets.

Copied to clipboard

Changxin Ke, Rui Zhang, Jiaming Guo, Yuanbo Wen, Li Ding, Shuo Wang, Xuyuan Zhu, Xiong Peng, Di Huang, Zidong Du, Xing Hu, Qi Guo, Yunji Chen

Can LLMs Learn to Map the World from Local Descriptions? (2026.acl-long)

Challenge:	Existing approaches to program repair are based on correctness alone.
Approach:	They propose a framework that mitigates over-editing and improves repair accuracy by generating buggy programs and re-edits.
Outcome:	The proposed framework improves repair precision by 31.4% under fix1@1, a metric that considers repair correctness and extent, and significantly increases decoding throughput when combined with speculative editing.

Copied to clipboard

Sirui Xia, Aili Chen, Xintao Wang, Tinghui Zhu, Yikai Zhang, Jiangjie Chen, Yanghua Xiao

Challenge:	Recent advances in large language models have demonstrated strong capabilities in tasks such as code generation and mathematical reasoning.
Approach:	They investigate whether large language models can construct coherent global spatial cognition by integrating fragmented relational descriptions.
Outcome:	The proposed models can generalize to unseen spatial relationships and exhibit latent representations aligned with real-world spatial distributions.

When Efficiency Becomes a Vulnerability: Computational Cost Attacks on WebAgents (2026.acl-long)

Copied to clipboard

Liang-Bo Ning, Yuchen Zhu, Heqing Huang, Xin Wang, Yi Chang, Li Qing, Wenqi Fan

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

Challenge:	Existing WebAgents suffer from computational cost attacks due to long reasoning processes and excessive computational cost.
Approach:	They propose a framework that generates adversarial prompts and a reinforcement learning-enhanced selector to identify the most effective perturbations.
Outcome:	The proposed framework exploits large language models to generate diverse adversarial prompts and a reinforcement learning–enhanced selector to identify the most effective perturbations.

Copied to clipboard

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

Robust Preference Optimization via Dynamic Target Margins (2025.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

Jie Sun, Junkang Wu, Jiancan Wu, Zhibo Zhu, Xingyu Lu, Jun Zhou, Lintao Ma, Xiang Wang

TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Finance (2021.acl-long)

Challenge:	Direct Preference Optimization (DPO) is an efficient method for ensuring safety and reliability in practical applications.
Approach:	They propose a dynamic target margin preference optimization algorithm that adjusts reward margins at the pairwise level.
Outcome:	The proposed method achieves an average 4.4% improvement over baselines, setting new benchmarks for state-of-the-art performance.

Copied to clipboard

Fengbin Zhu, Wenqiang Lei, Youcheng Huang, Chao Wang, Shuo Zhang, Jiancheng Lv, Fuli Feng, Tat-Seng Chua

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

Challenge:	Existing QA systems focus on unstructured text, structured knowledge base, or semi-structured tables.
Approach:	They propose a large-scale question answering model based on financial reports . numerical reasoning is usually required to infer the answer .
Outcome:	The proposed model achieves 58.0% inF1, an 11.1% increase over the baseline model, but still lags behind the best human model.

Copied to clipboard

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

Memorization, Emergence, and Explaining Reversal Failures: A Controlled Study of Relational Semantics in LLMs (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

Yihua Zhu, Qianying Liu, Jiaxin Wang, Fei Cheng, Chaoran Liu, Akiko Aizawa, Sadao Kurohashi, Hidetoshi Shimodaira

Explainability & Interpretability in NLP

Challenge:	Autoregressive LLMs perform well on relational tasks that require linking entities via relational words, but it is unclear whether they learn the logical semantics of such relations or whether left-to-right order bias is involved.
Approach:	They propose a framework that generates text from symmetric/inverse triples and trains autoregressive models from scratch.
Outcome:	The proposed framework generates text from symmetric/inverse triples, trains autoregressive models from scratch, and evaluates memorization, logical inference, and in-context generalization to unseen entities.

Lifting Optimized Binaries to Canonical Compiler IR via Structure-Aware Retrieval and Iterative Verification (2026.acl-long)

Copied to clipboard

Xiaoao Zhu, Jie Ren, Zhiqiang Li, Jie Zheng, Zhanyong Tang, Zheng Wang

Exons-Detect: Identifying and Amplifying Exonic Tokens via Hidden-State Discrepancy for Robust AI-Generated Text Detection (2026.acl-long)

Challenge:	Existing methods for decompiling binary code are brittle due to compiler optimizations that distort control-flow and data-flow structure.
Approach:	They propose a system that lifts optimized binaries to canonical compiler intermediate representation (IR) BRIDGE uses control-flow-aware retrieval-augmented generation with feedback-driven verification .
Outcome:	The proposed system outperforms seven baselines on humanEval-Decompile and MBPP, lifting x86-64 and ARM64 binaries to LLVM IR.

Copied to clipboard

Xiaowei Zhu, Yubing Ren, Fang Fang, Shi Wang, Yanan Cao, Li Guo

Learning to Ask Unanswerable Questions for Machine Reading Comprehension (P19-1)

Challenge:	Existing methods for AI-generated text detection assume uniform token contributions, making them less robust under short sequences or localized token modifications.
Approach:	They propose a training-free method for AI-generated text detection based on an exon-aware token reweighting perspective.
Outcome:	The proposed method achieves state-of-the-art detection performance and robustness to adversarial attacks and varying input lengths.

Copied to clipboard

Haichao Zhu, Li Dong, Furu Wei, Wenhui Wang, Bing Qin, Ting Liu

DarwinTOD: LLM-Driven Lifelong Self-evolution for Task-oriented Dialog Systems (2026.acl-long)

Challenge:	Existing models for extractive reading comprehension are not good at deciding whether no answer is presented in the context.
Approach:	They propose a data augmentation technique by automatically generating relevant unanswerable questions according to an answerable question paired with its corresponding paragraph that contains the answer.
Outcome:	The proposed model performs better on the SQuAD 2.0 dataset than the baseline model and the BERT-large model.

Copied to clipboard

Shuyu Zhang, Yujie Liu, Xinru Wang, Cheng Zhang, Yanmin Zhu, Bin Li

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

Challenge:	Continual learning approaches fail to achieve autonomy lifelong improvement in dynamic environments . current task-oriented dialog systems are static, unable to learn from ongoing interactions .
Approach:	They propose a lifelong self-evolving dialog framework that integrates evolutionary computation and LLM driven self-improvement into a single framework.
Outcome:	The proposed framework surpasses state-of-the-art methods and exhibits continuous performance gains throughout evolution.

Copied to clipboard

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

LangSuit·E: Planning, Controlling and Interacting with Large Language Models in Embodied Text Environments (2024.findings-acl)

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

Zixia Jia, Mengmeng Wang, Baichen Tong, Song-Chun Zhu, Zilong Zheng

Table-as-Search: Agentic Information Seeking is Table Completion (2026.findings-acl)

Challenge:	Recent advances in Large Language Models (LLMs) have shown inspiring achievements in constructing autonomous agents that rely on language descriptions as inputs.
Approach:	They propose a flexible and simulation-free testbed that simulates 6 representative embodied tasks in textual embodies.
Outcome:	The proposed testbed offers adaptability to diverse environments without multiple simulation engines and allows easy customization of communication and action strategies.

Copied to clipboard

Tian Lan, Felix Henry, Bin Zhu, Qianghuai Jia, Junyang Ren, Qihang PU, Haijun Li, Longyue Wang, Zhao Xu, Weihua Luo

Automated Creativity Evaluation for Large Language Models: A Reference-Based Approach (2025.findings-emnlp)

Challenge:	Current Information Seeking (InfoSeeking) agents struggle to maintain focus and coherence during long-horizon exploration, as tracking search states within one plain-text context is inherently fragile.
Approach:	They propose a structured planning framework that reformulates the InfoSeeking task as a Table Completion task.
Outcome:	The proposed framework outperforms state-of-the-art frameworks across three kinds of benchmarks, including multi-agent framework and commercial systems.

Copied to clipboard

Ruizhe Li, Chiwei Zhu, Benfeng Xu, Xiaorui Wang, Zhendong Mao

Sparsity-Accelerated Training for Large Language Models (2024.findings-acl)

Challenge:	Existing methods for evaluating creativity of machine-generated texts rely on costly manual annotations or fail to align closely with human assessments.
Approach:	They propose an automated method based on the Torrance Test of Creative Writing (TTCW) .
Outcome:	The proposed method improves the alignment between LLM evaluations and human assessments.

Copied to clipboard

Da Ma, Lu Chen, Pengyu Wang, Hongshen Xu, Hanqi Li, Liangtai Sun, Su Zhu, Shuai Fan, Kai Yu

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

Challenge:	Large language models (LLMs) have demonstrated proficiency across various NLP tasks but often require additional training, such as continual pre-training and supervised fine-tuning.
Approach:	They propose to leverage sparsity in pre-trained LLMs to accelerate training by disregarding computations for unimportant neurons.
Outcome:	The proposed framework achieves comparable or superior performance to standard training while significantly accelerating the process.

Copied to clipboard

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

PCEE-BERT: Accelerating BERT Inference via Patient and Confident Early Exiting (2022.findings-naacl)

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

Zhen Zhang, Wei Zhu, Jinfan Zhang, Peng Wang, Rize Jin, Tae-Sun Chung

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

Challenge:	Pre-trained language models (PLMs) are the state-of-the-art (SOTA) models for natural language processing (NLP).
Approach:	They propose a patient and confident early exiting BERT (PCEE-BERT) that can work with different PLMs and popular model compression methods.
Outcome:	The proposed method outperforms existing models on the GLUE benchmarks and achieves different speed-up ratios.

Copied to clipboard

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

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

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

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

CLEAN–EVAL: Clean Evaluation on Contaminated Large Language Models (2024.findings-naacl)

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

Wenhong Zhu, Hongkun Hao, Zhiwei He, Yun-Ze Song, Jiao Yueyang, Yumeng Zhang, Hanxu Hu, Yiran Wei, Rui Wang, Hongyuan Lu

Hybrid Self-evolving Structured Memory for Computer-Use Agents (2026.findings-acl)

Challenge:	Existing methods to evaluate large language models are prone to data contamination.
Approach:	They propose a method which parses contaminated data and back-translates it into a candidate set.
Outcome:	The proposed method reduces data contamination and evaluates the LLMs more cleanly.

Copied to clipboard

Sibo Zhu, Wenyi WU, Kun Zhou, Stephen Wang, Biwei Huang

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

Challenge:	despite advances in vision–language models, real-world computer-use tasks remain challenging due to long-horizon workflows, diverse interfaces, and frequent intermediate errors.
Approach:	They propose a graph-based memory that couples discrete symbolic nodes with continuous trajectory embeddings.
Outcome:	The proposed system outperforms closed-source models in Qwen2.5-VL-7B and Gemini2.5-Pro-Vision on desktop and mobile platforms.

Copied to clipboard

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

Answering Ambiguous Questions through Generative Evidence Fusion and Round-Trip Prediction (2021.acl-long)

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

Yifan Gao, Henghui Zhu, Patrick Ng, Cicero Nogueira dos Santos, Zhiguo Wang, Feng Nan, Dejiao Zhang, Ramesh Nallapati, Andrew O. Arnold, Bing Xiang

Bridging the Granularity Gap for Acoustic Modeling (2023.findings-acl)

Challenge:	Open-domain question answering is a task to answer questions using passages with diverse topics.
Approach:	They propose a model that aggregates evidence from multiple passages to adaptively predict a single answer or a set of question-answer pairs for ambiguous questions.
Outcome:	The proposed model achieves state-of-the-art performance on AmbigQA dataset and shows competitive performance on NQ-Open and TriviaQA.

Copied to clipboard

Chen Xu, Yuhao Zhang, Chengbo Jiao, Xiaoqian Liu, Chi Hu, Xin Zeng, Tong Xiao, Anxiang Ma, Huizhen Wang, Jingbo Zhu

Generation, Distillation and Evaluation of Motivational Interviewing-Style Reflections with a Foundational Language Model (2024.eacl-long)

Challenge:	Despite the success of speech recognition, how to encode the speech features effectively remains an open problem.
Approach:	They propose a Progressive Down-Sampling technique which compresses acoustic features into coarser-grained units containing more complete semantic information, like text-level representation.
Outcome:	The proposed method yields comparable or better results on the speech recognition task and inference speedups ranging from 1.20x to 1.47x.

Copied to clipboard

Andrew Brown, Jiading Zhu, Mohamed Abdelwahab, Alec Dong, Cindy Wang, Jonathan Rose

Planning-Guided Tutoring with Assessment-Driven Memory for Pedagogical LLM Tutors (2026.acl-long)

Challenge:	Motivational Interviewing (MI) is a counselling technique used to guide people towards behaviour change.
Approach:	They propose a method for distilling reflections from a foundational language model into smaller models that can be owned and controlled.
Outcome:	The proposed method achieves 100% success rate on hold-out test set and 90% on the GPT-2 XL.

Copied to clipboard

Zechen Li, Qiannan Zhu, Mei Wang, Jia Li, Hua Huang

MEVTR: A Multilingual Model Enhanced with Visual Text Representations (2024.lrec-main)

Challenge:	Existing approaches to simulate tutor behaviors or preferences fail to sustain high-quality pedagogical conversations that provide explicit stepwise scaffolding and adapt to learners’ evolving cognitive states.
Approach:	They propose a planning-guided tutoring framework with an assessment-driven memory for multi-turn math dialogue tutoring.
Outcome:	Experiments on multi-turn math tutoring benchmarks show that ScaffoldLM significantly improves pedagogical tutoring quality over strong baselines.

Copied to clipboard

Xiaohua Wang, Wenlong Fei, Min Hu, Qingyu Zhang, Aoqiang Zhu

HiDe-LLaVA: Hierarchical Decoupling for Continual Instruction Tuning of Multimodal Large Language Model (2025.acl-long)

Challenge:	Existing models that generate multilingual text representations perform poorly on low-resource languages due to lack of representation space and model capacity.
Approach:	They propose a multilingual model enhanced with visual text representations which complements textual representations and extends multilingual representation space with visual representations.
Outcome:	The proposed model outperforms state-of-the-art models on zero-shot cross-lingual transfer tasks without the target language adapter.

Copied to clipboard

Haiyang Guo, Fanhu Zeng, Ziwei Xiang, Fei Zhu, Da-Han Wang, Xu-Yao Zhang, Cheng-Lin Liu

Does Multi-Encoder Help? A Case Study on Context-Aware Neural Machine Translation (2020.acl-main)

Challenge:	Existing methods to improve instructionfollowing performance of MLLMs often trade off memory efficiency for performance gains, compromising overall efficiency.
Approach:	They propose a task-specific expansion and task-general fusion framework based on variations in Centered Kernel Alignment (CKA) similarity across different model layers when trained on diverse datasets.
Outcome:	The proposed framework improves performance compared to existing benchmarks.

Copied to clipboard

Bei Li, Hui Liu, Ziyang Wang, Yufan Jiang, Tong Xiao, Jingbo Zhu, Tongran Liu, Changliang Li

Efficient Dialogue Complementary Policy Learning via Deep Q-network Policy and Episodic Memory Policy (2021.emnlp-main)

Challenge:	In encoder-decoder neural models, multiple encoders are used to represent contextual information in addition to the individual sentence.
Approach:	They propose to use multiple context encoders to encode the individual sentences in document-level neural machine translation (NMT) They propose a noisy dropout setup and a single-encoder approach to encode context sentences.
Outcome:	The proposed approach encodes the context and the current sentence without contexts.

Copied to clipboard

Yangyang Zhao, Zhenyu Wang, Changxi Zhu, Shihan Wang

In-Context Demonstration Selection with Cross Entropy Difference (2023.findings-emnlp)

Challenge:	Existing methods for training dialogue policies rely on a single learning system, but it requires many rounds of interaction.
Approach:	They propose a complementary policy learning framework which exploits the complementary advantages of the episodic memory (EM) policy and the deep Q-network (DQN) policy.
Outcome:	The proposed framework outperforms existing methods relying on a single learning system on three dialogue datasets.

Copied to clipboard

Dan Iter, Reid Pryzant, Ruochen Xu, Shuohang Wang, Yang Liu, Yichong Xu, Chenguang Zhu

ClinicalMC: A Benchmark for Multi-Course Clinical Decision-Making with Large Language Models (2026.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

Ruihui Hou, Siyi Zhu, Ziyue Huai, Guangya Yu, Yongqi Fan, ChunMing Wang, Tong Ruan

DemonAgent: Dynamically Encrypted Multi-Backdoor Implantation Attack on LLM-based Agent (2025.findings-emnlp)

Challenge:	Existing benchmarks assess LLM performance in single-course settings and lack systematic evaluation in multi-course scenarios, where a patient’s condition evolves over time.
Approach:	They propose to use large language models to assess their performance in multi-course clinical decision-making scenarios where a patient’s condition evolves over time.
Outcome:	The proposed model includes 1,275 Chinese and 5,804 English samples across four stages from admission to discharge.

Copied to clipboard

Pengyu Zhu, Zhenhong Zhou, Yuanhe Zhang, Shilinlu Yan, Kun Wang, Sen Su

APPSI-139: A Parallel Corpus of English Application Privacy Policy Summarization and Interpretation (2026.acl-long)

Challenge:	a new method for detecting advanced backdoors is proposed to bypass safety audits.
Approach:	They propose a backdoor implantation strategy that introduces dynamic encryption to bypass safety audits.
Outcome:	The proposed method achieves an attack success rate approaching 100% while maintaining a detection rate of 0%.

Copied to clipboard

Pengyun Zhu, Qiheng Sun, Long Wen, Yanbo Wang, Yang Cao, Junxu Liu, Deyi Xiong, Jinfei Liu, Zhibo Wang, Kui Ren

How Should We Enhance the Safety of Large Reasoning Models: An Empirical Study (2026.acl-long)

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

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

Beyond Single-View Detection: A Dual-Space Reasoning Framework for Interpretable Harmful Meme Understanding (2026.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

Wenqing Hou, Hongkui Tu, Ye Wang, Yue Zhang, Yuying Liu, Dong Zhu, Liqun Gao, Bin Zhou

QA-MoE: Towards a Continuous Reliability Spectrum with Quality-Aware Mixture of Experts for Robust Multimodal Sentiment Analysis (2026.acl-long)

Challenge:	Existing methods for identifying harmful memes rely on modal alignment or black-box classifiers . BPDMoE-Hate provides visual explanations for viewpoint selection and hierarchical structuring .
Approach:	They propose a framework that conceptualizes harmful meme detection as a process of "viewpoint decoupling and hierarchical fusion" they propose BPDMoE-Hate, which generates adversarial binary perspectives via VLMs and incorporates an adaptive viewpoint gating to facilitate viewpoint selection.
Outcome:	The proposed framework surpasses existing methods in performance and provides visual explanations for viewpoint selection and hierarchical structuring.

Copied to clipboard

Yitong Zhu, Yuxuan Jiang, Guanxuan Jiang, Bojing Hou, Peng Yuan Zhou, Ge Lin, Yuyang Wang

ReflectEvo: Improving Meta Introspection of Small LLMs by Learning Self-Reflection (2025.findings-acl)

Challenge:	Existing models that use multimodal inputs are often noisy or incomplete.
Approach:	They propose a Quality-Aware Mixture-of-Experts framework that quantifies modality reliability via aleatoric uncertainty.
Outcome:	The proposed framework is competitive or state-of-the-art across diverse degradation scenarios and exhibits a promising One-Checkpoint-for-all property in practice.

Copied to clipboard

Jiaqi Li, Xinyi Dong, Yang Liu, Zhizhuo Yang, Quansen Wang, Xiaobo Wang, Song-Chun Zhu, Zixia Jia, Zilong Zheng

Large-Scale Multimodal Knowledge Graph about Classical Chinese Poetry: Fine-grained Method and Comprehensive Evaluation (2026.findings-acl)

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

Shuo Wang, Qing Zhu, Yang Xiao, Minglong Lei

BoundRL: Efficient Token-level Structured Text Segmentation through Reinforced Boundary Generation (2026.findings-acl)

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

Haoyuan Li, Zhengyuan Shen, Sullam Jeoung, Yueyan Chen, Jiayu Li, Qi Zhu, Shuai Wang, Vassilis N. Ioannidis, Huzefa Rangwala

Understanding and Mitigating Bias Inheritance in LLM-based Data Augmentation on Downstream Tasks (2026.acl-long)

Challenge:	Structured texts often contain elements beyond plain language, such as code snippets, which conventional sentence-level segmentation methods cannot handle effectively.
Approach:	They propose a token-level approach that performs efficient token-based text segmentation and label prediction for long structured texts.
Outcome:	The proposed approach outperforms existing models on short-shot prompts and SFT and standard RLVR models on complex LLM prompts.

Copied to clipboard

Miaomiao Li, Hao Chen, Yang Wang, Tingyuan Zhu, Weijia Zhang, Kaijie Zhu, Kam-Fai Wong, Jindong Wang

UMRSpell: Unifying the Detection and Correction Parts of Pre-trained Models towards Chinese Missing, Redundant, and Spelling Correction (2023.acl-long)

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

Zheyu He, Yujin Zhu, Linlin Wang, Liang Xu

Improving Robustness of Language Models from a Geometry-aware Perspective (2022.findings-acl)

Challenge:	Chinese Spelling Correction (CSC) is a task of detecting and correcting misspelled charac- ters in Chinese texts.
Approach:	They propose a model to learn detection and correction parts together from a multi-task learning perspective.
Outcome:	The proposed model can learn detection and correction parts together from a multi-task learning perspective.

Copied to clipboard

Bin Zhu, Zhaoquan Gu, Le Wang, Jinyin Chen, Qi Xuan

Detoxification for LLM: From Dataset Itself (2026.acl-long)

Challenge:	Recent studies have found that removing the norm-bounded projection and increasing search steps in adversarial training can significantly improve robustness.
Approach:	They propose friendly adversarial data augmentation and geometry-aware adversarial training to achieve stronger robustness using fewer search steps.
Outcome:	The proposed method can obtain stronger robustness using fewer steps than existing methods.

Copied to clipboard

Wei Shao, Yihang Wang, Gao yu Zhu, Ziqiang Cheng, Lei Yu, Jiafeng Guo, Xueqi Cheng

Alignment for Efficient Tool Calling of Large Language Models (2025.emnlp-main)

Challenge:	Existing methods for large language models focus on post-training stage or inference time, while few tackle the source of toxicity, namely, the dataset itself.
Approach:	They propose to localize and rewrite toxic spans in raw corpora with SoCD, which guides an LLM to localized and preserving semantics while preserving toxicity.
Outcome:	The proposed method reduces TP from 0.42 to 0.18 and Expected Maximum Toxicity (EMT) from 0.43 to 0.20 on three LLMs.

Copied to clipboard

Hongshen Xu, Zihan Wang, Zichen Zhu, Lei Pan, Xingyu Chen, Shuai Fan, Lu Chen, Kai Yu

You Only Read Once (YORO): Learning to Internalize Database Knowledge for Text-to-SQL (2025.naacl-long)

Challenge:	Recent advances in tool learning have enabled large language models to integrate external tools, enhancing their task performance by expanding their knowledge boundaries.
Approach:	They propose a framework that combines probabilistic knowledge boundary estimation with dynamic decision-making to allow LLMs to better assess when to invoke tools based on their confidence.
Outcome:	The proposed framework shows significant improvements in tool efficiency by reducing unnecessary tool usage.

Copied to clipboard

Hideo Kobayashi, Wuwei Lan, Peng Shi, Shuaichen Chang, Jiang Guo, Henghui Zhu, Zhiguo Wang, Patrick Ng

Diagnosing Vision-and-Language Navigation: What Really Matters (2022.naacl-main)

Challenge:	Existing text-to-SQL systems encode the same schema for every question, resulting in unnecessary high inference cost and missing crucial database knowledge.
Approach:	They propose a paradigm that directly internalizes database knowledge into the parametric knowledge of a text-to-SQL model during training and eliminates the need for schema encoding during inference.
Outcome:	The proposed paradigm significantly reduces the input token length by 66%-98% and outperforms traditional systems on three benchmarks.

Copied to clipboard

Wanrong Zhu, Yuankai Qi, Pradyumna Narayana, Kazoo Sone, Sugato Basu, Xin Wang, Qi Wu, Miguel Eckstein, William Yang Wang

DecompEval: Evaluating Generated Texts as Unsupervised Decomposed Question Answering (2023.acl-long)

Challenge:	Existing models claim to be able to align object tokens with specific visual targets, but there are non-negligible gaps between the two.
Approach:	They conduct diagnostic experiments to examine how the agents perceive multimodal input by ablation diagnostics input data.
Outcome:	The results show that indoor and outdoor navigation agents refer to object and direction tokens when making decisions.

Copied to clipboard

Pei Ke, Fei Huang, Fei Mi, Yasheng Wang, Qun Liu, Xiaoyan Zhu, Minlie Huang

Revealing the Parallel Multilingual Learning within Large Language Models (2024.emnlp-main)

Challenge:	Existing evaluation metrics for natural language generation (NLG) tasks face the challenges on generalization ability and interpretability.
Approach:	They propose a metric that evaluates natural language generation tasks as an instruction-style question answering task and utilizes instruction-tuned pre-trained language models without training on evaluation datasets.
Outcome:	The proposed metric achieves state-of-the-art performance in untrained metrics for evaluating text summarization and dialogue generation, which exhibits strong dimension-level / task-level generalization ability and interpretability.

Copied to clipboard

Yongyu Mu, Peinan Feng, Zhiquan Cao, Yuzhang Wu, Bei Li, Chenglong Wang, Tong Xiao, Kai Song, Tongran Liu, Chunliang Zhang, JingBo Zhu

LoRA-drop: Efficient LoRA Parameter Pruning based on Output Evaluation (2025.coling-main)

Challenge:	Large language models (LLMs) can handle multilingual and cross-lingual text within a single input; however, previous studies focusing on using English as the pivot language to enhance language understanding and reasoning focus on using multiple languages.
Approach:	They propose to use parallel multilingual input to enhance the model's comprehension of the input and to examine how multilingual processing affects prediction.
Outcome:	The proposed model can handle multilingual and cross-lingual text within a single input, but previous studies focused on using English as the pivot language to enhance language understanding and reasoning.

Copied to clipboard

Hongyun Zhou, Xiangyu Lu, Wang Xu, Conghui Zhu, Tiejun Zhao, Muyun Yang

MobileNMT: Enabling Translation in 15MB and 30ms (2023.acl-industry)

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

Ye Lin, Xiaohui Wang, Zhexi Zhang, Mingxuan Wang, Tong Xiao, Jingbo Zhu

AgentThink: A Unified Framework for Tool-Augmented Chain-of-Thought Reasoning in Vision-Language Models for Autonomous Driving (2025.findings-emnlp)

Challenge:	Existing work on NMT models is limited in storage, memory, computation and power consumption.
Approach:	They propose a mobile machine translation system that can translate in 15MB and 30ms on devices.
Outcome:	The proposed system can translate in 15MB and 30ms on mobile devices.

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

TCPO: Thought-Centric Preference Optimization for Effective Embodied Decision-making (2025.emnlp-main)

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

Kechen Jiao, Zhirui Fang, Jiahao Liu, Bei Li, Qifan Wang, Xinyu Liu, Junhao Ruan, Zhongjian Qiao, Yifan Zhu, Yaxin Xu, Jingang Wang, Xiu Li

AdapTime: Enabling Adaptive Temporal Reasoning in Large Language Models (2026.findings-acl)

Challenge:	Existing post-SFT methods for embodied AI are constrained by sparse rewards and action-only optimization, resulting in low sample efficiency, poor consistency, and model degradation.
Approach:	They propose to integrate Thought-Centric Preference Optimization (TCPO) into embodied decision-making by transforming sparse reward signals into richer step sample pairs.
Outcome:	The proposed approach achieves an average success rate of 26.67% in the ALFWorld environment, and a 6% improvement over RL4VLM.

Copied to clipboard

Yimin Deng, Yejing Wang, Zhenxi Lin, Zichuan Fu, Guoshuai Zhao, Derong Xu, Yefeng Zheng, Xiangyu Zhao, Xian Wu, Li Zhu, Xueming Qian

TROVE: A Challenge for Fine-Grained Text Provenance via Source Sentence Tracing and Relationship Classification (2025.acl-long)

Challenge:	Existing methods for temporal reasoning are limited and apply a fixed pipeline to all questions.
Approach:	They propose an adaptive temporal reasoning method that dynamically executes reasoning steps based on context and task requirements.
Outcome:	Experiments on two temporal QA benchmarks show the proposed method works.

Copied to clipboard

Junnan Zhu, Min Xiao, Yining Wang, Feifei Zhai, Yu Zhou, Chengqing Zong

Hybrid Alignment Training for Large Language Models (2024.findings-acl)

Challenge:	Large language models have demonstrated great potential in natural language generation, but their widespread adoption has raised concerns regarding content reliability and accountability.
Approach:	They propose a challenge to trace each sentence of a target text back to specific source sentences within potentially lengthy or multi-document inputs.
Outcome:	The proposed challenge traces each sentence of a target text back to specific source sentences . the dataset includes 11 scenarios covering QA and summarization in english and Chinese .

Copied to clipboard

Chenglong Wang, Hang Zhou, Kaiyan Chang, Bei Li, Yongyu Mu, Tong Xiao, Tongran Liu, JingBo Zhu

DGPO: Beyond Pairwise Preferences with Directional Consistent Groupwise Optimization (2026.findings-acl)

Challenge:	Existing approaches to align large language models with instructions and preferences are conflicting . et al., 2023b) show that hybrid alignment training can outperform baselines .
Approach:	They propose a hybrid alignment training approach based on alternating alignment and modified elastic weight consolidation methods to achieve better collaboration between different alignment tasks.
Outcome:	The proposed approach outperforms baseline alignment training methods on summarization and dialogue tasks.

Copied to clipboard

Mengyi Deng, Zhiwei Li, Xin Li, Tingyu Zhu, Yulan Yuan, Zhijiang Guo, Wei Wang

Event Extraction as Multi-turn Question Answering (2020.findings-emnlp)

Challenge:	Existing methods for directional consistency alignment of large language models are limited . a recent study suggests reverse supervision as a complement to forward reasoning .
Approach:	They propose a framework that aggregates supervision signals at the group level and explicitly models direction-aware alignment through multi-candidate comparisons.
Outcome:	The proposed framework achieves 3.2% accuracy improvement across five benchmarks and multiple datasets.

Copied to clipboard

Fayuan Li, Weihua Peng, Yuguang Chen, Quan Wang, Lu Pan, Yajuan Lyu, Yong Zhu

RA2FD: Distilling Faithfulness into Efficient Dialogue Systems (2024.emnlp-main)

Challenge:	Current approaches to event extraction fail to model rich interactions among event types and arguments of different roles.
Approach:	They propose a new paradigm that formulates event extraction as multi-turn question answering . they propose to use reading comprehension problems to extract triggers and arguments .
Outcome:	The proposed approach outperforms current state-of-the-art on argument extraction tasks . it makes full use of dependency among arguments and event types, and generalizes well .

Copied to clipboard

Zhiyuan Zhu, Yusheng Liao, Chenxin Xu, Yunfeng Guan, Yanfeng Wang, Yu Wang

BabyWalk: Going Farther in Vision-and-Language Navigation by Taking Baby Steps (2020.acl-main)

Challenge:	Retrieval Augmented Generation (RAG) is effective but inference inefficient, while Retrieral Free Generations (RFG) are more efficient but sacrifice faithfulness.
Approach:	They propose a retrieval-free model training scheme that uses a teacher-student framework to distill the faithfulness capacity of a student's knowledge-infused responses.
Outcome:	The proposed model surpasses the previous SOTA RFG model on knowledge-grounded dialogue datasets by an average of 33% while improving inference efficiency.

Copied to clipboard

Wang Zhu, Hexiang Hu, Jiacheng Chen, Zhiwei Deng, Vihan Jain, Eugene Ie, Fei Sha

SERM: Self-Evolving Relevance Model with Agent-Driven Learning from Massive Query Streams (2026.findings-acl)

Challenge:	Existing state-of-the-art VLN agents do not generalize well for long navigation tasks.
Approach:	They propose a VLN agent that is learned to navigate by decomposing long instructions into shorter ones and completing them sequentially.
Outcome:	The proposed agent can follow long instructions better than existing ones, but it does not generalize well.

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.

StreamMeCo: Long-Term Agent Memory Compression for Efficient Streaming Video Understanding (2026.findings-acl)

Copied to clipboard

Junxi Wang, Te Sun, Jiayi Zhu, Junxian Li, Haowen Xu, Zichen Wen, Xuming Hu, Zhiyu li, Linfeng Zhang

LLM Agents for Education: Advances and Applications (2025.findings-emnlp)

Challenge:	StreamMeCo is an efficient Stream Agent Memory Compression framework for video understanding.
Approach:	They propose an efficient Stream Agent Memory Compression framework that evicts redundant memory nodes and introduces a time-decay memory retrieval mechanism to mitigate performance degradation.
Outcome:	The proposed framework achieves 1.87 speedup in memory retrieval while delivering an average accuracy improvement of 1.0% on three challenging benchmark datasets.

Copied to clipboard

Zhendong Chu, Shen Wang, Jian Xie, Tinghui Zhu, Yibo Yan, Jingheng Ye, Aoxiao Zhong, Xuming Hu, Jing Liang, Philip S. Yu, Qingsong Wen

Entity-level Factual Consistency of Abstractive Text Summarization (2021.eacl-main)

Challenge:	Large Language Model (LLM) agents are transforming education by automating complex tasks and enhancing both teaching and learning processes.
Approach:	This survey analyzes recent advances in applying Large Language Model agents to educational settings . it highlights ethical issues, hallucination and overreliance, and integration with existing ecosystems .
Outcome:	The authors analyze the technologies enabling LLM agents and highlight key challenges in deploying them in educational settings.

Copied to clipboard

Feng Nan, Ramesh Nallapati, Zhiguo Wang, Cicero Nogueira dos Santos, Henghui Zhu, Dejiao Zhang, Kathleen McKeown, Bing Xiang

InfoCL: Alleviating Catastrophic Forgetting in Continual Text Classification from An Information Theoretic Perspective (2023.findings-emnlp)

Challenge:	Existing models exhibit entity hallucination, generating names of entities that are not present in the source document.
Approach:	They propose to use entity-level factual consistency to improve model quality . they propose to filter the training data to reduce entity hallucination problem .
Outcome:	The proposed model can reduce the entity hallucination problem by filtering the training data.

Copied to clipboard

Yifan Song, Peiyi Wang, Weimin Xiong, Dawei Zhu, Tianyu Liu, Zhifang Sui, Sujian Li

Same Claim, Different Judgment: Benchmarking Scenario-Induced Bias in Multilingual Financial Misinformation Detection (2026.findings-acl)

Challenge:	Recent studies have identified the severe performance decrease on analogous classes as a key factor for catastrophic forgetting.
Approach:	They propose a replay-based continual text classification method that uses fast-slow and current-past contrastive learning to perform mutual information maximization and better recover previously learned representations.
Outcome:	The proposed method achieves state-of-the-art on three text classification tasks.

Copied to clipboard

Zhiwei Liu, Yupeng Cao, Yuechen Jiang, Mohsinul Kabir, Polydoros Giannouris, Chen Xu, Ziyang Xu, Tianlei Zhu, Md. Tariquzzaman, Triantafillos Papadopoulos, Yan Wang, Lingfei Qian, Xueqing Peng, Zhuohan Xie, Ye Yuan, Saeed Almheiri, Abdulrazzaq Alnajjar, Ming-Bin Chen, Harry Stuart, Paul Thompson, Prayag Tiwari, Alejandro Lopez-Lira, Xue Liu, Jimin Huang, Sophia Ananiadou

ScreenQA: Large-Scale Question-Answer Pairs Over Mobile App Screenshots (2025.naacl-long)

Challenge:	Existing research on LLM biases has focused on direct questioning or general-purpose settings . pronounced behavioral biase despite their growing deployment in financial analysis, forecasting, and decision support.
Approach:	They propose a benchmark to evaluate behavioral biases of large language models in MFMD . they use a multilingual financial misinformation dataset to integrate these with misinformation claims .
Outcome:	The proposed benchmark evaluates behavioral biases of large language models across economic scenarios.

Copied to clipboard

Yu-Chung Hsiao, Fedir Zubach, Gilles Baechler, Srinivas Sunkara, Victor Carbune, Jason Lin, Maria Wang, Yun Zhu, Jindong Chen

See the World, Discover Knowledge: A Chinese Factuality Evaluation for Large Vision Language Models (2025.findings-acl)

Challenge:	Existing screen datasets focus on low-level structural and component understanding or on a much higher-level composite task such as navigation and task completion for autonomous agents.
Approach:	They propose to annotate 86k question-answer pairs over the RICO dataset to benchmark screen content understanding.
Outcome:	The proposed dataset covers full answers, short answer phrases, and corresponding UI contents with bounding boxes, enabling four subtasks to address various application scenarios.

Copied to clipboard

Jihao Gu, Yingyao Wang, Pi Bu, Chen Wang, Ziming Wang, Tengtao Song, Donglai Wei, Jiale Yuan, Yingxiu Zhao, Yancheng He, Shilong Li, Jiaheng Liu, Meng Cao, Jun Song, Yingshui Tan, Xiang Li, Wenbo Su, Xiaoyong Zhu, Bo Zheng

Marco-Bench-MIF: On Multilingual Instruction-Following Capability of Large Language (2025.acl-long)

Challenge:	Existing models for large vision language models do not fully reflect their knowledge capacity and reliability, resulting in erroneous outputs that do not align with the image content or provide answers lacking knowledge evidence.
Approach:	They propose a Chinese-based benchmark for visual factuality across 8 major topics and 56 subtopics and a multi-hop question construction.
Outcome:	The proposed model decouples visual factuality into two parts: seeing the world and discovering knowledge.

Copied to clipboard

Bo Zeng, Chenyang Lyu, Sinuo Liu, Mingyan Zeng, Minghao Wu, Xuanfan Ni, Tianqi Shi, Yu Zhao, Yefeng Liu, Chenyu Zhu, Ruizhe Li, Jiahui Geng, Qing Li, Yu Tong, Longyue Wang, Weihua Luo, Kaifu Zhang

Towards Interpretable Tabular Reasoning: Enhancing LLM Reasoning on Tabular Data with Pre-Constructed Logic Graph (2026.acl-long)

Challenge:	Existing datasets for instruction-following are monolingual and centered on English . existing data are unable to capture linguistic and cultural subtle differences .
Approach:	They propose an extension of IFEval to a localized multilingual version called Marco-Bench-MIF . their benchmark addresses linguistic constraints and cultural references via translation and verification .
Outcome:	The proposed extension of IFEval to a localized multilingual version covers 30 languages with varying levels of localization.

Copied to clipboard

Lirong Gao, Zewei Yu, Zhongrui Yin, Qi Zhang, Yuke Zhu, Bo Zheng, Haobo Wang, Junbo Zhao, Gang Chen, Sheng Guo

I²B-LPO: Latent Policy Optimization via Iterative Information Bottleneck (2026.acl-long)

Challenge:	Tabular data is used in fields such as finance and healthcare due to its heterogeneity and complexity.
Approach:	They propose a Logic-Graph-Enhanced LLM Reasoning framework that integrates the strengths of tree-based models and LLMs to improve their interpretability.
Outcome:	The proposed framework outperforms tree-based models and state-of-the-art LLMs on tabular prediction tasks, achieving superior accuracy and interpretability.

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

SEEKR: Selective Attention-Guided Knowledge Retention for Continual Learning of Large Language Models (2024.emnlp-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

Jinghan He, Haiyun Guo, Kuan Zhu, Zihan Zhao, Ming Tang, Jinqiao Wang

ClusterUCB: Efficient Gradient-Based Data Selection for Targeted Fine-Tuning of LLMs (2025.findings-emnlp)

Challenge:	Existing methods fail to fully exploit the knowledge embedded in models from previous tasks . Existing techniques fail to exploit the information embedded in previous tasks, resulting in a large number of replay samples to achieve good results.
Approach:	They propose a method that uses attention weights to extract knowledge from previous tasks . they use a data replay strategy to extract the knowledge from the previous tasks.
Outcome:	The proposed method achieves comparable or even better performance with only 1/10 of replayed data used by other methods.

Copied to clipboard

Zige Wang, Qi Zhu, Fei Mi, Minghui Xu, Ruochun Jin, Wenjing Yang

Why LLMs Hallucinate on Structured Knowledge: A Mechanistic Analysis of Reasoning over Linearized Representations (2026.acl-long)

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

Shanghao Li, Jinda Han, Yibo Wang, Yuanjie Zhu, Zihe Song, Langzhou He, Kenan Kamel A Alghythee, Philip S. Yu

Retrieval Enhanced Model for Commonsense Generation (2021.findings-acl)

Challenge:	Existing literature primarily addresses this problem through external interventions such as retrieval augmentation and prompt engineering at the input or output level.
Approach:	They find that LLMs can still produce hallucinated outputs when using structured external knowledge.
Outcome:	The proposed models fail to ground the provided knowledge, causing the model to revert to parametric memory.

Copied to clipboard

Han Wang, Yang Liu, Chenguang Zhu, Linjun Shou, Ming Gong, Yichong Xu, Michael Zeng

Zero-Shot Learners for Natural Language Understanding via a Unified Multiple Choice Perspective (2022.emnlp-main)

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

Ping Yang, Junjie Wang, Ruyi Gan, Xinyu Zhu, Lin Zhang, Ziwei Wu, Xinyu Gao, Jiaxing Zhang, Tetsuya Sakai

Entailment Tree Explanations via Iterative Retrieval-Generation Reasoner (2022.findings-naacl)

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

Danilo Neves Ribeiro, Shen Wang, Xiaofei Ma, Rui Dong, Xiaokai Wei, Henghui Zhu, Xinchi Chen, Peng Xu, Zhiheng Huang, Andrew Arnold, Dan Roth

Question Answering

Challenge:	Large language models have achieved high performance on various natural language benchmarks, but the explainability of their output remains elusive.
Approach:	They propose an architecture called iterative retrieval-generation reasoner that generates an entailment tree that explains a given hypothesis by using premises from C.
Outcome:	The proposed model outperforms existing benchmarks on premise retrieval and entailment tree generation with around 300% gain in overall correctness.

GradOT: Training-free Gradient-preserving Offsite-tuning for Large Language Models (2025.acl-long)

Copied to clipboard

Kai Yao, Zhaorui Tan, Penglei Gao, Lichun Li, Kaixin Wu, Yinggui Wang, Yuan Zhao, Yixin Ji, Jianke Zhu, Wei Wang

AUTOGEN STUDIO: A No-Code Developer Tool for Building and Debugging Multi-Agent Systems (2024.emnlp-demo)

Challenge:	Existing methods for offsite-tuning of large language models require high computational costs and lack theoretical analysis.
Approach:	They propose an offsite-tuning approach that selectively applies compression techniques such as rank compression and channel pruning to preserve the gradients of fine-tuned adapters while ensuring privacy.
Outcome:	The proposed method surpasses existing OT methods in privacy protection and model performance.

Copied to clipboard

Victor Dibia, Jingya Chen, Gagan Bansal, Suff Syed, Adam Fourney, Erkang Zhu, Chi Wang, Saleema Amershi

Verifier-Free RL for LLMs via Intrinsic Gradient-Norm Reward (2026.findings-acl)

Challenge:	Multi-agent systems are emerging as effective pattern for solving long-running, complex tasks in numerous do- mains.
Approach:	They propose a no-code developer tool for rapidly prototyping, debugging, and evaluating multi-agent work flows built upon the AUTOGEN framework.
Outcome:	The proposed tool provides an intuitive drag-and-drop UI for agent workflow specification, interactive evaluation and debugging of workflows, and a gallery of reusable agent components.

Copied to clipboard

Xuexiang Wen, Hang Yu, Linchao Zhu, Gaoang Wang

Certainty in Uncertainty: Reasoning over Uncertain Knowledge Graphs with Statistical Guarantees (2025.emnlp-main)

Challenge:	Large Language Models (LLMs) have demonstrated remarkable capabilities in reasoning tasks and general tasks.
Approach:	They propose a "Verifier-free Intrinsic Gradient-Norm Reward" that uses only the policy model itself.
Outcome:	The proposed reward outperforms the state-of-the-art RLIF baseline INTUITOR on math benchmarks and shows cross-domain transfer to code benchmarks when trained only on math data.

Copied to clipboard

Yuqicheng Zhu, Jingcheng Wu, Yizhen Wang, Hongkuan Zhou, Jiaoyan Chen, Evgeny Kharlamov, Steffen Staab

MTAG: Modal-Temporal Attention Graph for Unaligned Human Multimodal Language Sequences (2021.naacl-main)

Challenge:	Existing methods produce only point estimates, without quantifying predictive uncertainty—limiting their reliability in high-stakes applications where understanding confidence in predictions is crucial.
Approach:	They propose a framework that generates prediction intervals guaranteed to contain the true score with a user-specified level of confidence.
Outcome:	The proposed framework generates prediction intervals guaranteed to contain the true score with a user-specified level of confidence.

Copied to clipboard

Jianing Yang, Yongxin Wang, Ruitao Yi, Yuying Zhu, Azaan Rehman, Amir Zadeh, Soujanya Poria, Louis-Philippe Morency

Bit-by-Bit: Progressive QAT Strategy with Outlier Channel Splitting for Stable Low-Bit LLMs (2026.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

Binxing Xu, Hao Gu, Lujun Li, Hao Wang, Bei Liu, Jiacheng Liu, Qiyuan Zhu, Xintong Yang, Chao Li, Sirui Han, Yike Guo

Towards Understanding Sample Variance in Visually Grounded Language Generation: Evaluations and Observations (2020.emnlp-main)

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

Wanrong Zhu, Xin Wang, Pradyumna Narayana, Kazoo Sone, Sugato Basu, William Yang Wang

Multimodal Invariant Sentiment Representation Learning (2025.findings-acl)

Challenge:	A major challenge in visually grounded language generation is to build robust benchmark datasets and models that can generalize well in real-world settings.
Approach:	They propose to use visual attention to build robust benchmark datasets and models that can generalize well in real-world settings.
Outcome:	The proposed models show that human-generated references vary drastically in different datasets/tasks, revealing the nature of each task.

Copied to clipboard

Aoqiang Zhu, Min Hu, Xiaohua Wang, Jiaoyun Yang, Yiming Tang, Ning An

Discontinuous Named Entity Recognition as Maximal Clique Discovery (2021.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

Yucheng Wang, Bowen Yu, Hongsong Zhu, Tingwen Liu, Nan Yu, Limin Sun

APOLLO: A Simple Approach for Adaptive Pretraining of Language Models for Logical Reasoning (2023.acl-long)

Challenge:	Existing methods for named entity recognition break the recognition process into several sequential steps.
Approach:	They propose a method that breaks the recognition process into several sequential steps . they construct a segment graph for each sentence and a grid tagging scheme to learn it .
Outcome:	Experiments show that the proposed method outperforms the state-of-the-art model and achieves 5x speedup over the SOTA model.

Copied to clipboard

Soumya Sanyal, Yichong Xu, Shuohang Wang, Ziyi Yang, Reid Pryzant, Wenhao Yu, Chenguang Zhu, Xiang Ren

RGAR: Recurrence Generation-augmented Retrieval for Factual-aware Medical Question Answering (2025.findings-emnlp)

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

Sichu Liang, Linhai Zhang, Hongyu Zhu, Wenwen Wang, Yulan He, Deyu Zhou

Dynamic Curriculum Learning for Low-Resource Neural Machine Translation (2020.coling-main)

Challenge:	Existing retrieval approaches often overlook patient-specific factual knowledge embedded in EHRs . existing retrieval frameworks often overlook this factual information, limiting its effectiveness in clinical decision-making.
Approach:	They propose a recurrence generation-augmented retrieval framework that synergizes factual and conceptual knowledge from dual sources.
Outcome:	The proposed framework improves on factual-aware medical QA benchmarks.

Copied to clipboard

Chen Xu, Bojie Hu, Yufan Jiang, Kai Feng, Zeyang Wang, Shen Huang, Qi Ju, Tong Xiao, Jingbo Zhu

CE-VDG: Counterfactual Entropy-based Bias Reduction for Video-grounded Dialogue Generation (2024.lrec-main)

Challenge:	Recent work on neural machine translation (NMT) has demonstrated impressive performance improvements and became the de-facto standard.
Approach:	They propose a dynamic curriculum learning method to reorder training samples in training using a Transformer-based system.
Outcome:	The proposed method outperforms baselines on three low-resource machine translation benchmarks and different sized data of WMT’16 En-De.

Copied to clipboard

Hongcheng Liu, Pingjie Wang, Zhiyuan Zhu, Yanfeng Wang, Yu Wang

Quantifying Semantic Emergence in Language Models (2025.acl-long)

Challenge:	Existing methods to reduce question-related bias in video-grounded dialogue generation (VDG) however, the dataset often contains inherent bias, which can cause VDG models to learn spurious correlations between questions and answers.
Approach:	They propose to extend the counterfactual reasoning from the information entropy perspective to the generative task, which can effectively reduce the question-related bias in the auto-regressive generation task.
Outcome:	The proposed method can reduce question-related bias in the auto-regressive generation task by using counterfactual entropy as an external loss.

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.

FastCorrect 2: Fast Error Correction on Multiple Candidates for Automatic Speech Recognition (2021.findings-emnlp)

Copied to clipboard

Yichong Leng, Xu Tan, Rui Wang, Linchen Zhu, Jin Xu, Wenjie Liu, Linquan Liu, Xiang-Yang Li, Tao Qin, Edward Lin, Tie-Yan Liu

Using Linguistic Entrainment to Evaluate Large Language Models for Use in Cognitive Behavioral Therapy (2025.findings-naacl)

Challenge:	Error correction is widely used in automatic speech recognition (ASR) to post-process the generated sentence.
Approach:	They propose a fast correction model that takes multiple ASR candidates as input for better correction accuracy.
Outcome:	The proposed model can reduce the word error rate (WER) with multiple candidates by 3.2% and 2.6%.

Copied to clipboard

Mina Kian, Kaleen Shrestha, Katrin Fischer, Xiaoyuan Zhu, Jonathan Ong, Aryan Trehan, Jessica Wang, Gloria Chang, Séb Arnold, Maja Mataric

Second Language (Arabic) Acquisition of LLMs via Progressive Vocabulary Expansion (2025.acl-long)

Challenge:	Entrainment is a communication process that builds a strong relationship between a mental health therapist and their client.
Approach:	They evaluate the linguistic entrainment of an LLM in a mental health dialog setting and compare it to trained therapists and non-expert online peer supporters.
Outcome:	The proposed model outperforms humans in a cognitive behavioral therapy setting.

Copied to clipboard

Jianqing Zhu, Huang Huang, Zhihang Lin, Juhao Liang, Zhengyang Tang, Khalid Almubarak, Mosen Alharthi, Bang An, Juncai He, Xiangbo Wu, Fei Yu, Junying Chen, Ma Zhuoheng, Yuhao Du, He Zhang, Saied Alshahrani, Emad A. Alghamdi, Lian Zhang, Ruoyu Sun, Haizhou Li, Benyou Wang, Jinchao Xu

Integrating Visual Modalities with Large Language Models for Mental Health Support (2025.coling-main)

Challenge:	In the evolving landscape of large language models, the predominant focus has been on English and Chinese.
Approach:	They propose to utilize Arabic-specific vocabulary in the tokenizer to accelerate decoding.
Outcome:	The proposed model achieves decent performance comparable to the best Arabic LLMs across various Arabic benchmarks.

Copied to clipboard

Zhouan Zhu, Shangfei Wang, Yuxin Wang, Jiaqiang Wu

Bypassing Neural Evaluations for Fast Audio Editing via Adaptive Trajectory Extrapolation (2026.findings-acl)

Challenge:	Existing work of mental health support primarily utilizes unimodal textual data and fails to understand and respond to users’ emotional states comprehensively.
Approach:	They propose a framework that integrates multimodal inputs and counseling strategies to enhance the performance of Large Language Models (LLMs) This approach allows LLMs to generate more nuanced and supportive responses.
Outcome:	The proposed framework outperforms existing models and delivers more empathetic, coherent, and contextually relevant mental health support responses.

Copied to clipboard

Xiaoqian Liu, Zhengkun Ge, Jianjin Wang, Haoran Zhang, Yuan Ge, Kaiyan Chang, Chen Xu, Tong Xiao, Zhengtao Yu, Linfeng Zhang, JingBo Zhu

DVMap: Fine-Grained Pluralistic Value Alignment via High-Consensus Demographic-Value Mapping (2026.acl-long)

Challenge:	Recent advances in audio diffusion models have significantly improved text-to-audio editing via inversion techniques, but these models typically rely on dense, fixed-step sampling trajectories to maintain structural integrity.
Approach:	They propose a model-agnostic Adaptive Trajectory Extrapolation framework that accelerates inversion-based editing process by dynamically evaluating only the most critical generative phases.
Outcome:	The proposed framework achieves a 3.9 speedup with negligible loss in fidelity.

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 .

RankNAS: Efficient Neural Architecture Search by Pairwise Ranking (2021.emnlp-main)

Copied to clipboard

Chi Hu, Chenglong Wang, Xiangnan Ma, Xia Meng, Yinqiao Li, Tong Xiao, Jingbo Zhu, Changliang Li

A Systematic Assessment of Language Models with Linguistic Minimal Pairs in Chinese (2026.tacl-1)

Challenge:	Existing methods require training millions of architectures to estimate the accuracy of the search results.
Approach:	They propose a performance ranking method (RankNAS) that uses pairwise ranking and search space pruning to enlarge the search space.
Outcome:	The proposed method significantly accelerates NAS through pairwise ranking and search space pruning.

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

Beyond Full Fine-tuning: Harnessing the Power of LoRA for Multi-Task Instruction Tuning (2024.lrec-main)

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

Chunlei Xin, Yaojie Lu, Hongyu Lin, Shuheng Zhou, Huijia Zhu, Weiqiang Wang, Zhongyi Liu, Xianpei Han, Le Sun

FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluation (D18-1)

Challenge:	Low-Rank Adaptation (LoRA) is a parameter-efficient fine-tuning algorithm for large-scale language models.
Approach:	They conduct a systematic study of Low-Rank Adaptation (LoRA) on diverse tasks and rich resources with different learning capacities.
Outcome:	The proposed algorithm can achieve remarkable performance in high-resource and multi-task scenarios, even comparable to full fine-tuning.

Copied to clipboard

Xu Han, Hao Zhu, Pengfei Yu, Ziyun Wang, Yuan Yao, Zhiyuan Liu, Maosong Sun

Towards IP Intelligence: Benchmarking Large Language Models on Intellectual Property Knowledge and Practice (2026.findings-acl)

Challenge:	Empirical results show that even the most competitive few-shot learning models struggle on this task, especially as compared with humans.
Approach:	They propose a Few-Shot Relation Classification Dataset consisting of 70, 000 sentences on 100 relations derived from Wikipedia and annotated by crowdworkers.
Outcome:	The proposed methods perform well on the most competitive few-shot learning models, especially as compared with humans.

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

Reinforcement Learning on Pre-Training Data (2026.acl-long)

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

Siheng Li, Kejiao Li, Zenan Xu, Guanhua Huang, Kun Li, Haoyuan Wu, null Wujiajia, Zihao Zheng, Chenchen Zhang, Kun Shi, Xue Gong, Qi Yi, Ruibin Xiong, Tingqiang Xu, Yuhao Jiang, Jianfeng Yan, Yuyuan Zeng, Guanghui Xu, Jinbao Xue, Zhijiang xu, Zheng Fang, Shuai LI, Qibin Liu, Xiaoxue Li, Zhuoyu Li, Yangyu Tao, Fei Gao, Cheng Jiang, Bochao Wang, Kai Liu, Jianchen Zhu, Wai Lam, Bo Zhou, Di Wang

RealHiTBench: A Comprehensive Realistic Hierarchical Table Benchmark for Evaluating LLM-Based Table Analysis (2025.findings-acl)

Challenge:	Recent progress in large language models is driven by scaling of training compute through pre-training with nexttoken prediction (NTP) or post-training (RL) Pre-training using NTP enables models to acquire extensive knowledge and skills from general data, but it suffers from data inefficiency and catastrophic forgetting in continual learning settings.
Approach:	They propose to scale training compute through pre-training with next-token prediction (NTP) or post-training by scaling reinforcement learning (RL) to improve learning from general data.
Outcome:	Experiments on multiple benchmarks and models show that the proposed approach improves continual pre-training and provides a strong foundation for post-training on Qwen3-8B-Base.

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

Noise-injected Consistency Training and Entropy-constrained Pseudo Labeling for Semi-supervised Extractive Summarization (2022.coling-1)

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

Yiming Wang, Qianren Mao, Junnan Liu, Weifeng Jiang, Hongdong Zhu, Jianxin Li

DISCO Balances the Scales: Adaptive Domain- and Difficulty-Aware Reinforcement Learning on Imbalanced Data (2025.findings-emnlp)

Challenge:	Existing studies on semi-supervised learning methods focus on how to effectively utilize abundant unlabeled data.
Approach:	They propose a semi-supervised consistency training method to regularize model predictions and a pseudo-labeling strategy to obtain high-confidence labels from unlabeled predictions.
Outcome:	The proposed method improves extractive summarization over an insufficient labeled dataset.

Copied to clipboard

Yuhang Zhou, Jing Zhu, Shengyi Qian, Zhuokai Zhao, Xiyao Wang, Xiaoyu Liu, Ming Li, Paiheng Xu, Wei Ai, Furong Huang

On the Emotion Understanding of Synthesized Speech (2026.acl-long)

Challenge:	Large Language Models (LLMs) are increasingly aligned with human preferences through Reinforcement Learning from Human Feedback (RLHF).
Approach:	a new study proposes a domain-informed self-consistency policy optimization extension to GRPO that addresses inter-group imbalance.
Outcome:	a new extension of GRPO addresses inter-group imbalance with two key innovations . the proposed method outperforms existing GR PO variants by 5% on Qwen3 models .

Copied to clipboard

Yuan Ge, Haishu Zhao, AoKai Hao, Junxiang Zhang, Bei Li, Xiaoqian Liu, Chenglong Wang, Jianjin Wang, Bingsen Zhou, Bingyu Liu, JingBo Zhu, Zhengtao Yu, Tong Xiao

SCCS: Semantics-Consistent Cross-domain Summarization via Optimal Transport Alignment (2023.findings-acl)

Challenge:	Existing models for emotion understanding do not capture fundamental features of synthesized speech.
Approach:	They evaluate emotion recognition models on synthesized speech using SER models and generative models.
Outcome:	The proposed model can't generalize to synthesized speech because of speech token prediction . generative models tend to infer emotion from textual semantics while ignoring paralinguistic cues.

Copied to clipboard

Jielin Qiu, Jiacheng Zhu, Mengdi Xu, Franck Dernoncourt, Trung Bui, Zhaowen Wang, Bo Li, Ding Zhao, Hailin Jin

Seer Self-Consistency: Advance Budget Estimation for Adaptive Test-Time Scaling (2026.findings-acl)

Challenge:	Existing methods for multimodal summarization ignore the structure and semantics of the whole video and article.
Approach:	They propose a semantic-consistent cross-domain summarization model that extracts features from video and article and uses fusion methods to select representative one.
Outcome:	The proposed model produces high-quality multimodal summaries on three MSMO datasets.

Copied to clipboard

Shiyu Ji, Yixuan Wang, Yijun Liu, Qingfu Zhu, Wanxiang Che

Challenge:	Large Language Models (LLMs) have demonstrated exceptional performance in reasoning tasks, particularly in mathematics.
Approach:	They propose a dynamic self-consistency framework that integrates System 1 and System 2 reasoning to improve token efficiency and latency.
Outcome:	The proposed method outperforms existing methods, achieving up to 47% reduction in token consumption and 43% reduction in inference latency without significant performance loss.

MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale (2025.acl-long)

Copied to clipboard

Jiawei Guo, Tianyu Zheng, Yizhi Li, Yuelin Bai, Bo Li, Yubo Wang, King Zhu, Graham Neubig, Wenhu Chen, Xiang Yue

Intent Contrastive Learning Based on Multi-view Augmentation for Sequential Recommendation (2025.coling-main)

Challenge:	Current instruction-tuning datasets focus on simplistic visual question answering tasks, and provide phrase-level answers without any intermediate rationales.
Approach:	They propose to use open-source multimodal large language models to train MLLMs on a dataset with 12M instruction-response pairs to elicit CoT reasoning.
Outcome:	The proposed model achieves state-of-the-art performance on benchmarks such as MathVerse, MMMU-Pro, and MuirBench, and gains improvements of up to 4% on non-reasoning-based benchmarks.

Copied to clipboard

Bo Pei, Yingzheng Zhu, Guangjin Wang, Huajuan Duan, Wenya Wu, Fuyong Xu, Yizhao Zhu, Peiyu Liu, Ran Lu

Benchmarking Diverse-Modal Entity Linking with Generative Models (2023.findings-acl)

Challenge:	Existing work on intent-related models fails to capture long-term dependencies in user behavior and fails to effectively utilize item relevance.
Approach:	They propose a sequential recommendation framework that combine temporal variability with position encoding that has extrapolation properties to encode sequences, thereby expanding the model’s view of user behavior.
Outcome:	The proposed model improves on three real datasets by 0.8% to 14.7% compared to baselines.

Copied to clipboard

Sijia Wang, Alexander Hanbo Li, Henghui Zhu, Sheng Zhang, Pramuditha Perera, Chung-Wei Hang, Jie Ma, William Yang Wang, Zhiguo Wang, Vittorio Castelli, Bing Xiang, Patrick Ng

Can Large Language Models Effectively Support Decision-Making in Sudden Emergencies? (2026.findings-acl)

Challenge:	Existing models for diverse-mode entity linking (EL) work well on per modality configurations, but it is more challenging to design a unified model for diverse modality.
Approach:	They propose a generative diverse-modal model that integrates text, image and table . they propose combining a multimodal encoder-decoder paradigm with a fine-tuning GDMM .
Outcome:	The proposed model outperforms state-of-the-art models by 8.51 F1 on average for diverse-modal EL.

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

Towards Transferable Personality Representation Learning based on Triplet Comparisons and Its Applications (2025.emnlp-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

Kai Tang, Rui Wang, Renyu Zhu, Minmin Lin, Xiao Ding, Tangjie Lv, Changjie Fan, Runze Wu, Haobo Wang

Representation Learning

Challenge:	Existing methods for personality analysis treat corpus as a single unit for classification, but this approach presents several challenges.
Approach:	They propose a task paradigm for text-based personality representation learning that uses a triplet personality trend comparison dataset to learn single-sentence personality embeddings with desirable metric properties.
Outcome:	The proposed model significantly boosts performance across various applications, including personality detection, personality retrieval, and emotion translation prediction.

ClinAlign: Scaling Healthcare Alignment from Clinician Preference (2026.findings-acl)

Copied to clipboard

Shiwei Lyu, Xidong Wang, Hao Zhu, Lei Liu, Chaohe Zhang, Jian Wang, Jinjie Gu, Benyou Wang, Yue Shen

Challenge:	Existing methods for aligning open-ended outputs with fine-grained clinician preferences are weakly grounded in professional guidelines.
Approach:	They propose a framework to align large language models' outputs with fine-grained clinician preferences . they propose 119 broadly reusable, clinically grounded principles organized by clinical dimensions .
Outcome:	The proposed framework outperforms existing models on HealthBench-Hard and Deepseek-R1 and o3.

Quite Good, but Not Enough: Nationality Bias in Large Language Models - a Case Study of ChatGPT (2024.lrec-main)

Copied to clipboard

Shucheng Zhu, Weikang Wang, Ying Liu

StratMem-Bench: Evaluating Strategic Memory Use in Virtual Character Conversation Beyond Factual Recall (2026.acl-long)

Challenge:	Nationality is a key demographic element that enhances the performance of large language models, but it has received less scrutiny regarding inherent biases.
Approach:	They investigated nationality bias in ChatGPT, a large language model for text generation.
Outcome:	The proposed model generates 4,680 discourses about nationality in Chinese and English, with 195 countries, 4 temperature settings, and 3 prompt types.

Copied to clipboard

Yerong Wu, Tianxing Wu, Minghao Zhu, Hangyu Sha, Haofen Wang

SLAM: Towards Efficient Multilingual Reasoning via Selective Language Alignment (2025.coling-main)

Challenge:	Current benchmarks for memory utilization ignore this nuance, treating memory as a static repository of facts rather than a dynamic resource to be strategically deployed in character-centric dialogues.
Approach:	They propose a benchmark to evaluate strategic memory use in character-centric dialogues . they use a dataset of 657 instances where virtual characters must navigate heterogeneous memory pools .
Outcome:	The proposed benchmarks show that all models perform well at distinguishing between required and irrelevant memories, but struggle once supportive memories are introduced into the decision process.

Copied to clipboard

Yuchun Fan, Yongyu Mu, YiLin Wang, Lei Huang, Junhao Ruan, Bei Li, Tong Xiao, Shujian Huang, Xiaocheng Feng, Jingbo Zhu

Enhancing Emotion-Cause Pair Extraction in Conversations via Center Event Detection and Reasoning (2024.findings-emnlp)

Challenge:	Large language models (LLMs) have demonstrated significant improvements in reasoning abilities, but these improvements are primarily focused on English, leading to inferior performance in non-English scenarios.
Approach:	They propose a multilingual reasoning alignment approach that fine-tunes the layers responsible for multilingual comprehension in one stage.
Outcome:	The proposed method fine-tunes 6 of the 9 layers responsible for multilingual comprehension, while reducing training time by 4.1-11.9 compared to the two-stage method.

Copied to clipboard

Botao Wang, Keke Tang, Peican Zhu

HIT: Nested Named Entity Recognition via Head-Tail Pair and Token Interaction (2020.emnlp-main)

Challenge:	Emotion-Cause Pair Extraction in Conversations (ECPEC) aims to identify emotion utterances and their corresponding cause utterrances in unannotated conversations.
Approach:	They propose a new method to identify emotion utterances and their corresponding cause utterrances in unannotated conversations by using a center event-aware graph.
Outcome:	The proposed model outperforms existing methods and achieves state-of-the-art performance across three benchmark datasets.

Copied to clipboard

Yu Wang, Yun Li, Hanghang Tong, Ziye Zhu

Aligning Retrieval with Reader Needs: Reader-Centered Passage Selection for Open-Domain Question Answering (2025.coling-main)

Challenge:	Named Entity Recognition (NER) is a fundamental task in natural language processing due to the nature of the named entity.
Approach:	They propose a nested NER model that leverages two key properties pertaining to the named entity, including explicit boundary tokens and tight internal connection between tokens within the boundary.
Outcome:	The proposed model achieves state-of-the-art on three public NER datasets.

Copied to clipboard

Chunlei Xin, Shuheng Zhou, Xuanang Chen, Yaojie Lu, Huijia Zhu, Weiqiang Wang, Zhongyi Liu, Xianpei Han, Le Sun

Cultivating Forensic Reasoning for Generalizable Multimodal Manipulation Detection (2026.acl-long)

Challenge:	Existing retrieval methods aim to gather relevant passages but fail to prioritize consistent and useful information for the reader.
Approach:	They propose a novel method which re-ranks passages based on the reader's prediction probability distribution and clusters passage according to the predicted answers.
Outcome:	The proposed method improves the quality of evidence passages under zero-shot scenarios.

Copied to clipboard

Yuchen Zhang, Yaxiong Wang, Kecheng Han, Yujiao Wu, Lianwei Wu, Li Zhu, Zhedong Zheng

DetectBench: Can Large Language Model Detect and Piece Together Implicit Evidence? (2024.findings-emnlp)

Challenge:	Existing methods for manipulation detection and grounding focus on manipulator type classification under result-oriented supervision.
Approach:	They propose a reasoning-driven framework that shifts learning from outcome fitting to process modeling.
Outcome:	The proposed framework achieves state-of-the-art with superior generalization on large-scale datasets.

Copied to clipboard

Zhouhong Gu, Lin Zhang, Xiaoxuan Zhu, Jiangjie Chen, Wenhao Huang, Yikai Zhang, Shusen Wang, Zheyu Ye, Yan Gao, Hongwei Feng, Yanghua Xiao

Sentiment Forecasting in Dialog (2020.coling-main)

Challenge:	Existing LLMs' abilities to detect evidence in long contexts are far inferior to humans.
Approach:	They propose a benchmark to assess LLMs' abilities in evidence and multi-step commonsense reasoning within a long context.
Outcome:	The proposed method improves the performance of LLMs in evidence detection and commonsense reasoning.

Copied to clipboard

Zhongqing Wang, Xiujun Zhu, Yue Zhang, Shoushan Li, Guodong Zhou

CTC-based Non-autoregressive Speech Translation (2023.acl-long)

Challenge:	Existing studies on sentiment classification focus on determining polarity of existing utterances.
Approach:	They propose a Neural Sentiment Forecasting task which simulates the next utterance based on context and a sequence influence model to learn both pair-wise and seq-wise influence.
Outcome:	The proposed model outperforms existing models over several strong baselines.

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

Phonetic and Lexical Discovery of Canine Vocalization (2024.findings-emnlp)

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

Theron Wang, Xingyuan Li, Chunhao Zhang, Mengyue Wu, Kenny Zhu

CHROMIC: Chronological Reasoning Across Multi-Panel Comics (2026.eacl-long)

Challenge:	Existing methods to study animal language systems rely on human prior knowledge on limited data.
Approach:	They propose a self-supervised approach that enables the accurate classification of phones and an adaptive grammar induction method that identifies phone sequence patterns that suggest a preliminary vocabulary within dog vocalizations.
Outcome:	The proposed approach breaks the barrier existing approaches relying on human prior knowledge on limited data.

Copied to clipboard

Bingxuan Hou, Jiayi Lin, Chenyang Zhang, Dapeng Yin, Shuyue Zhu, Qingqing Hong, Mengna Gao, Junli Wang

iAgent: LLM Agent as a Shield between User and Recommender Systems (2025.findings-acl)

Challenge:	Large-scale vision–language models have achieved remarkable progress on various reasoning tasks, but most studies focus on natural photographic images and pay limited attention to multi-panel visual narratives such as comics.
Approach:	They propose a benchmark dataset for chronological reasoning in multi-panel comics that covers six types of reasoning questions and spans both Western and Japanese comic styles.
Outcome:	The proposed dataset covers six types of reasoning questions and spans both Western and Japanese comic styles.

Copied to clipboard

Wujiang Xu, Yunxiao Shi, Zujie Liang, Xuying Ning, Kai Mei, Kun Wang, Xi Zhu, Min Xu, Yongfeng Zhang

Challenge:	Traditional recommender systems focus on the user-platform paradigm, where users are directly exposed under the control of the platform's recommendation algorithms.
Approach:	They propose a user-agent-platform paradigm where agent serves as the protective shield between user and recommender system that enables indirect exposure.
Outcome:	The proposed model improves 16.6% over baselines on four datasets and mitigates echo chamber effects and reduces model bias in disadvantaged users.

ConvSearch-R1: Enhancing Query Reformulation for Conversational Search with Reasoning via Reinforcement Learning (2025.emnlp-main)

Copied to clipboard

Changtai Zhu, Siyin Wang, Ruijun Feng, Kai Song, Xipeng Qiu

AMA: Adaptive Memory via Multi-Agent Collaboration (2026.findings-acl)

Challenge:	Existing approaches to conversational Query Reformulation (CQR) suffer from high dependency on external supervision from annotations or large language models and insufficient alignment between the rewriter and downstream retrievers.
Approach:	They propose a framework that transforms context-dependent queries into self-contained forms suitable for off-the-shelf retrievers.
Outcome:	The proposed framework outperforms existing methods on topiOCQA and QReCC datasets while using smaller 3B parameter models without external supervision.

Copied to clipboard

Weiquan Huang, Zixuan Wang, Hehai Lin, Sudong Wang, Bo Xu, Qian Li, Beier Zhu, Linyi Yang, Chengwei Qin

CuMA: Aligning LLMs with Sparse Cultural Values via Demographic-Aware Mixture of Adapters (2026.acl-long)

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

Ao Sun, Xiaoyu Wang, Zhe Tan, Yu Li, Zhu Jiachen, Yuheng Jia, Shu Su

On the data requirements of probing (2022.findings-acl)

Challenge:	Large Language Models (LLMs) have a global audience, so alignment must extend to cultural resonance.
Approach:	They propose a framework that frames alignment as a conditional capacity separation problem.
Outcome:	The proposed framework outperforms both dense baselines and semantic-only MoEs on three large language models.

Copied to clipboard

Zining Zhu, Jixuan Wang, Bai Li, Frank Rudzicz

Challenge:	Existing methods to probe neural networks are expensive and require large datasets.
Approach:	They propose a method to estimate the required number of data samples in probing datasets . they use a classification task to encode a text with a deep neural network .
Outcome:	The proposed method estimates the required number of data samples in two probing configurations and proves it is statistically powerful.

BADGE: Speeding Up BERT Inference after Deployment via Block-wise Bypasses and Divergence-based Early Exiting (2023.acl-industry)

Copied to clipboard

Wei Zhu, Peng Wang, Yuan Ni, Guotong Xie, Xiaoling Wang

KG-FPQ: Evaluating Factuality Hallucination in LLMs with Knowledge Graph-based False Premise Questions (2025.coling-main)

Challenge:	Recent years have witnessed the rise of many pre-trained language models (PLMs) such as GPT (Radford et al., 2019) and XLNet (Yang e.t al, 2019).
Approach:	They propose a framework which consists of two off-the-shelf methods for improving PLMs’ early exiting.
Outcome:	The proposed method can reduce the average latency of pre-trained language models and work with other inference speed-up methods like model pruning.

Copied to clipboard

Yanxu Zhu, Jinlin Xiao, Yuhang Wang, Jitao Sang

FGraDA: A Dataset and Benchmark for Fine-Grained Domain Adaptation in Machine Translation (2022.lrec-1)

Challenge:	Existing benchmarks that assess this vulnerability rely on manual construction, resulting in limited size and lack of expandability.
Approach:	They propose a method to generate false premise questions based on knowledge graphs . they modify true triplets extracted from KGs to create false premises .
Outcome:	The proposed method generates semantically rich FPQs using state-of-the-art GPTs.

Copied to clipboard

Wenhao Zhu, Shujian Huang, Tong Pu, Pingxuan Huang, Xu Zhang, Jian Yu, Wei Chen, Yanfeng Wang, Jiajun Chen

Comprehensive Benchmarking of Long-Form Speech Generation in Diverse Scenarios (2026.findings-acl)

Challenge:	Recent research on domain adaptation neglects diversity in translation within a domain . current research on NMT models considers very broad target domains .
Approach:	They propose a fine-grained domain adaptation task for autonomous vehicles, AI education, real-time networks, and smart phone.
Outcome:	The proposed task is compared with a dataset of Chinese-English translation tasks for four sub-domains of information technology: autonomous vehicles, AI education, real-time networks, and smart phone.

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

Composition-based Heterogeneous Graph Multi-channel Attention Network for Multi-aspect Multi-sentiment Classification (2022.coling-1)

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

Hao Niu, Yun Xiong, Jian Gao, Zhongchen Miao, Xiaosu Wang, Hongrun Ren, Yao Zhang, Yangyong Zhu

Toward Automatic Discovery of a Canine Phonetic Alphabet (2025.acl-long)

Challenge:	Existing methods for Aspect-based sentiment analysis (ABSA) focus on aspect terms with the same sentiment polarity . current methods focus on sentences with only one aspect term or multiple aspect terms .
Approach:	They propose a novel method to model inter-aspect relationships and aspect-context relationships simultaneously using a heterogeneous graph.
Outcome:	The proposed method can predict sentiments towards the given aspect term in a sentence . it can provide more detailed predictions compared with sentence-level sentiment analysis.

Copied to clipboard

Theron S. Wang, Xingyuan Li, Hridayesh Lekhak, Tuan Minh Dang, Mengyue Wu, Kenny Q. Zhu

Adaptive Graph Convolutional Network for Knowledge Graph Entity Alignment (2022.findings-emnlp)

Challenge:	a new algorithm for vocalization communication between dogs is being developed . phonetic units alone are not sufficient to constitute a "language"
Approach:	They propose an algorithm that produces a complete alphabet of distinct canine phonemes . the algorithm is expected to function on canines and other animal species .
Outcome:	The proposed algorithm produces a complete alphabet of distinct canine phoneme-like units . it is expected to work on canines and other animal species .

Copied to clipboard

Renbo Zhu, Xukun Luo, Meng Ma, Ping Wang

T2A-Feedback: Improving Basic Capabilities of Text-to-Audio Generation via Fine-grained AI Feedback (2025.acl-long)

Challenge:	Entity alignment (EA) aims to identify equivalent entities from different Knowledge Graphs (KGs) noisy neighbors of entities transfer invalid information, drown out equivalent information, and ultimately reduce the performance of EA.
Approach:	They propose a method to deal with neighbor noises to reduce the performance of EA by capturing the differences and complementarities of multiple KGs.
Outcome:	The proposed framework outperforms the state-of-the-art methods in supervised and unsupervised settings.

Copied to clipboard

Zehan Wang, Ke Lei, Chen Zhu, Jiawei Huang, Sashuai Zhou, Luping Liu, Xize Cheng, Shengpeng Ji, Zhenhui Ye, Tao Jin, Zhou Zhao

Zoom Out and Observe: News Environment Perception for Fake News Detection (2022.acl-long)

Challenge:	Text-to-audio (T2A) models still struggle to satisfy human preferences for prompt-following and acoustic quality when generating complex multi-event audio.
Approach:	They propose to use AI feedback learning to enhance basic capabilities of text-to-audio models . they use a large audio preference dataset to evaluate the model's capabilities .
Outcome:	The proposed model improves in simple and complex scenarios with AI feedback learning.

Copied to clipboard

Qiang Sheng, Juan Cao, Xueyao Zhang, Rundong Li, Danding Wang, Yongchun Zhu

HEAL: A Hypothesis-Based Preference-Aware Analysis Framework (2025.findings-emnlp)

Challenge:	Existing methods for fake news detection "zoom in" to verify content with knowledge sources or check readers’ replies to posts but neglect information in the external news environment where a fake news post is created and disseminated.
Approach:	They propose a framework to capture news environment signals and a module to perceive useful signals and assist final prediction.
Outcome:	The proposed framework can improve the performance of basic fake news detectors by capturing the environmental signals of news posts and analyzing the results.

Copied to clipboard

Yifu Huo, Chenglong Wang, Qiren Zhu, Shunjie Xing, Tong Xiao, Chunliang Zhang, Tongran Liu, JingBo Zhu

Challenge:	Preference optimization methods like DPO are often evaluated on a single response, overlooking other outputs.
Approach:	They propose a Hypothesis-based PrEference-aware AnaLysis Framework that formulates preference alignment as a re-ranking process within hypothesis spaces.
Outcome:	The proposed evaluation paradigm re-ranks preference alignment as a reranking process within hypothesis spaces.

StruNRAG: Evaluation of OCR-Induced Structural Noise on RAG Robustness (2026.findings-acl)

Copied to clipboard

Mengna Gao, Dapeng Yin, Shuyue Zhu, Bingxuan Hou, Zhanpeng Ni, Junli Wang

Dynamic Model-Bank Test-Time Adaptation for Automatic Speech Recognition (2025.emnlp-main)

Challenge:	Existing evaluations of RAG systems ignore structural noise, authors say . complex layouts can cause OCR failures and disrupt semantic flow of text . advanced LLMs demonstrate robustness against local noise, but struggle to maintain reasoning capabilities under severe structural disruption that fragments global context.
Approach:	They propose a benchmark to evaluate RAG robustness against OCR-induced structural perturbations.
Outcome:	The proposed benchmark systematically injects three categories of real-world structural noise into a bilingual dataset of 2,132 question-answer pairs . results show that advanced LLMs demonstrate robustness against local noise, but struggle to maintain reasoning capabilities under severe structural disruption .

Copied to clipboard

Yanshuo Wang, Yanghao Zhou, Yukang Lin, Haoxing Chen, Jin Zhang, Wentao Zhu, Jie Hong, Xuesong Li

MMErroR: A Benchmark for Erroneous Reasoning in Vision-Language Models (2026.acl-long)

Challenge:	Existing ASR TTA methods struggle with instability under continual and long-term distribution shifts.
Approach:	They propose a continuous adaptive model-bank framework that adapts to domain shifts in ASR test-time scenarios.
Outcome:	Experiments on diverse, continuously shifting ASR benchmarks show that DMSUTA outperforms existing continual TTA baselines.

Copied to clipboard

Yang Shi, Yifeng Xie, Minzhe Guo, Liangsi Lu, Mingxuan Huang, Jingchao Wang, Zhihong Zhu, Boyan Xu, Zhiqi Huang

Learn over Past, Evolve for Future: Forecasting Temporal Trends for Fake News Detection (2023.acl-industry)

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

Beizhe Hu, Qiang Sheng, Juan Cao, Yongchun Zhu, Danding Wang, Zhengjia Wang, Zhiwei Jin

R3Mem: Bridging Memory Retention and Retrieval via Reversible Compression (2025.findings-acl)

Challenge:	Existing work on fake news detection does not consider the temporal shift issue caused by the rapidly-evolving nature of news data.
Approach:	They propose a framework to forecast temporal patterns of news data and guide detector to fast adapt to future distributions.
Outcome:	The proposed framework forecasts temporal distribution patterns and guides detector to fast adapt to future distribution.

Copied to clipboard

Xiaoqiang Wang, Suyuchen Wang, Yun Zhu, Bang Liu

MdEval: Massively Multilingual Code Debugging (2026.findings-acl)

Challenge:	Existing memory solutions that store information via parameters struggle with reliable retrieval.
Approach:	They propose a memory network that optimizes both information Retention and Retrieval through Reversible context compression.
Outcome:	The proposed memory network outperforms conventional memory modules in long-horizon interaction tasks like conversational agents and achieves state-of-the-art performance in language modeling and retrieval-augmented generation tasks.

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

Learning from Diverse Reasoning Paths with Routing and Collaboration (2025.emnlp-main)

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

Zhenyu Lei, Zhen Tan, Song Wang, Yaochen Zhu, Zihan Chen, Yushun Dong, Jundong Li

Concise and Precise Context Compression for Tool-Using Language Models (2024.findings-acl)

Challenge:	Recent studies suggest that the reasoning abilities of large language models (LLMs) grows with model size and pre-training data.
Approach:	They propose to combine quality filtering, conditional routing, and cooperative peer teaching to transfer knowledge from powerful teacher models to compact and transparent students.
Outcome:	Experiments show that QR-Distill is superior to traditional methods.

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

A Versatile Adaptive Curriculum Learning Framework for Task-oriented Dialogue Policy Learning (2022.findings-naacl)

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

Yang Zhao, Hua Qin, Wang Zhenyu, Changxi Zhu, Shihan Wang

ARTIST: A Transformer-based Chinese Text-to-Image Synthesizer Digesting Linguistic and World Knowledge (2022.findings-emnlp)

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

Tingting Liu, Chengyu Wang, Xiangru Zhu, Lei Li, Minghui Qiu, Jun Huang, Ming Gao, Yanghua Xiao

Simulating Dual-Process Thinking in Dialogue Topic Shift Detection (2025.coling-main)

Challenge:	Text-to-Image Synthesis (TIS) is a popular task to convert natural language texts into realistic images.
Approach:	They propose a transformer-based Chinese text-to-image synthesizer for high-resolution image generation that incorporates linguistic and relational knowledge facts into the model to ensure better performance without the usage of ultra-large models.
Outcome:	The proposed model outperforms existing models in Chinese with linguistic and relational knowledge facts.

Copied to clipboard

Huiyao Wang, Peifeng Li, Yaxin Fan, Qiaoming Zhu

CityCube: Benchmarking Cross-view Spatial Reasoning on Vision-Language Models in Urban Environments (2026.acl-long)

Challenge:	Existing methods for topic shift detection focus on shallow local reasoning, overlooking the importance of considering the global historical structure and local details to elucidate the underlying causes of topic shift.
Approach:	They propose a dual-process theory for dialogue topic shift detection that employs Large Language Models to extract and store the global topic structure of historical dialogue, while a reasoning module introduces a LLM to generate reasoning samples between the response and the most recent topic of historical dialog.
Outcome:	The proposed framework outperforms the state-of-the-art on three public datasets and is based on a dual-process theory.

Copied to clipboard

Haotian Xu, Yue Hu, Zhengqiu Zhu, Chen Gao, Ziyou Wang, Junreng Rao, Wenhao Lu, Weishi Li, Quanjun Yin, Yong Li

SWE-QA-Pro: A Representative Benchmark and Scalable Training Recipe for Repository-Level Code Understanding (2026.findings-acl)

Challenge:	Existing benchmarks focus on indoor or street settings, overlooking challenges of open-ended urban spaces.
Approach:	They propose a benchmark to probe cross-view spatial reasoning capabilities of current VLMs in urban settings.
Outcome:	The citycube benchmark examines the performance of current vision-language models in urban environments.

Copied to clipboard

Songcheng Cai, Zhiheng Lyu, Yuansheng Ni, Xiangchao Chen, Baichuan Zhou, Shenzhe Zhu, Yi Lu, Haozhe Wang, Chi Ruan, Benjamin Schneider, Weixu Zhang, Xiang Li, Andy Zheng, Yuyu Zhang, Ping Nie, Wenhu Chen

Penalty Decoding: Well Suppress the Self-Reinforcement Effect in Open-Ended Text Generation (2023.emnlp-main)

Challenge:	Existing benchmarks for agentic repository-level code understanding overlook long tail topics and rely on memorized knowledge.
Approach:	They propose a repository-level agentic code understanding benchmark that uses long-tail repositories with executable environments to enforce topical balance.
Outcome:	Empirically, a Qwen3-8B model trained with the proposed benchmark outperforms GPT-4o by 2.3 points.

Copied to clipboard

Wenhong Zhu, Hongkun Hao, Rui Wang

Multimodal Procedural Planning via Dual Text-Image Prompting (2024.findings-emnlp)

Challenge:	Experimental results demonstrate the efficacy of our approach in generating high-quality sentences resembling human output.
Approach:	They propose a forgetting mechanism that disregards distant tokens, reducing the burden of penalty selection.
Outcome:	The proposed approach generates high-quality sentences resembling human output.

Copied to clipboard

Yujie Lu, Pan Lu, Zhiyu Chen, Wanrong Zhu, Xin Wang, William Yang Wang

CNNSum: Exploring Long-Context Summarization with Large Language Models in Chinese Novels (2025.findings-acl)

Challenge:	Embodied agents have demonstrated performance in following instructions informed by texts and images . however, the potential of models providing useful guidelines for humans to complete tasks remains underexplored .
Approach:	They propose a multimodal procedural planning task that generates paired text-image plans . this task provides more complementary and informative guidance than unimodal plans a . authors propose modality prompting methods that leverage zero-shot reasoning ability .
Outcome:	The proposed method improves the interaction in dual modalities and provides more information than unimodal plans.

Copied to clipboard

Lingxiao Wei, He Yan, Lu Xiangju, Junmin Zhu, Jun Wang, Wei Zhang

WikiSeeker: Rethinking the Role of Vision-Language Models in Knowledge-Based Visual Question Answering (2026.findings-acl)

Challenge:	Currently, long-context summarization mainly relies on memory ability.
Approach:	They propose a multi-scale long-context summarization benchmark based on Chinese novels . they use human-driven annotations to analyze long-constituency models .
Outcome:	The proposed benchmark features human-driven annotations across four subsets with lengths ranging from 16k to 128k.

Copied to clipboard

Yingjian Zhu, Xinming Wang, Kun Ding, Ying Wang, Bin Fan, Shiming Xiang

YuLan-Mini: Pushing the Limits of Open Data-efficient Language Model (2025.acl-long)

Challenge:	Existing methods for Knowledge-Based Visual Question Answering rely on images as the retrieval key, and often overlook or misplace the role of Vision-Language Models (VLMs)
Approach:	They propose a multi-modal RAG framework that assigns VLMs two specialized agents: a Refiner and an Inspector.
Outcome:	Experiments on EVQA, InfoSeek, and M2KR show that the proposed framework achieves state-of-the-art performance with significant improvements in both retrieval accuracy and answer quality.

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

InspireDebate: Multi-Dimensional Subjective-Objective Evaluation-Guided Reasoning and Optimization for Debating (2025.acl-long)

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

Fuyu Wang, Jiangtong Li, Kun Zhu, Changjun Jiang

Can Large Language Models Understand You Better? An MBTI Personality Detection Dataset Aligned with Population Traits (2025.coling-main)

Challenge:	Existing LLMs focus on responding to specific arguments while neglecting objective assessments such as authenticity and logical validity.
Approach:	They propose a multi-dimensional evaluation system and an optimized debating framework . they propose to use coT reasoning enhancement, web-based Retrieval Augmented Generation to optimize across various dimensions.
Outcome:	The proposed framework outperforms baseline models in argument quality assessment and debate process simulation by 57%.

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

AdaReTaKe: Adaptive Redundancy Reduction to Perceive Longer for Video-language Understanding (2025.findings-acl)

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

Xiao Wang, Qingyi Si, Shiyu Zhu, Jianlong Wu, Li Cao, Liqiang Nie

Confidence-Calibrated Small-Large Language Model Collaboration for Cost-Efficient Reasoning (2026.eacl-long)

Challenge:	Multimodal Large Language Models (MLLMs) are limited by context length when processing long videos.
Approach:	They propose a training-free method that flexibly reduces redundancy by allocating compression ratios among time and model layers with theoretical guarantees.
Outcome:	Experiments on videoMME, MLVU, LongVideoBench, and LVBench show that AdaRETAKE outperforms existing methods by 2.3% and 2.8% for 7B and 72B models.

Copied to clipboard

Chuang Zhang, Zizhen Zhu, Yihao Wei, Bing Tian, Junyi Liu, Henan Wang, Wang Xavier, Yaxiao Liu

Improving Grammatical Error Correction via Contextual Data Augmentation (2024.findings-acl)

Challenge:	Large language models (LLMs) have superior reasoning capabilities compared to small language models, but incur substantially higher inference costs.
Approach:	They propose a system that cascades an LLM with an SLM to achieve a balance between accuracy and cost in complex reasoning tasks.
Outcome:	The proposed system improves the SLM’s reasoning ability and confidence calibration across diverse datasets and model backbones.

Copied to clipboard

Yixuan Wang, Baoxin Wang, Yijun Liu, Qingfu Zhu, Dayong Wu, Wanxiang Che

R3 Prompting: Review, Rephrase and Resolve for Chain-of-Thought Reasoning in Large Language Models under Noisy Context (2023.findings-emnlp)

Challenge:	Increasing use of synthetic data due to inconsistent error distribution and noisy labels is limiting the use of these data.
Approach:	They propose a method for augmentation of synthetic data with a more consistent error distribution.
Outcome:	The proposed method outperforms strong baselines and achieves state-of-the-art with only a few synthetic data.

Copied to clipboard

Qingyuan Tian, Hanlun Zhu, Lei Wang, Yang Li, Yunshi Lan

Empirical Studies of Institutional Federated Learning For Natural Language Processing (2020.findings-emnlp)

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

Xinghua Zhu, Jianzong Wang, Zhenhou Hong, Jing Xiao

MTR-Suite: A Framework for Evaluating and Synthesizing Conversational Retrieval Benchmarks (2026.acl-long)

Challenge:	federated learning is a promising ideology to unite isolated datasets for machine learning problems.
Approach:	They propose to use federated natural language processing networks to train a popular NLP model with applications in sentence intent classification.
Outcome:	The proposed model is sensitive to imbalanced data load and tested against a federated model under imbalanced datasets.

Copied to clipboard

Junhao Ruan, Abudukeyumu Abudula, Bei Li, Yongjing Yin, Xinyu Liu, Kechen Jiao, Xin Chen, Jingang Wang, Xunliang Cai, Tong Xiao, JingBo Zhu

IIET: Efficient Numerical Transformer via Implicit Iterative Euler Method (2025.emnlp-main)

Challenge:	Existing conversational retrieval benchmarks suffer from costly, sparse human annotation or rigid, unnatural automated heuristics.
Approach:	They propose a framework for auditing, synthesizing, and benchmarking conversational retrieval.
Outcome:	The proposed framework is based on three LLM-based auditors and a multi-agent system . it mimics production-style challenges (hard topic switching, verbosity) and offers superior discriminative power.

Copied to clipboard

Xinyu Liu, Bei Li, Jiahao Liu, Junhao Ruan, Kechen Jiao, Hongyin Tang, Jingang Wang, Tong Xiao, JingBo Zhu

FACT: Examining the Effectiveness of Iterative Context Rewriting for Multi-fact Retrieval (2025.findings-naacl)

Challenge:	High-order numerical methods enhance performance in tasks like NLP but introduce a performance-efficiency trade-off due to increased computational overhead.
Approach:	They propose an iterative implicit Euler Transformer which simplifies high-order numerical methods by iterating implicit Eule.
Outcome:	The proposed method improves accuracy and reduces inference overhead by 55% while retaining 99.4% of the original task accuracy.

Copied to clipboard

Jinlin Wang, Suyuchen Wang, Ziwen Xia, Sirui Hong, Yun Zhu, Bang Liu, Chenglin Wu

Parenting: Optimizing Knowledge Selection of Retrieval-Augmented Language Models with Parameter Decoupling and Tailored Tuning (2025.acl-long)

Challenge:	Large Language Models (LLMs) are proficient at retrieving single facts from extended contexts, but struggle with tasks requiring simultaneous retrieval of multiple facts.
Approach:	They propose a method that refines context through successive rounds of rewriting to address this problem by finding all Crucial Texts (FACT)
Outcome:	The proposed method improves multi-fact retrieval performance across tasks, though improvements are less notable in general-purpose QA scenarios.

Copied to clipboard

Yongxin Xu, Ruizhe Zhang, Xinke Jiang, Yujie Feng, Yuzhen Xiao, Xinyu Ma, Runchuan Zhu, Xu Chu, Junfeng Zhao, Yasha Wang

Huatuo-26M, a Large-scale Chinese Medical QA Dataset (2025.findings-naacl)

Challenge:	Existing methods for integrating internal and external knowledge lack effective control mechanisms for generating hallucinations and dealing with outdated knowledge.
Approach:	They propose a framework that decouples, identifies, and purposefully optimizes parameter subspaces related to adherence and robustness.
Outcome:	The proposed framework decouples, identifies, and purposefully optimizes parameter subspaces related to adherence and robustness.

Copied to clipboard

Xidong Wang, Jianquan Li, Shunian Chen, Yuxuan Zhu, Xiangbo Wu, Zhiyi Zhang, Xiaolong Xu, Junying Chen, Jie Fu, Xiang Wan, Anningzhe Gao, Benyou Wang

Question Answering

Challenge:	Large Language Models are a powerful tool for medical research, but the data is a bottleneck.
Approach:	They propose to use the largest ever medical Question Answering dataset with 26 Million QA pairs as a fine-tuning data for training large language models.
Outcome:	The proposed dataset demonstrates that it can be used to train large language models and improves zero-shot performance on other datasets.

Imagination-Augmented Natural Language Understanding (2022.naacl-main)

Copied to clipboard

Yujie Lu, Wanrong Zhu, Xin Wang, Miguel Eckstein, William Yang Wang

MedDialog: Large-scale Medical Dialogue Datasets (2020.emnlp-main)

Challenge:	Existing methods for Natural Language Understanding focus on textual signals, which hinders models from learning efficiently from limited data samples.
Approach:	They propose an Imagination-Augmented Cross-modal Encoder to solve natural language understanding tasks from a novel learning perspective.
Outcome:	The proposed learning paradigm bridges the gap between human and agent language understanding in both linguistic and perceptual procedures.

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

Question Tells You Where the Answer Is: Intention-aware Long-Context KV Cache Compression (2026.acl-long)

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

Liang Zhao, Xiaocheng Feng, Weihong Zhong, Lei Huang, Kun Zhu, Baoxin Wang, Dayong Wu, Guoping Hu, Ting Liu, Bing Qin

Challenge:	Recent methods to reduce the KV cache size fail to identify crucial KVs for generation while excluding others accurately, resulting in severe information loss.
Approach:	They propose an intention-aware KV cache eviction method that identifies and retains crucial KVs according to the attention distribution of intention, which semantically reflects the user’s goal and determines which part of the context is relevant.
Outcome:	The proposed method can maintain the model performance while reducing the KV cache size from 128K to 2K, leading to a 6.3x increase in decoding speed and 7.8x enhancement in memory efficiency compared to the default setting.

Sliding Windows Are Not the End: Exploring Full Ranking with Long-Context Large Language Models (2025.acl-long)

Copied to clipboard

Wenhan Liu, Xinyu Ma, Yutao Zhu, Ziliang Zhao, Shuaiqiang Wang, Dawei Yin, Zhicheng Dou

RQT: Hierarchical Residual Quantization for Multi-Model Compression (2025.findings-acl)

Challenge:	Existing methods for listwise passage ranking use sliding window approach, which is inefficient as it requires repetitive and serialized processing.
Approach:	They propose a listwise label construction approach and importance-aware learning objective for full ranking.
Outcome:	The proposed method outperforms existing methods in listwise ranking tasks.

Copied to clipboard

Chen Tianqi, Peisong Wang, Weixiang Xu, Zeyu Zhu, Jian Cheng

Hey, That’s My Data! Token-Only Dataset Inference in Large Language Models (2026.findings-acl)

Challenge:	Existing methods for decomposing fine-tuned LLMs are sensitive to the magnitude of delta values.
Approach:	They propose a hierarchical quantization framework that shares low-bit integer weights across similar models.
Outcome:	The proposed framework achieves an average accuracy degradation of approximately 3% on fine-tuned models across mathematics, coding, chatbot, and Chinese LLMs.

Copied to clipboard

Chen Xiong, Zihao Wang, Rui Zhu, Tsung-Yi Ho, Pin-Yu Chen, Jingwei Xiong, Haixu Tang

GLTW: Joint Improved Graph Transformer and LLM via Three-Word Language for Knowledge Graph Completion (2025.findings-acl)

Challenge:	Existing dataset inference methods require logit access, but many modern LLMs restrict such access.
Approach:	They propose a token-only dataset inference framework that allows models to overwrite prior knowledge when trained on new data.
Outcome:	The proposed framework overwrites prior knowledge when trained on new data.

Copied to clipboard

Kangyang Luo, Yuzhuo Bai, Cheng Gao, Shuzheng Si, Zhu Liu, Yingli Shen, Zhitong Wang, Cunliang Kong, Wenhao Li, Yufei Huang, Ye Tian, Xuantang Xiong, Lei Han, Maosong Sun

Better Literary Translation: A Multi-Aspect Data Generation and LLM Training Approach (2026.acl-industry)

Challenge:	Existing knowledge graphs lack the ability to integrate structural information into LLMs and output predictions deterministically.
Approach:	They propose a method which encodes structural information of KGs and merges it with LLMs to enhance KGC performance.
Outcome:	The proposed method improves the performance of KG Completion datasets on KGs by integrating structural information with LLMs.

Copied to clipboard

Zhihao Lin, Ziqi Zhu, Hao Huang, Guanghui Wang, Peiyang He

WildGraphBench: Benchmarking GraphRAG with Wild-Source Corpora (2026.findings-acl)

Challenge:	Literary translation requires balancing expression fluency with literary effect due to the scarcity of high-quality training data and the difficulty of capturing nuanced quality trade-offs.
Approach:	They propose a multi-aspect iterative refinement framework that generates high-quality translation references and preference data through specialized LLM translators.
Outcome:	The proposed models outperform the ground truth for SFT by 8.65 CEA100 points while leveraging an explicit reward model for GRPO yields an additional 1.51 point improvement.

Copied to clipboard

Pengyu Wang, Benfeng Xu, Licheng Zhang, Shaohan Wang, Mingxuan Du, Chiwei Zhu, Zhendong Mao

HMoE: Heterogeneous Mixture of Experts for Language Modeling (2025.emnlp-main)

Challenge:	Existing benchmarks for Graph-based Retrieval-Augmented Generation (GraphRAG) rely on short, curated passages as external knowledge, failing to adequately evaluate systems in realistic settings involving long contexts and large-scale heterogeneous documents.
Approach:	They propose a benchmark to assess GraphRAG performance in the wild using Wikipedia's unique structure where cohesive narratives are grounded in long and heterogeneous external reference documents.
Outcome:	Experiments with articles across 12 top-level topics show that GraphRAG performs better in the wild than existing methods.

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

A Survey on Patent Analysis: From NLP to Multimodal AI (2025.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

Homaira Huda Shomee, Zhu Wang, Sathya N. Ravi, Sourav Medya

What Breaks Knowledge Graph based RAG? Benchmarking and Empirical Insights into Reasoning under Incomplete Knowledge (2026.eacl-long)

Challenge:	Recent advances in pretrained language models and large language models have demonstrated transformative capabilities across diverse domains.
Approach:	They propose a taxonomy for categorization based on tasks in the patent life cycle . they introduce a novel taxonomies for categorizing based upon tasks in patent life cycles .
Outcome:	The proposed method is based on tasks in the patent life cycle and provides a taxonomy for categorization based upon tasks in patent life cycles.

Copied to clipboard

Dongzhuoran Zhou, Yuqicheng Zhu, Xiaxia Wang, Hongkuan Zhou, Yuan He, Jiaoyan Chen, Steffen Staab, Evgeny Kharlamov

Multi-Party Empathetic Dialogue Generation: A New Task for Dialog Systems (2022.acl-long)

Challenge:	Existing evaluation metrics and lenient answer matching criteria obscure meaningful comparisons.
Approach:	They propose a general method for constructing benchmarks and a method to assess KG-RAG methods under incomplete knowledge.
Outcome:	The proposed method systematically assesses KG-RAG methods under incomplete knowledge.

Copied to clipboard

Ling.Yu Zhu, Zhengkun Zhang, Jun Wang, Hongbin Wang, Haiying Wu, Zhenglu Yang

From Real to Synthetic: Synthesizing Millions of Diversified and Complicated User Instructions with Attributed Grounding (2025.acl-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

Chiwei Zhu, Benfeng Xu, Xiaorui Wang, Zhendong Mao

Challenge:	a pursuit of diverse, complex, and large-scale instruction data is crucial for automatically aligning large language models . authors: methods that generate synthetic instructions at scale suffer from limited grounding sources . attributed grounding is a technique that can be used to align language models with human .
Approach:	They synthesize 1 million instructions using attributed grounding and a bottom-up synthesis process that leverages web documents to generate a situation, then a meaningful instruction.
Outcome:	The proposed framework achieves leading performance on benchmarks and scales with more web corpora.

Unsupervised Candidate Answer Extraction through Differentiable Masker-Reconstructor Model (2023.findings-emnlp)

Copied to clipboard

Zhuoer Wang, Yicheng Wang, Ziwei Zhu, James Caverlee

Scaling Down, Serving Fast: Compressing and Deploying Efficient LLMs for Recommendation Systems (2025.emnlp-industry)

Challenge:	Existing methods for candidate answer extraction are reliant on linguistic rules or annotated data and face partial annotation issue and challenges in generalization.
Approach:	They propose an unsupervised approach that leverages the inherent structure of context passages through a Differentiable Masker-Reconstructor (DMR) Model with the enforcement of self-consistency for picking up salient information tokens.
Outcome:	The proposed model outperforms supervised and unsupervised methods in two datasets with exhaustively-annotated answers and shows that it is comparable to supervised methods.

Copied to clipboard

Kayhan Behdin, Ata Fatahibaarzi, Qingquan Song, Yun Dai, Aman Gupta, Zhipeng Wang, Hejian Sang, Shao Tang, Gregory Dexter, Sirou Zhu, Siyu Zhu, Tejas Dharamsi, Vignesh Kothapalli, Zhoutong Fu, Yihan Cao, Pin-Lun Hsu, Fedor Borisyuk, Natesh S. Pillai, Luke Simon, Rahul Mazumder

XMC-Agent : Dynamic Navigation over Scalable Hierarchical Index for Incremental Extreme Multi-label Classification (2024.findings-acl)

Challenge:	Large language models (LLMs) have demonstrated remarkable performance across a wide range of industrial applications.
Approach:	They propose two techniques for training and deploying small language models that deliver high performance for a variety of industry use cases.
Outcome:	The proposed techniques retain much of the quality of larger models while reducing training/serving costs and latency.

Copied to clipboard

Yanjiang Liu, Tianyun Zhong, Yaojie Lu, Hongyu Lin, Ben He, Shuheng Zhou, Huijia Zhu, Weiqiang Wang, Zhongyi Liu, Xianpei Han, Le Sun

Astra: Activation-Space Tail-Eigenvector Low-Rank Adaptation of Large Language Models (2026.findings-acl)

Challenge:	Existing methods for XMC struggle with the growing set of labels due to their static label assumptions, and embedding-based methods struggle with complex mapping relationships due to late interaction paradigm.
Approach:	They propose a large language model (LLM) powered agent framework for extreme multi-label classification, XMC-Agent, which can effectively learn, manage and predict the extremely large and dynamically increasing set of labels.
Outcome:	The proposed framework can learn, manage and predict the extremely large and dynamically growing set of labels and achieves state-of-the-art performance on three standard datasets.

Copied to clipboard

Kainan Liu, Yong Zhang, Ning Cheng, Yun Zhu, Yanmeng Wang, Shaojun Wang, Jing Xiao

Cross-Modal Coreference Alignment: Enabling Reliable Information Transfer in Omni-LLMs (2026.acl-long)

Challenge:	Existing methods for fine-tuning pre-trained models are limited due to suboptimal activation subspaces.
Approach:	They propose a method that leverages tail eigenvectors of model output activations to construct low-rank adapters.
Outcome:	The proposed method outperforms existing methods across 16 benchmarks and surpasses full fine-tuning in certain scenarios.

Copied to clipboard

Hongcheng Liu, Yuhao Wang, Zhe Chen, Pingjie Wang, Zhiyuan Zhu, Yixuan Hou, Yanfeng Wang, Yu Wang

A Contrastive Framework for Learning Sentence Representations from Pairwise and Triple-wise Perspective in Angular Space (2022.acl-long)

Challenge:	Experiments on 13 Omni-LLMs reveal systematic weaknesses in cross-modal coreference . cross-module coreference is a crucial missing piece for advancing robust omni-modal reasoning.
Approach:	They propose a cross-modal coreference problem to evaluate and enhance Omni-LLMs' reasoning capabilities.
Outcome:	Experiments on 13 Omni-LLMs show they lack coreference-aware thinking patterns . the CROSSOMNI dataset yields significant performance gains and generalizes well to collaborative reasoning tasks.

Copied to clipboard

Yuhao Zhang, Hongji Zhu, Yongliang Wang, Nan Xu, Xiaobo Li, Binqiang Zhao

RAG-HAT: A Hallucination-Aware Tuning Pipeline for LLM in Retrieval-Augmented Generation (2024.emnlp-industry)

Challenge:	Existing methods for learning sentence representations focus on constitution of positive and negative representation pairs and do not focus on training objective.
Approach:	They propose a new method to learn sentence representations using BERT-like pre-trained models . they use a pairwise discriminating power and a model to model the entailment relation of triplet sentences .
Outcome:	The proposed method outperforms the previous state-of-the-art on diverse sentence related tasks.

Copied to clipboard

Juntong Song, Xingguang Wang, Juno Zhu, Yuanhao Wu, Xuxin Cheng, Randy Zhong, Cheng Niu

Context-Sensitive Generation of Open-Domain Conversational Responses (C18-1)

Challenge:	Retrieval-augmented generation (RAG) has emerged as a significant advancement in the field of large language models (LLMs).
Approach:	They propose a method that uses hallucination detection labels to correct hallucines by integrating up-to-date information into their initial training.
Outcome:	The proposed method is based on the Retrieval Augmented Generation (RAG) method, which has shown to be effective in mitigating hallucinations and improving answer quality.

Copied to clipboard

Weinan Zhang, Yiming Cui, Yifa Wang, Qingfu Zhu, Lingzhi Li, Lianqiang Zhou, Ting Liu

FS-Researcher: Test-Time Scaling for Long-Horizon Research Tasks with File-System-Based Agents (2026.acl-long)

Challenge:	Existing studies on single-turn conversation generation focus on coherence and context-sensitive generation of open-domain conversational responses.
Approach:	They propose static and dynamic attention based approaches for context-sensitive generation of open-domain conversational responses.
Outcome:	The proposed model outperforms all baselines on automatic and human evaluation on two public datasets.

Copied to clipboard

Chiwei Zhu, Benfeng Xu, Mingxuan Du, Shaohan Wang, Xiaorui Wang, Zhendong Mao, Yongdong Zhang

Global Attention Decoder for Chinese Spelling Error Correction (2021.findings-acl)

Challenge:	Long trajectories in deep research often exceed model context limits, compressing token budgets for both evidence collection and report writing.
Approach:	They propose a file-system-based framework that scales deep research beyond context window . a Context Builder agent acts as a librarian and a Report Writer agent composes the final report .
Outcome:	Experiments on two open-ended benchmarks show that FS-Researcher achieves state-of-the-art report quality across different backbone models.

Copied to clipboard

Zhao Guo, Yuan Ni, Keqiang Wang, Wei Zhu, Guotong Xie

GEMv2: Multilingual NLG Benchmarking in a Single Line of Code (2022.emnlp-demos)

Challenge:	Existing methods for Chinese spelling error correction focus on local contextual information, thus misleading the user and reducing performance.
Approach:	They propose a global attention decoder that learns the global relationship of correct input characters and candidates of potential error characters.
Outcome:	The proposed method outperforms all competitor models by a large margin of up to 6.2% on three human-annotated datasets.

Copied to clipboard

Sebastian Gehrmann, Abhik Bhattacharjee, Abinaya Mahendiran, Alex Wang, Alexandros Papangelis, Aman Madaan, Angelina Mcmillan-major, Anna Shvets, Ashish Upadhyay, Bernd Bohnet, Bingsheng Yao, Bryan Wilie, Chandra Bhagavatula, Chaobin You, Craig Thomson, Cristina Garbacea, Dakuo Wang, Daniel Deutsch, Deyi Xiong, Di Jin, Dimitra Gkatzia, Dragomir Radev, Elizabeth Clark, Esin Durmus, Faisal Ladhak, Filip Ginter, Genta Indra Winata, Hendrik Strobelt, Hiroaki Hayashi, Jekaterina Novikova, Jenna Kanerva, Jenny Chim, Jiawei Zhou, Jordan Clive, Joshua Maynez, João Sedoc, Juraj Juraska, Kaustubh Dhole, Khyathi Raghavi Chandu, Laura Perez Beltrachini, Leonardo F . R. Ribeiro, Lewis Tunstall, Li Zhang, Mahim Pushkarna, Mathias Creutz, Michael White, Mihir Sanjay Kale, Moussa Kamal Eddine, Nico Daheim, Nishant Subramani, Ondrej Dusek, Paul Pu Liang, Pawan Sasanka Ammanamanchi, Qi Zhu, Ratish Puduppully, Reno Kriz, Rifat Shahriyar, Ronald Cardenas, Saad Mahamood, Salomey Osei, Samuel Cahyawijaya, Sanja Štajner, Sebastien Montella, Shailza Jolly, Simon Mille, Tahmid Hasan, Tianhao Shen, Tosin Adewumi, Vikas Raunak, Vipul Raheja, Vitaly Nikolaev, Vivian Tsai, Yacine Jernite, Ying Xu, Yisi Sang, Yixin Liu, Yufang Hou

MoE Adapter for Large Audio Language Models: Sparsity, Disentanglement, and Gradient-Conflict-Free (2026.findings-acl)

Challenge:	Evaluations in machine learning rarely use the latest metrics, datasets, or human evaluation in favor of remaining compatible with prior work.
Approach:	They propose to use the Generation, Evaluation, and Metrics Benchmark to integrate new evaluation methods into existing evaluations.
Outcome:	The proposed evaluation infrastructure bridges the gap between the advantages of leaderboards and in-depth and evolving evaluations by allowing model developers to benefit from each other's work.

Copied to clipboard

Yishu Lei, Shuwei He, Hu Jing, Dan Zhang, Xianlong Luo, Danxiang Zhu, Shikun Feng, Rui Liu, Jingzhou HE, Yu Sun, Hua Wu, Haifeng Wang

MultiAgentBench : Evaluating the Collaboration and Competition of LLM agents (2025.acl-long)

Challenge:	Existing research on Large Language Models (LLMs) limited to textual input modality . acoustic information is intrinsically heterogeneous, entangling attributes such as speech, music, and environmental context.
Approach:	They propose a sparse Mixture-of-Experts architecture to decouple acoustic information by routing audio tokens to specialized experts.
Outcome:	The proposed architecture outperforms existing models on audio semantic and paralinguistic tasks while retaining shared experts for global context.

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.

Black-Box Membership Inference Attacks for Video Training Data in Multimodal Large Language Models (2026.acl-long)

Copied to clipboard

Jinrui Wang, Zhenfeng Gao, Wendan Wang, Huili Wang, Zichen Qin, Linjie Zhu, Hongke Fu, Shangguang Wang, Tao Qi

Context-Aware Tracking and Dynamic Introduction for Incomplete Utterance Rewriting in Extended Multi-Turn Dialogues (2024.findings-acl)

Challenge:	Existing methods assess model memorization of key semantic concepts within a video but do not provide reliable evidence that a specific video was used during training.
Approach:	They propose a black-box MIA framework that can provide reliable evidence of specific video data usage for training multimodal large language models.
Outcome:	The proposed framework can provide reliable evidence of specific video data usage for training multimodal large language models.

Copied to clipboard

Xinnan Guo, Qian Zhu, Qiuhui Shi, Xuan Lin, Liubin Wang, DaqianLi DaqianLi, Yongrui Chen

Debiasing In-Context Learning by Instructing LLMs How to Follow Demonstrations (2024.findings-acl)

Challenge:	Existing methods to reconstruct utterance with omitted information and pronouns are limited to brief multi-turn dialogues.
Approach:	They propose a method to reconstruct utterance with omitted information and pronouns to be standalone and complete based on context.
Outcome:	The proposed method improves existing models and achieves state-of-the-art on three benchmarks.

Copied to clipboard

Lvxue Li, Jiaqi Chen, Xinyu Lu, Yaojie Lu, Hongyu Lin, Shuheng Zhou, Huijia Zhu, Weiqiang Wang, Zhongyi Liu, Xianpei Han, Le Sun

ImaginE: An Imagination-Based Automatic Evaluation Metric for Natural Language Generation (2023.findings-eacl)

Challenge:	In-context learning (ICL) has gained considerable attention due to its data efficiency and task adaptability.
Approach:	They propose to de-biase demonstration bias in in-context learning by focusing on semantic ambiguity induced by demonstrations and reducing the semantic hazard.
Outcome:	The proposed methods significantly improve performance on six datasets.

Copied to clipboard

Wanrong Zhu, Xin Wang, An Yan, Miguel Eckstein, William Yang Wang

PSC: Extending Context Window of Large Language Models via Phase Shift Calibration (2024.emnlp-main)

Challenge:	Existing evaluation methods for natural language generation rely on token-level or embedding-level comparisons with text references.
Approach:	They propose to use text-to-image generator to generate an image as the embodied imagination for the text snippet and compute the imagination similarity using contextual embeddings.
Outcome:	The proposed metric improves existing evaluation metrics’ correlations with human similarity judgments in both reference-based and reference-free scenarios.

Copied to clipboard

Wenqiao Zhu, Chao Xu, Lulu Wang, Jun Wu

IGenBench: Benchmarking the Reliability of Text-to-Infographic Generation (2026.acl-long)

Challenge:	Large-scale language models (LLMs) have shown impressive results across a variety of tasks.
Approach:	They propose a module for calibrating the frequencies predefined by existing methods . they conducted extensive experiments across multiple models and tasks .
Outcome:	The proposed method reduces perplexity as the context window size is varied from 16k to 32k and up to 64k.

Copied to clipboard

Yinghao Tang, Xueding Liu, Boyuan Zhang, Tingfeng Lan, Yupeng Xie, Jiale Lao, Yiyao Wang, Haoxuan Li, Tingting Gao, Bo Pan, Luoxuan Weng, Xiuqi Huang, Minfeng Zhu, Yingchaojie Feng, Yuyu Luo, Wei Chen

A Multi-Expert Structural-Semantic Hybrid Framework for Unveiling Historical Patterns in Temporal Knowledge Graphs (2025.findings-acl)

Challenge:	Generated infographics may appear correct at first glance but contain easily overlooked issues, such as distorted data encoding or incorrect textual content.
Approach:	They propose to evaluate reliability of text-to-infographic generation using IGenBench . they employ multimodal large language models to verify each question .
Outcome:	The proposed framework decomposes reliability verification into atomic yes/no questions based on a taxonomy of 10 question types.

Copied to clipboard

Yimin Deng, Yuxia Wu, Yejing Wang, Guoshuai Zhao, Li Zhu, Qidong Liu, Derong Xu, Zichuan Fu, Xian Wu, Yefeng Zheng, Xiangyu Zhao, Xueming Qian

Knowledge Representation

Challenge:	Existing methods focus on graph structure learning or semantic reasoning, lacking the capability to capture the inherent differences between historical and non-historical events.
Approach:	They propose a temporal knowledge graph reasoning framework that integrates both structural and semantic information to guide the reasoning process for different events.
Outcome:	The proposed framework integrates structural and semantic information to predict future events . it can provide evidence for many downstream tasks, including situation analysis and political decision making .

Speculative Safety-Aware Decoding (2025.emnlp-main)

Copied to clipboard

Xuekang Wang, Shengyu Zhu, Xueqi Cheng

Label-Free Distant Supervision for Relation Extraction via Knowledge Graph Embedding (D18-1)

Challenge:	Speculative Safety-Aware Decoding (SSD) equips large language models with desired safety property while accelerating inference.
Approach:	They propose a lightweight decoding-time approach that equips large models with the desired safety property while accelerating inference.
Outcome:	Experimental results show that a small language model has the desired safety property while accelerating inference.

Copied to clipboard

Guanying Wang, Wen Zhang, Ruoxu Wang, Yalin Zhou, Xi Chen, Wei Zhang, Hai Zhu, Huajun Chen

Improved Knowledge Distillation for Pre-trained Language Models via Knowledge Selection (2022.findings-emnlp)

Challenge:	Existing methods to generate large scale labeled data for relation extraction produce noisy relation labels when there are multiple relationships between entities.
Approach:	They propose a method which assumes that a pair of entities appears in a Knowledge Graph and trains a relation classifier.
Outcome:	The proposed method performs well in the current distant supervision dataset.

Copied to clipboard

Chenglong Wang, Yi Lu, Yongyu Mu, Yimin Hu, Tong Xiao, Jingbo Zhu

Self-Generated Critiques Boost Reward Modeling for Language Models (2025.naacl-long)

Challenge:	Existing studies on knowledge distillation have shown that not all knowledge is necessary for learning a good student model.
Approach:	They propose an actor-critic approach to selecting appropriate knowledge to transfer during the process of knowledge distillation.
Outcome:	The proposed method outperforms several strong knowledge distillation baselines significantly on the GLUE datasets.

Copied to clipboard

Yue Yu, Zhengxing Chen, Aston Zhang, Liang Tan, Chenguang Zhu, Richard Yuanzhe Pang, Yundi Qian, Xuewei Wang, Suchin Gururangan, Chao Zhang, Melanie Kambadur, Dhruv Mahajan, Rui Hou

ImCoref-CeS: An Improved Lightweight Pipeline for Coreference Resolution with LLM-based Checker-Splitter Refinement (2026.acl-long)

Challenge:	Existing reward models produce scalar scores and struggle to incorporate critiques in a natural language format.
Approach:	They propose a framework that predicts critiques and rewards using self-generated critiques without extra supervision.
Outcome:	The proposed framework improves reward modeling accuracy by 3.7%-7.3% compared to standard reward models and LLM judges.

Copied to clipboard

Kangyang Luo, Yuzhuo Bai, Shuzheng Si, Cheng Gao, Zhitong Wang, Yingli Shen, Wenhao Li, Zhu Liu, Yufeng Han, Jiayi Wu, Cunliang Kong, Maosong Sun

Language-Specific Layer Matters: Efficient Multilingual Enhancement for Large Vision-Language Models (2025.findings-emnlp)

Challenge:	Existing supervised neural methods for coreference resolution are underexplored . current methods rely on small language models, but their potential is underexploited .
Approach:	They propose a framework that integrates an enhanced supervised model with LLM-based reasoning.
Outcome:	The proposed method surpasses existing state-of-the-art methods in coreference resolution.

Copied to clipboard

Yuchun Fan, Yilin Wang, Yongyu Mu, Lei Huang, Bei Li, Xiaocheng Feng, Tong Xiao, JingBo Zhu

GenDis: Generative-Discriminative Dual-View Co-Training for Generalized Category Discovery (2026.acl-long)

Challenge:	Large vision-language models exhibit an imbalance in multilingual capabilities .
Approach:	They propose a training recipe that achieves efficient multilingual enhancement for LVLMs by Precise Language Specific layers fine-tuning.
Outcome:	The proposed training recipe achieves efficient multilingual enhancement for LVLMs by fine-tuning language specific layers.

Copied to clipboard

Xi Chen, Chuan Qin, Jinpeng Li, Shasha Hu, Chao Wang, Hengshu Zhu, Hui Xiong

Challenge:	Existing methods rely on one-hot discriminative supervision, leading to overfitting on seen classes and poor generalization to unseen ones.
Approach:	They propose a Generative–Discriminative Dual-View Co-Training framework that unifies discriminative classification and semantic label generation within an LLM.
Outcome:	The proposed framework outperforms existing methods on five benchmarks on the generalized category discovery (GCD) task.

Mirror: A Universal Framework for Various Information Extraction Tasks (2023.emnlp-main)

Copied to clipboard

Tong Zhu, Junfei Ren, Zijian Yu, Mengsong Wu, Guoliang Zhang, Xiaoye Qu, Wenliang Chen, Zhefeng Wang, Baoxing Huai, Min Zhang

Forgetting Curve: A Reliable Method for Evaluating Memorization Capability for Long-Context Models (2024.emnlp-main)

Challenge:	Recent studies often formulate IE tasks as a triplet extraction problem, but this paradigm does not support multi-span and n-ary extraction, leading to weak versatility.
Approach:	They propose a multi-span cyclic graph extraction problem and a non-autoregressive graph decoding algorithm to extract all spans in a single step.
Outcome:	The proposed model outperforms or reaches competitive performance with SOTA systems under few-shot and zero-shot settings and it is compatible with 57 datasets.

Copied to clipboard

Xinyu Liu, Runsong Zhao, Pengcheng Huang, Chunyang Xiao, Bei Li, Jingang Wang, Tong Xiao, JingBo Zhu

EDSD: Entropy-Driven Design for Faster Speculative Decoding (2026.acl-long)

Challenge:	Existing methods, tasks and benchmarks to measure model’s effective memory length are limited.
Approach:	They propose a method called forgetting curve to measure the memorization capability of long-context models.
Outcome:	The proposed method is robust to the tested corpus and experimental settings, and can be applied to any model size.

Copied to clipboard

Longkai Cheng, Ximing Wang, Jiangcai Zhu, Kailai Shao, Chao Chen, Haixiang Hu

LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Models (2026.acl-long)

Challenge:	Existing methods for speculative decoding incur substantial training overhead to mitigate information misalignment between autoregressive draft model training and decoding.
Approach:	They propose an Entropy-Driven Speculative Decoding framework that uses entropy as a unified, interpretable signal for both draft model training and architectural design.
Outcome:	Experiments on seven large language models show that EDSD improves training efficiency by 24.8% and increases acceptance length by 4.0% compared to state-of-the-art methods.

Copied to clipboard

Fengqi Zhu, Rongzhen Wang, Shen Nie, Xiaolu Zhang, Chunwei Wu, Jun Zhou, Yankai Lin, Ji-Rong Wen, Chongxuan Li

CoV: Chain-of-View Prompting for Spatial Reasoning (2026.findings-acl)

Challenge:	Masked diffusion language models have achieved significant progress in language modeling . however, the systematic analysis and empirical validation of their alignment on general tasks remains underexplored.
Approach:	They propose a framework that analyzes the bias and variance of preference optimization loss and gradient based on Direct Preference Optimization.
Outcome:	The proposed model outperforms its SFT-only predecessor on general benchmarks . it consistently outperformed other strong language models and ARMs on general tasks .

Copied to clipboard

Haoyu Zhao, Akide Liu, Zeyu Zhang, Weijie Wang, Feng Chen, Ruihan Zhu, Gholamreza Haffari, Bohan Zhuang

RoT: Enhancing Table Reasoning with Iterative Row-Wise Traversals (2025.emnlp-main)

Challenge:	Embodied question answering requires collecting context that is distributed across multiple viewpoints . most recent vision–language models (VLMs) are constrained to a fixed and finite set of input views .
Approach:	They propose a training-free, test-time reasoning framework that transforms a VLM into an active viewpoint reasoner through a coarse-to-fine exploration process.
Outcome:	The proposed framework improves LLM-Match performance by 11.98% on four mainstream VLMs.

Copied to clipboard

Xuanliang Zhang, Dingzirui Wang, Keyan Xu, Qingfu Zhu, Wanxiang Che

MPPO: Multi Pair-wise Preference Optimization for LLMs with Arbitrary Negative Samples (2025.coling-main)

Challenge:	Recent advances in reasoning large language models (RLLMs) have significantly enhanced reasoning capabilities, leading to brilliant performance on table reasoning.
Approach:	They propose a method which performs iterative row-wise table traversal, allowing for reasoning extension and reflection-based refinement at each traversal.
Outcome:	Experiments show that the proposed method outperforms RLLMs on WikiTableQuestions and TableBench by 4.3% and achieves state-of-the-art results with comparable models.

Copied to clipboard

Shuo Xie, Fangzhi Zhu, Jiahui Wang, Lulu Wen, Wei Dai, Xiaowei Chen, Junxiong Zhu, Kai Zhou, Bo Zheng

Challenge:	Existing preference optimization methods such as DPO and KTO are inherently derived from PPO, requiring a reference model that adds GPU memory resources and relies heavily on abundant preference data.
Approach:	They propose an algorithm that leverages the average likelihood of model responses to fit the reward function and maximizes the utilization of preference data.
Outcome:	The proposed algorithm outperforms DPO, ORPO, and SimPO on MT-Bench and Arena-Hard.

Multi-layer Representation Fusion for Neural Machine Translation (C18-1)

Copied to clipboard

Qiang Wang, Fuxue Li, Tong Xiao, Yanyang Li, Yinqiao Li, Jingbo Zhu

EmRel: Joint Representation of Entities and Embedded Relations for Multi-triple Extraction (2022.naacl-main)

Challenge:	Neural machine translation systems require a number of stacked layers for deep models, but the prediction depends on the sentence representation of the top-most layer with no access to low-level representations.
Approach:	They propose a multi-layer representation fusion approach to fusing stacked layers to learn a better representation from the stack.
Outcome:	The proposed approach yields 0.92 and 0.56 BLEU points over the strong Transformer baseline on IWSLT German-English and NIST Chinese-English MT tasks respectively.

Copied to clipboard

Benfeng Xu, Quan Wang, Yajuan Lyu, Yabing Shi, Yong Zhu, Jie Gao, Zhendong Mao

Adversarial Preference Learning for Robust LLM Alignment (2025.findings-acl)

Challenge:	Existing studies only explore entity representations, but propose a novel triple perspective for relation extraction.
Approach:	They propose to explicitly introduce relation representation and jointly represent it with entities to identify valid triples.
Outcome:	The proposed method is based on ablations and document-level relation extraction and joint entity and relation extraction.

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

Learning from LLM Agents: In-Context Generative Models for Text Casing in E-Commerce Ads (2025.emnlp-industry)

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

Yingxue Zhou, Tan Zhu, Tao Zeng, Zigeng Wang, Wei Shen

EvolveBench: A Comprehensive Benchmark for Assessing Temporal Awareness in LLMs on Evolving Knowledge (2025.acl-long)

Challenge:	Existing NER-based transformer models are expensive and lack contextual dependencies, making them less reliable when handling unseen or ad-specific terms, e.g., brand names.
Approach:	They propose a two-stage approach to casing correction in e-commerce ad content that leverages Chain-of-Actions to enforce content policies while accurately handling ads-specific terms.
Outcome:	The proposed model outperforms existing NER-based models and achieves near-LLM performance at a fraction of the cost.

Copied to clipboard

Zhiyuan Zhu, Yusheng Liao, Zhe Chen, Yuhao Wang, Yunfeng Guan, Yanfeng Wang, Yu Wang

Challenge:	Existing studies have explored how LLMs perceive time, but they often overlook the critical aspect of knowledge utilization.
Approach:	They propose a benchmark that evaluates temporal competence along five key dimensions: Cognition, Awareness, Trustworthiness and reasoning.
Outcome:	EvolveBench measures temporal competence along five key dimensions: Cognition, Awareness, Trustworthiness, Understanding and reasoning.

LAM SIMULATOR: Advancing Data Generation for Large Action Model Training via Online Exploration and Trajectory Feedback (2025.findings-acl)

Copied to clipboard

Thai Quoc Hoang, Kung-Hsiang Huang, Shirley Kokane, Jianguo Zhang, Zuxin Liu, Ming Zhu, Jake Grigsby, Tian Lan, Michael S Ryoo, Chien-Sheng Wu, Shelby Heinecke, Huan Wang, Silvio Savarese, Caiming Xiong, Juan Carlos Niebles

Challenge:	Large Action Models (LAMs) face challenges due to the need for high-quality training data, especially for multi-steps tasks that involve planning, executing tool calls, and responding to feedback.
Approach:	They propose a framework for online exploration of agentic tasks with high-quality feedback . they use a dynamic task query generator and an extensive collection of tools to create a high-level feedback environment for LLM Agents.
Outcome:	The proposed framework achieves 49.3% performance improvement over baselines on toolbench and CRMArena.

DocEE: A Large-Scale and Fine-grained Benchmark for Document-level Event Extraction (2022.naacl-main)

Copied to clipboard

MeiHan Tong, Bin Xu, Shuai Wang, Meihuan Han, Yixin Cao, Jiangqi Zhu, Siyu Chen, Lei Hou, Juanzi Li

MedEinst: Benchmarking the Einstellung Effect in Medical LLMs through Counterfactual Differential Diagnosis (2026.acl-long)

Challenge:	Existing datasets focus on sentence-level event extraction, but document-level EE is limited due to the lack of large-scale and practical training and evaluation datasets.
Approach:	They propose a document-level event extraction dataset with 27,000+ events and 180,000+ arguments.
Outcome:	The proposed dataset includes 27,000+ events, 180,000+ arguments and large-scale manual annotations, fine-grained argument types and application-oriented settings.

Copied to clipboard

Wenting Chen, Guolin Huang, Wenxuan Wang, Zhongrui Zhu

MIO: A Foundation Model on Multimodal Tokens (2025.emnlp-main)

Challenge:	Existing medical benchmarks fail to detect the Einstellung Effect in clinical diagnosis . Existing models exhibit the Einstellung effect, relying on statistical shortcuts rather than logical reasoning.
Approach:	They propose a counterfactual benchmark that uses statistical shortcuts to diagnose patients . they propose CGME-based system that iteratively refines reasoning paths .
Outcome:	The proposed model achieves high baseline accuracy but severe bias trap rates . iteratively refines reasoning paths in an exemplar base and consolidates disease-specific knowledge into illness graphs.

Copied to clipboard

Zekun Moore Wang, King Zhu, Chunpu Xu, Wangchunshu Zhou, Jiaheng Liu, Yibo Zhang, Jessie Wang, Ning Shi, Siyu Li, Yizhi Li, Haoran Que, Zhaoxiang Zhang, Yuanxing Zhang, Ge Zhang, Ke Xu, Jie Fu, Wenhao Huang

Q-Mamba: Towards more efficient Mamba models via post-training quantization (2025.findings-acl)

Challenge:	Existing models lack multimodal understanding capabilities, resulting in closed-source model that does not support multimodal interleaved sequences.
Approach:	They propose a foundation model built on multimodal tokens capable of understanding and generating speech, text, images, and videos in an end-to-end, autoregressive manner.
Outcome:	The proposed model is able to understand speech, text, images, and videos in an end-to-end, autoregressive manner.

Copied to clipboard

Chen Tianqi, Yuanteng Chen, Peisong Wang, Weixiang Xu, Zeyu Zhu, Jian Cheng

Mem2Evolve: Towards Self-Evolving Agents via Co-Evolutionary Capability Expansion and Experience Distillation (2026.acl-long)

Challenge:	Existing studies show that Mamba architectures have room for further optimization in linear projections and state caches.
Approach:	They propose a decoupled scale quantization scheme to mitigate outliers in states and channels by applying separate quantization scales.
Outcome:	The proposed method reduces memory consumption by 50% across various quantization settings, model sizes, and generation and zero-shot tasks.

Copied to clipboard

Zihao Cheng, Zeming Liu, Yingyu Shan, Xinyi Wang, Xiangrong Zhu, Yunpu Ma, Hongru Wang, Yuhang Guo, Wei Lin, Yunhong Wang

Answer Quality Aware Aggregation for Extractive QA Crowdsourcing (2022.findings-emnlp)

Challenge:	Existing frameworks that focus on static tools and static assets are ineffective for self-evolving agents.
Approach:	They propose a paradigm of co-evolutionary Capability Expansion and Experience Distillation that leverages accumulated experience to guide dynamic creation of assets.
Outcome:	The proposed framework improves performance in single-task and cross-task settings by 18.53% over standard LLMs, 11.80% over agents evolving solely through experience, and 6.46% over those evolving solelly through asset creation.

Copied to clipboard

Peide Zhu, Zhen Wang, Claudia Hauff, Jie Yang, Avishek Anand

Towards Effective and Efficient Continual Pre-training of Large Language Models (2025.acl-long)

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

Jie Chen, Zhipeng Chen, Jiapeng Wang, Kun Zhou, Yutao Zhu, Jinhao Jiang, Yingqian Min, Xin Zhao, Zhicheng Dou, Jiaxin Mao, Yankai Lin, Ruihua Song, Jun Xu, Xu Chen, Rui Yan, Zhewei Wei, Di Hu, Wenbing Huang, Ji-Rong Wen

Dual Reader-Parser on Hybrid Textual and Tabular Evidence for Open Domain Question Answering (2021.acl-long)

Challenge:	Continual pre-training (CPT) has been an important approach for adapting language models to specific domains or tasks.
Approach:	They propose a Continual pre-training method that can greatly improve Chinese language ability and scientific reasoning ability of LLMs.
Outcome:	The proposed method can greatly improve Chinese language ability and scientific reasoning ability of LLMs.

Copied to clipboard

Alexander Hanbo Li, Patrick Ng, Peng Xu, Henghui Zhu, Zhiguo Wang, Bing Xiang

SmartTrim: Adaptive Tokens and Attention Pruning for Efficient Vision-Language Models (2024.lrec-main)

Challenge:	Existing generative models for open-domain question answering focus on generating direct answers from unstructured textual information, but a large amount of knowledge is stored in structured databases, and need to be accessed using query languages such as SQL.
Approach:	They propose a hybrid framework that takes both textual and tabular evidences as input and generates either direct answers or SQL queries depending on which form could better answer the question.
Outcome:	The proposed framework outperforms baseline models on OpenSQuAD datasets and can generate SQL queries on the associated databases to obtain the final answers.

Copied to clipboard

Zekun Wang, Jingchang Chen, Wangchunshu Zhou, Haichao Zhu, Jiafeng Liang, Liping Shan, Ming Liu, Dongliang Xu, Qing Yang, Bing Qin

Leveraging Knowledge in Multilingual Commonsense Reasoning (2022.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

Yuwei Fang, Shuohang Wang, Yichong Xu, Ruochen Xu, Siqi Sun, Chenguang Zhu, Michael Zeng

Dynamic Multistep Reasoning based on Video Scene Graph for Video Question Answering (2022.naacl-main)

Challenge:	Commonsense reasoning is a language-agnostic process, but most comprehensive knowledge sources are limited to a small number of languages, especially English.
Approach:	They propose to use English as a pivot language to integrate commonsense reasoning into models using a translate-retrieve-translate strategy.
Outcome:	The proposed model outperforms the state-of-the-art on the XCSR benchmarks.

Copied to clipboard

Jianguo Mao, Wenbin Jiang, Xiangdong Wang, Zhifan Feng, Yajuan Lyu, Hong Liu, Yong Zhu

Chart2Code53: A Large-Scale Diverse and Complex Dataset for Enhancing Chart-to-Code Generation (2025.emnlp-main)

Challenge:	Existing video QA models lack the capacity for deep video understanding and flexible multistep reasoning.
Approach:	They propose a video question answering model which performs dynamic multistep reasoning between questions and videos.
Outcome:	The proposed model improves on three widely used video QA datasets and displays better interpretability by backtracing along with the attention mechanisms to the video scene graphs.

Copied to clipboard

Tianhao Niu, Yiming Cui, Baoxin Wang, Xiao Xu, Xin Yao, Qingfu Zhu, Dayong Wu, Shijin Wang, Wanxiang Che

DyBBT: Dynamic Balance via Bandit-inspired Targeting for Dialog Policy with Cognitive Dual Systems (2026.acl-long)

Challenge:	Existing Chart2code-related training datasets suffer from limited scale, limited type coverage, and inadequate complexity.
Approach:	They propose to synthesize chart2code-related training datasets using web plotting code and chart images to address these challenges.
Outcome:	The proposed dataset exhibits the greatest diversity and higher complexity compared to other open-source Chart2code related datasets.

Copied to clipboard

Shuyu Zhang, Yifan Wei, Jialuo Yuan, Xinru Wang, Yanmin Zhu, Yujie Liu, Bin Li

PlanGPT-VL: Enhancing Urban Planning with Domain-Specific Vision-Language Models (2025.emnlp-industry)

Challenge:	Task oriented dialog systems often rely on static exploration strategies that do not adapt to dynamic dialog contexts.
Approach:	They propose a dialog policy learning framework that formalizes the exploration challenge through a structured cognitive state space C.
Outcome:	The proposed framework achieves SOTA performance in success rate, efficiency, and generalization.

Copied to clipboard

He Zhu, Junyou Su, Minxin Chen, Wen Wang, Yijie Deng, Guanhua Chen, Wenjia Zhang

Emotion Inference in Multi-Turn Conversations with Addressee-Aware Module and Ensemble Strategy (2021.emnlp-main)

Challenge:	Existing Vision-Language Models (VLMs) fail to analyze planning maps . specialized visual representations of land use zones, transportation networks, and development policies are needed to interpret complex planning maps.
Approach:	They propose a domain-specific VLM tailored for urban planning maps that employs three innovations: PlanAnno-V framework for high-quality VQA data synthesis, Critical Point Thinking (CPT) and PlanBench-V benchmark for systematic evaluation.
Outcome:	The new model outperforms general-purpose VLMs on planning map interpretation tasks.

Copied to clipboard

Dayu Li, Xiaodan Zhu, Yang Li, Suge Wang, Deyu Li, Jian Liao, Jianxing Zheng

Auto-Instruct: Automatic Instruction Generation and Ranking for Black-Box Language Models (2023.findings-emnlp)

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

Zhihan Zhang, Shuohang Wang, Wenhao Yu, Yichong Xu, Dan Iter, Qingkai Zeng, Yang Liu, Chenguang Zhu, Meng Jiang

EffiQA: Efficient Question-Answering with Strategic Multi-Model Collaboration on Knowledge Graphs (2025.coling-main)

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

Zixuan Dong, Baoyun Peng, Yufei Wang, Jia Fu, Xiaodong Wang, Xin Zhou, Yongxue Shan, Kangchen Zhu, Weiguo Chen

Zero-Shot Spoken Language Understanding via Large Language Models: A Preliminary Study (2024.lrec-main)

Challenge:	Existing approaches that integrate LLMs and KGs either underutilize the reasoning abilities of LLM or suffer from prohibitive computational costs due to tight coupling.
Approach:	They propose a framework that can strike a balance between performance and efficiency via an iterative paradigm.
Outcome:	The proposed framework can strike a balance between performance and efficiency via an iterative paradigm.

Copied to clipboard

Zhihong Zhu, Xuxin Cheng, Hao An, Zhichang Wang, Dongsheng Chen, Zhiqi Huang

SCITAT: A Question Answering Benchmark for Scientific Tables and Text Covering Diverse Reasoning Types (2025.findings-acl)

Challenge:	Recent advances in large language models (LLMs) have shown promising results in zero-shot settings, which motivates us to explore prompt-based methods.
Approach:	They propose a two-stage framework which transforms the SLU task into a question-answering problem by directly prompting LLMs.
Outcome:	The proposed framework can be built by directly prompting LLMs to understand user needs without training data.

Copied to clipboard

Xuanliang Zhang, Dingzirui Wang, Baoxin Wang, Longxu Dou, Xinyuan Lu, Keyan Xu, Dayong Wu, Qingfu Zhu

Enhancing Multimodal Unified Representations for Cross Modal Generalization (2025.findings-acl)

Challenge:	Existing scientific question answering datasets lack diverse reasoning types and neglect relevance between tables and text.
Approach:	They propose a scientific question answering benchmark for scientific tables and text with diverse reasoning types (SCITAT) to address these challenges, they propose QA benchmark which incorporates tables and texts to ensure that the questions encompass both tables and textes.
Outcome:	The proposed benchmark improves by 4.1% over baselines on SCITAT.

Copied to clipboard

Hai Huang, Yan Xia, Shengpeng Ji, Shulei Wang, Hanting Wang, Minghui Fang, Jieming Zhu, Zhenhua Dong, Sashuai Zhou, Zhou Zhao

PartialFormer: Modeling Part Instead of Whole for Machine Translation (2024.findings-acl)

Challenge:	Existing studies on discrete unified representations overlook important distinctions between different dimensions of features.
Approach:	They propose to use a codebook to optimize unified representations from pretraining and fine- and coarse-grained disentangling to optimize the representations.
Outcome:	The proposed methods improve the interpretability of multimodal unified representations . they use training-free optimization of codebook and fine and coarse cross-modal disentangling .

Copied to clipboard

Tong Zheng, Bei Li, Huiwen Bao, Jiale Wang, Weiqiao Shan, Tong Xiao, JingBo Zhu

AgentReview: Exploring Peer Review Dynamics with LLM Agents (2024.emnlp-main)

Challenge:	Existing feed-forward neural networks have significant computational and parametric overhead.
Approach:	They propose a parameter-efficient Transformer architecture that utilizes multiple smaller FFNs to reduce parameters and computation while maintaining essential hidden dimensions.
Outcome:	The proposed architecture reduces computational and parameter overhead while maintaining essential hidden dimensions.

Copied to clipboard

Yiqiao Jin, Qinlin Zhao, Yiyang Wang, Hao Chen, Kaijie Zhu, Yijia Xiao, Jindong Wang

Ethical NLP

Challenge:	Existing methods of peer review analysis do not address multivariate nature of the process, account for latent variables, and are constrained by privacy concerns due to the sensitive nature of data.
Approach:	They propose a large language model based peer review simulation framework which effectively disentangles the impacts of multiple latent factors and addresses the privacy issue.
Outcome:	The proposed framework disentangles the impacts of multiple latent factors and addresses privacy concerns.

Length Controlled Generation for Black-box LLMs (2025.acl-long)

Copied to clipboard

Yuxuan Gu, Wenjie Wang, Xiaocheng Feng, Weihong Zhong, Kun Zhu, Lei Huang, Ting Liu, Bing Qin, Tat-Seng Chua

JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs (2021.findings-acl)

Challenge:	Existing length control methods involve fine-tuning the parameters of LLMs, which is inefficient and suboptimal for practical use.
Approach:	They propose an iterative sampling framework that regulates LLMs to generate length-constrained text without modifying the underlying parameters.
Outcome:	The proposed method achieves 100% success rates on Llama3.1 tasks with minimal additional computational overhead.

Copied to clipboard

Pei Ke, Haozhe Ji, Yu Ran, Xin Cui, Liwei Wang, Linfeng Song, Xiaoyan Zhu, Minlie Huang

WebCPM: Interactive Web Search for Chinese Long-form Question Answering (2023.acl-long)

Challenge:	Existing pre-trained models for knowledgegraph-to-text generation ignore graph structure during encoding and lack elaborate pre-training tasks to explicitly model graph-text alignments.
Approach:	They propose a graph-text joint representation learning model called JointGT which incorporates a structure-aware semantic aggregation module into each Transformer layer to preserve the graph structure.
Outcome:	The proposed model achieves state-of-the-art performance on various KG-to-text datasets.

Copied to clipboard

Yujia Qin, Zihan Cai, Dian Jin, Lan Yan, Shihao Liang, Kunlun Zhu, Yankai Lin, Xu Han, Ning Ding, Huadong Wang, Ruobing Xie, Fanchao Qi, Zhiyuan Liu, Maosong Sun, Jie Zhou

Prompting Large Language Models with Chain-of-Thought for Few-Shot Knowledge Base Question Generation (2023.emnlp-main)

Challenge:	Long-form question answering requires two procedures: information retrieval and information synthesis.
Approach:	They propose a Chinese long-form question answering dataset called WebCPM . the dataset is based on a web search interface that engages with a search engine in real time .
Outcome:	The proposed dataset generates answers that are no worse than human-written ones . the dataset is the first Chinese LFQA dataset .

Copied to clipboard

Yuanyuan Liang, Jianing Wang, Hanlun Zhu, Lei Wang, Weining Qian, Yunshi Lan

Enabling Agents to Communicate Entirely in Latent Space (2026.acl-long)

Challenge:	Existing methods for question generation over knowledge bases rely on annotated data for fine-tuning . emergence of Large Language Models (LLMs) has shown impressive generalization ability in few-shot tasks.
Approach:	They propose to use a logical form to generate a question in a reasoning problem . they propose to extend the prompting method into a method that can generate questions in logical forms .
Outcome:	The proposed method outperforms baselines on three public KBQG datasets.

Copied to clipboard

Zhuoyun Du, Runze Wang, Huiyu Bai, Zouying Cao, Xiaoyong Zhu, Yu Cheng, Bo Zheng, Wei Chen, Haochao Ying

Challenge:	Natural language is the de facto communication medium for LLM-based agents, but it presents a fundamental constraint . natural language downsampling limits the depth and nuance of information that can be transmitted . et al.: inter-agent latent space communication is a promising paradigm for solving complex tasks .
Approach:	They propose a paradigm that leverages the last hidden states of an LLM as a representation of its thought for direct communication.
Outcome:	The proposed paradigm outperforms fine-tuned chain-of-thought prompting and single-agent baselines even across heterogeneous models.

LOOK-M: Look-Once Optimization in KV Cache for Efficient Multimodal Long-Context Inference (2024.findings-emnlp)

Copied to clipboard

Zhongwei Wan, Ziang Wu, Che Liu, Jinfa Huang, Zhihong Zhu, Peng Jin, Longyue Wang, Li Yuan

CLIP-UP: A Simple and Efficient Mixture-of-Experts CLIP Training Recipe with Sparse Upcycling (2025.findings-emnlp)

Challenge:	Long-context Multimodal Large Language Models (MLLMs) require substantial computational resources for inference . the growth of their multimodal Key-Value (KV) cache challenges memory and time efficiency.
Approach:	They propose a fine-tuning-free approach that efficiently reduces the multimodal KV cache size while maintaining performance comparable to a full cache.
Outcome:	The proposed method reduces the multimodal KV cache size while maintaining performance comparable to a full cache.

Copied to clipboard

Xinze Wang, Chen Chen, Yinfei Yang, Hong-You Chen, Bowen Zhang, Aditya Pal, Xiangxin Zhu, Xianzhi Du

Knowledge Graph-Enhanced Large Language Models via Path Selection (2024.findings-acl)

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

Haochen Liu, Song Wang, Yaochen Zhu, Yushun Dong, Jundong Li

Gloss-Free End-to-End Sign Language Translation (2023.acl-long)

Challenge:	Large Language Models (LLMs) have shown unprecedented performance in various real-world applications, but they are known to generate factually inaccurate outputs.
Approach:	They propose a framework to integrate external knowledge extracted from Knowledge Graphs (KGs) they propose to generate scores for knowledge paths with input texts via latent semantic matching.
Outcome:	Experiments on real-world datasets validate the effectiveness of a framework to extract knowledge from Knowledge Graphs (KGs) incorporating external knowledge has become a promising strategy to improve the factual accuracy of LLM-generated outputs.

Copied to clipboard

Kezhou Lin, Xiaohan Wang, Linchao Zhu, Ke Sun, Bang Zhang, Yi Yang

HyperMR: Hyperbolic Hypergraph Multi-hop Reasoning for Knowledge-based Visual Question Answering (2024.lrec-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

Bin Wang, Fuyong Xu, Peiyu Liu, Zhenfang Zhu

TCSinger 2: Customizable Multilingual Zero-shot Singing Voice Synthesis (2025.findings-acl)

Challenge:	Existing studies on knowledge-based visual question answering (KBVQA) describe the semantic distance using the actual Euclidean distance between two nodes, which leads to distortion in modeling knowledge graphs with hierarchical and scale-free structure.
Approach:	They propose to use the actual Euclidean distance between two nodes to solve a problem of hierarchical and free-scale knowledge graphs.
Outcome:	Extensive experiments on the KVQA, PQ and PQL datasets demonstrate the effectiveness of HyperMR for strong-hierarchy knowledge graphs.

Copied to clipboard

Yu Zhang, Wenxiang Guo, Changhao Pan, Dongyu Yao, Zhiyuan Zhu, Ziyue Jiang, Yuhan Wang, Tao Jin, Zhou Zhao

Let Modalities Teach Each Other: Modal-Collaborative Knowledge Extraction and Fusion for Multimodal Knowledge Graph Completion (2025.findings-naacl)

Challenge:	Existing zero-shot singing voice synthesis models depend on phoneme and note boundary annotations, limiting their robustness and producing poor transitions between phonemes and notes.
Approach:	They propose a multi-task multilingual zero-shot SVS model with style transfer and style control based on various prompts.
Outcome:	Experimental results show that TCSinger 2 outperforms baseline models in subjective and objective metrics across multiple related tasks.

Copied to clipboard

Guoliang Zhu, Tao Ren, Dandan Wang, Jun Hu

JurisBench: A Deep Benchmark for Assessing Large Language Models in Professional Legal Practice (2026.acl-long)

Challenge:	Recent studies have focused on missing triples in knowledge graphs, but lack correlation between modalities.
Approach:	They propose a framework to foster mutual guidance and collaboration in unimodal knowledge extraction and multimodal knowledge fusion.
Outcome:	Extensive experiments on three real-world datasets demonstrate advantages of Moodle over state-of-the-art methods.

Copied to clipboard

Ziang Chen, Guannan Li, Fanlin Ji, Yipeng Kang, Jiaqi Li, Muhan Zhang, Yangtao Zhang, Li Tianjiao, Jiannan Wang, Xin Guo, Song-Chun Zhu, Bin Ling

M3TQA: Massively Multilingual Multitask Table Question Answering (2026.findings-acl)

Challenge:	Existing legal benchmarks evaluate isolated tasks or exam-style questions, failing to capture the procedural interdependencies and adjudicative rigor inherent in professional practice.
Approach:	They propose a vertical, depth-oriented, domain-specific benchmark to evaluate Large Language Models (LLMs) in Chinese civil litigation.
Outcome:	The proposed benchmarks show that large language models exhibit an "illusion of competence" the results highlight a critical gap between fluent linguistic output and judicial reliability .

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

MMAPG: A Training-Free Framework for Multimodal Multi-hop Question Answering via Adaptive Planning Graphs (2025.emnlp-main)

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

Yiheng Hu, Xiaoyang Wang, Qing Liu, Xiwei Xu, Qian Fu, Wenjie Zhang, Liming Zhu

Proxy-Driven Robust Multimodal Sentiment Analysis with Incomplete Data (2025.acl-long)

Challenge:	Existing multimodal question answering models rely on sequential retrieval and reasoning, but this single-path paradigm makes them vulnerable to errors due to misleading intermediate steps.
Approach:	They propose a multimodal multi-hop question answering framework guided by an Adaptive Planning Graph . they propose modality-specific strategies that dynamically adapt to distinct data types .
Outcome:	The proposed framework outperforms existing models that rely on training.

Copied to clipboard

Aoqiang Zhu, Min Hu, Xiaohua Wang, Jiaoyun Yang, Yiming Tang, Ning An

Learned Adapters Are Better Than Manually Designed Adapters (2023.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

Yuming Zhang, Peng Wang, Ming Tan, Wei Zhu

Unleashing the Potential of Large Language Models through Spectral Modulation (2024.findings-emnlp)

Challenge:	Existing approaches to improve adapter-based tuning are sub-optimal . a learning framework is proposed to learn the optimal adapter architectures .
Approach:	They propose a framework to automatically learn optimal adapter architectures for better task adaptation of pre-trained models.
Outcome:	The proposed framework outperforms the previous parameter-efficient tuning baselines while tuning comparable or fewer parameters.

Copied to clipboard

Peng Sun, Yao Zhu, Yunjian Zhang, Xiu Yan, Zizhe Wang, Xiangyang Ji

Mitigating Lost-in-Retrieval Problems in Retrieval Augmented Multi-Hop Question Answering (2025.acl-long)

Challenge:	Large Language Models (LLMs) have demonstrated impressive capabilities across various domains, garnering significant attention from both academia and industry.
Approach:	They propose to conduct spectral modulation in the parameter space of LLMs to integrate with various models in a plug-and-play manner.
Outcome:	The proposed approach improves performance by 10.12% with spectral modulation.

Copied to clipboard

Rongzhi Zhu, Xiangyu Liu, Zequn Sun, Yiwei Wang, Wei Hu

To Code or not to Code? Adaptive Tool Integration for Math Language Models via Expectation-Maximization (2025.findings-acl)

Challenge:	Empirical results show that ChainRAG consistently outperforms baselines in both effectiveness and efficiency.
Approach:	They propose a method which sequentially handles each sub-question by completing missing key entities and retrieving relevant sentences from a sentence graph for answer generation.
Outcome:	The proposed method outperforms baselines on three multi-hop QA datasets.

Copied to clipboard

Haozhe Wang, Long Li, Chao Qu, Weidi Xu, Fengming Zhu, Wei Chu, Fangzhen Lin

RSDA: Restoring Stale Data Affinity via Dynamic Renovation Strategy for Mitigating Data Scarcity (2026.acl-long)

Challenge:	Existing tools that integrate chain-of-thought reasoning and code execution lack metacognitive awareness to integrate tools.
Approach:	They propose a framework that synergizes structured exploration with off-policy RL optimization to create a cycle between metacognitive tool-use decisions and evolving capabilities.
Outcome:	The proposed framework improves over 11% on MATH500 and 9.4% on AIME without o1-like CoT.

Copied to clipboard

Yidan Liang, Jia Zhu, Weijie Shi, Hanghui Guo, Yue Cui, Jiawei Shen, Guoqing Ma, Jingjiang Liu, Qingyu Niu, Yilin Wang, Shimin Di, Jiajie Xu

Mind the Context: The Impact of Contextualization in Neural Module Networks for Grounding Visual Referring Expressions (2021.emnlp-main)

Challenge:	High-quality data is the cornerstone of advancing large language models, but the supply of premium data is nearing depletion, while vast stale corpora remain underutilized.
Approach:	They propose a framework to restore stale data affinity by quantifying the latent value of samples and employing a dynamic renovation strategy selection mechanism to determine the optimal component-level strategy.
Outcome:	The proposed framework achieves performance improvements using less than 10% of the data volume, underscoring that the latent potential of stale corpora remains largely untapped.

Copied to clipboard

Arjun Akula, Spandana Gella, Keze Wang, Song-Chun Zhu, Siva Reddy

Towards Human-Like Machine Comprehension: Few-Shot Relational Learning in Visually-Rich Documents (2024.lrec-main)

Challenge:	Prior implementations of NMN use pre-defined and fixed textual inputs in their module instantiation.
Approach:	They propose to parameterize the module arguments to reduce the number of modules in NMN by up to 75% without any loss in performance.
Outcome:	The proposed model outperforms the state-of-the-art model on CLEVR-Ref+ dataset with +8.1% improvement in accuracy and +4.3% on full test set.

Copied to clipboard

Hao Wang, Tang Li, Chenhui Chu, Rui Wang, Pinpin Zhu

When LLMs Read Tables Carelessly: Measuring and Reducing Data Referencing Errors (2026.acl-long)

Challenge:	Existing document AI approaches fail to consider key-value relations in visually-rich documents . a few-shot approach is proposed to extract key- value relation triplets in VRDs .
Approach:	They propose a few-shot relational learning approach targeting the extraction of key-value relation triplets in Visually-Rich Documents.
Outcome:	The proposed method outperforms existing methods in visually-rich documents.

Copied to clipboard

Yuqing Yang, Qi Zhu, Zhen Han, Boran Han, Zhengyuan Shen, Shuai Wang, Vassilis N. Ioannidis, Huzefa Rangwala

Training Flexible Depth Model by Multi-Task Learning for Neural Machine Translation (2020.findings-emnlp)

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

Qiang Wang, Tong Xiao, Jingbo Zhu

Understanding In-Context Learning Beyond Transformers: An Investigation of State Space and Hybrid Architectures (2026.findings-acl)

Challenge:	Experimental results show that multitask learning can support decoding in 24 depth configurations and is superior to individual training.
Approach:	They propose to use multi-task learning to train a flexible depth model that can adapt to different depth configurations during inference.
Outcome:	The proposed model can support decoding in 24 depth configurations and is superior to the individual training and another flexible depth model training method——LayerDrop.

Copied to clipboard

Shenran Wang, Timothy Tin-Long Tse, Jian Zhu

Distribution Prompting: Understanding the Expressivity of Language Models Through the Next-Token Distributions They Can Produce (2025.emnlp-main)

Challenge:	In-context learning is an emergent ability from pretrained Large Language Models (LLMs).
Approach:	They perform in-depth evaluations of in-context learning on transformers and hybrid large language models using behavioral probing and intervention-based methods.
Outcome:	The proposed model performs well on state-of-the-art transformer, state-space, and hybrid large language models.

Copied to clipboard

Haojin Wang, Zining Zhu, Freda Shi

Collaborative Generative AI: Integrating GPT-k for Efficient Editing in Text-to-Image Generation (2023.emnlp-main)

Challenge:	Autoregressive neural language models (LMs) generate a probability distribution over tokens at each time step given a prompt.
Approach:	They propose to find a prompt that induces LMs to output a distribution as close as possible to the target, using either soft or hard gradient-based prompt tuning.
Outcome:	The proposed model is able to generate a distribution as close as possible to a target given a prompt, and it can be used to approximate distributions with low or high entropy.

Copied to clipboard

Wanrong Zhu, Xinyi Wang, Yujie Lu, Tsu-Jui Fu, Xin Wang, Miguel Eckstein, William Wang

An Efficient Conversational Smart Compose System (2023.acl-demo)

Challenge:	Experimental results show that GPT-k models focus more on inserting modifiers than predicting spontaneous changes in the primary subject matter.
Approach:	They compare the common edits made by humans and GPT-k models to examine their performance in prompting T2I.
Outcome:	The proposed models improve the prompt editing process by 20-30%, the authors show . they show that humans tend to replace words and phrases with modifiers .

Copied to clipboard

Yun Zhu, Xiayu Chen, Lei Shu, Bowen Tan, Xinying Song, Lijuan Liu, Maria Wang, Jindong Chen, Ning Ruan

Dict-BERT: Enhancing Language Model Pre-training with Dictionary (2022.findings-acl)

Challenge:	a cloud-based smart compose system is designed to improve human-to-human conversation efficiency.
Approach:	They propose a cloud-based smart compose system to improve conversation efficiency . they propose heuristics to achieve the best trade-off between quality and latency .
Outcome:	The proposed system reduces latency without losing composing quality further.

Copied to clipboard

Wenhao Yu, Chenguang Zhu, Yuwei Fang, Donghan Yu, Shuohang Wang, Yichong Xu, Michael Zeng, Meng Jiang

Counterfactual Off-Policy Training for Neural Dialogue Generation (2020.emnlp-main)

Challenge:	Pre-trained language models (PLMs) capture word semantics in different contexts, hence the embeddings of rare words on the tail are poorly optimized.
Approach:	They propose to leverage definitions of rare words in dictionaries to enhance language model pre-training by leveraging dictionary definitions.
Outcome:	The proposed model improves understanding of rare words and boosts performance on various NLP downstream tasks.

Copied to clipboard

Qingfu Zhu, Wei-Nan Zhang, Ting Liu, William Yang Wang

AHA: Aligning Large Audio-Language Models for Reasoning Hallucinations via Counterfactual Hard Negatives (2026.findings-acl)

Challenge:	Existing models for open-domain dialogue generation suffer from data insufficiency . a potential response inferred in hindsight is called a counterfactual reasoning .
Approach:	They propose to explore potential responses by counterfactual reasoning . given an observed response, the model automatically infers the outcome of an alternative policy that could have been taken .
Outcome:	The proposed model outperforms the HRED model and conventional learning frameworks on the DailyDialog dataset.

Copied to clipboard

Yanxi Chen, Wenhui Zhu, Xiwen Chen, Zhipeng Wang, Xin Li, Peijie Qiu, Hao Wang, Xuanzhao Dong, Yujian Xiong, Anderson Schneider, Yuriy Nevmyvaka, Yalin Wang

SPS: Steering Probability Squeezing for Better Exploration in Reinforcement Learning for Large Language Models (2026.findings-acl)

Challenge:	Large Audio-Language Models suffer from hallucinations, e.g., generating text not grounded in the audio input.
Approach:	They propose a framework to address hallucination problems in large audio-language models . they use a preference dataset to test the model's accuracy .
Outcome:	The proposed model outperforms the latest SOTA methods in terms of performance and generalization.

Copied to clipboard

Yifu Huo, Chenglong Wang, Ziming Zhu, Shunjie Xing, Peinan Feng, Tongran Liu, Qiaozhi He, Tian Hua Zhou, null Changxiaojia, JingBo Zhu, Zhengtao Yu, Tong Xiao

Weighted Contrastive Learning With False Negative Control to Help Long-tailed Product Classification (2023.acl-industry)

Challenge:	Reinforcement learning (RL) training typically improves single-sample success rates but limited exploration of diverse reasoning trajectories.
Approach:	They propose a training paradigm that interleaves conventional RL with inverse reinforcement learning (IRL) they propose 'Steering Probability Squeezing' to enhance exploration without external supervision .
Outcome:	The proposed training paradigm improves Pass@k and improves exploration of diverse reasoning trajectories without external supervision.

Copied to clipboard

Tianqi Wang, Lei Chen, Xiaodan Zhu, Younghun Lee, Jing Gao

Can LLMs Really Judge? A Progressive Argumentation-Mining Framework for Distinguishing Understanding from Aggregation (2026.findings-acl)

Challenge:	Item categorization (IC) aims to classify a product into leaf nodes in a categorical taxonomy due to scarce supervision.
Approach:	They propose to use K-positive contrastive loss (KCL) to address IC task’s long-tail issue by re-weighting positive pairs in the KCL loss with a regularization that the sum of weights should be constrained to K+1 as close as possible.
Outcome:	The proposed method improves on the long-tail issue in the image classification task and when using text-based contrastive learning, it can be applied on the IC task.

Copied to clipboard

Fuyu Wang, Jiangtong Li, Kun Zhu, Changjun Jiang

Layer-Wise Multi-View Learning for Neural Machine Translation (2020.coling-main)

Challenge:	Existing evaluations of large language models rely on dataset-based generation accuracy . however, generative correctness does not guarantee discriminative capability to verify solutions .
Approach:	They propose a diagnostic framework that explicitly controls context and isolates discriminative behaviors.
Outcome:	The proposed framework explicitly controls context and isolates discriminative behaviors.

Copied to clipboard

Qiang Wang, Changliang Li, Yue Zhang, Tong Xiao, Jingbo Zhu

DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak (2025.emnlp-main)

Challenge:	Existing approaches to neural machine translation are limited to the topmost encoder layer’s context representation and cannot perceive the lower encoder layers.
Approach:	They propose a layer-wise multi-view learning approach to solve this problem by incorporating an auxiliary view into the model.
Outcome:	The proposed model can achieve stable results over multiple strong baselines and is agnostic to network architectures.

Copied to clipboard

Hao Wang, Hao Li, Junda Zhu, Xinyuan Wang, Chengwei Pan, Minlie Huang, Lei Sha

A Simple and Effective Approach to Coverage-Aware Neural Machine Translation (P18-2)

Challenge:	Large Language Models (LLMs) are susceptible to generating harmful content when prompted with carefully crafted inputs, a vulnerability known as LLM jailbreaking.
Approach:	They propose an end-to-end generative approach for jailbreak rewriting inspired by diffusion models that uses a sequence-tosequence (seq2sequ) diffusion model as a generator, conditioning on the original prompt and guiding the denoising process with a novel attack loss.
Outcome:	Experiments on Advbench and Harmbench show that the proposed method outperforms autoregressive jailbreak models across evaluation metrics including ASR, fluency, diversity and diversity.

Copied to clipboard

Yanyang Li, Tong Xiao, Yinqiao Li, Qiang Wang, Changming Xu, Jingbo Zhu

ICG: Improving Cover Image Generation via MLLM-based Prompting and Personalized Preference Alignment (2025.emnlp-main)

Challenge:	Neural Machine Translation (NMT) models are used to solve translation problems using long-term models.
Approach:	They propose a method to seek a better balance between model confidence and length preference for Neural Machine Translation.
Outcome:	The proposed model improves on Chinese-English and English-German translation tasks.

Copied to clipboard

Zhipeng Bian, Jieming Zhu, Qijiong Liu, Wang Lin, Guohao Cai, Zhaocheng Du, Jiacheng Sun, Zhou Zhao, Zhenhua Dong

SConU: Selective Conformal Uncertainty in Large Language Models (2025.acl-long)

Challenge:	Large language models and diffusion models have opened new possibilities for AI-generated content . personalized cover image generation remains underexplored despite its critical role in boosting user engagement on digital platforms.
Approach:	They propose a framework that integrates MLLM-based prompting with personalized preference alignment to generate high-quality, contextually relevant covers.
Outcome:	The proposed framework improves image quality, semantic fidelity, and personalization, leading to stronger user appeal and offline recommendation accuracy in downstream tasks.

Copied to clipboard

Zhiyuan Wang, Qingni Wang, Yue Zhang, Tianlong Chen, Xiaofeng Zhu, Xiaoshuang Shi, Kaidi Xu

Mitigating Hallucinations in Large Vision-Language Models without Performance Degradation (2026.acl-long)

Challenge:	Existing frameworks fail to identify outliers that violate the exchangeability assumption, leading to unbounded miscoverage rates and unactionable prediction sets.
Approach:	They propose a method that implements significance tests to determine whether a given sample deviates from the uncertainty distribution of the calibration set.
Outcome:	The proposed approach facilitates rigorous management of miscoverage rates across single-domain and interdisciplinary contexts, and enhances the efficiency of predictions.

Copied to clipboard

Xingyu Zhu, Junfeng Fang, Shuo Wang, Beier Zhu, Zhicai Wang, Yonghui Yang, Xiangnan He

Graph-guided Cross-composition Feature Disentanglement for Compositional Zero-shot Learning (2025.findings-acl)

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

Yuxia Geng, Runkai Zhu, Jiaoyan Chen, Jintai Chen, Xiang Chen, Zhuo Chen, Shuofei Qiao, Yuxiang Wang, Xiaoliang Xu, Sheng-Jun Huang

IceBreaker for Conversational Agents: Breaking the First-Message Barrier with Personalized Starters (2026.acl-industry)

Challenge:	Disentanglement of visual features of primitives (i.e., attributes and objects) has shown exceptional results in Compositional Zero-shot Learning (CZSL).
Approach:	They propose a solution that takes multiple compositions as inputs and constrains disentangled primitive features to be general across compositions.
Outcome:	The proposed architecture significantly improves performance on three popular CZSL benchmarks and has been verified by solid ablation studies.

Copied to clipboard

Hongwei Zheng, Weiqi Wu, Zhengjia Wang, Guanyu Jiang, Haoming Li, Tianyu Wu, Yongchun Zhu, Jingwu Chen, Feng Zhang

FocalOrder: Focal Preference Optimization for Reading Order Detection (2026.acl-long)

Challenge:	Existing efforts focus on activation within ongoing dialogues, while overlooking a key real-world bottleneck.
Approach:	They propose a conversation starter generation system that generates personalized starters to guide users into conversation without explicit user intent.
Outcome:	The proposed system improves user active days by +1.84 and click-through rate by +94.25 and has been deployed in production.

Copied to clipboard

Fuyuan Liu, Dianyu Yu, He Ren, Nayu Liu, Xiaomian Kang, Delai Qiu, Fa Zhang, Genpeng Zhen, Shengping Liu, Liang Jiaen, null Weihuang, Yining Wang, Junnan Zhu

Challenge:	Existing methods for document comprehension rely on uniform supervision, resulting in a performance degradation in the intermediate sections.
Approach:	They propose a framework driven by Focal Preference Optimization to detect reading order in document layouts.
Outcome:	The proposed framework outperforms competing baselines and surpasses large-scale general VLMs.

Little Giants: Synthesizing High-Quality Embedding Data at Scale (2025.naacl-long)

Copied to clipboard

Haonan Chen, Liang Wang, Nan Yang, Yutao Zhu, Ziliang Zhao, Furu Wei, Zhicheng Dou

Rationales Are Not Silver Bullets: Measuring the Impact of Rationales on Model Performance and Reliability (2025.findings-acl)

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

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

LLaSE-G1: Incentivizing Generalization Capability for LLaMA-based Speech Enhancement (2025.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

Boyi Kang, Xinfa Zhu, Zihan Zhang, Zhen Ye, Mingshuai Liu, Ziqian Wang, Yike Zhu, Guobin Ma, Jun Chen, Longshuai Xiao, Chao Weng, Wei Xue, Lei Xie

Neural Stylistic Response Generation with Disentangled Latent Variables (2021.acl-long)

Challenge:	Recent advances in language models have demonstrated strong capabilities in semantic understanding and contextual modeling.
Approach:	They propose a LLaMA-based language model that incentivizes generalization capabilities for speech enhancement.
Outcome:	The proposed language model outperforms prior task-specific discriminative and generative models in acoustic enhancement tasks.

Copied to clipboard

Qingfu Zhu, Wei-Nan Zhang, Ting Liu, William Yang Wang

Less Is More: Domain Adaptation with Lottery Ticket for Reading Comprehension (2021.findings-emnlp)

Challenge:	Existing parallel datasets for creating stylistic responses are not stylistically consistent.
Approach:	They propose to disentangle the content and style in latent space by diluting sentence-level information in style representations.
Outcome:	The proposed approach achieves a higher BERT-based style intensity score and comparable BLEU scores, compared with baselines.

Copied to clipboard

Haichao Zhu, Zekun Wang, Heng Zhang, Ming Liu, Sendong Zhao, Bing Qin

KCVR: Knowledge-Centric Video Reconstruction for Structured Pedagogical Summarization via Dynamic Graph Planning (2026.acl-long)

Challenge:	Existing domain adaptation paradigms for reading comprehension require large amounts of annotation data to achieve the desired task performance.
Approach:	They propose a few-shot domain adaptation paradigm for reading comprehension . they introduce self-attention attribution to weigh parameters and refine the lottery subnetwork .
Outcome:	The proposed model outperforms the full model fine-tuning adaptation on four out of five domains with a small amount of data available for adaptation.

Copied to clipboard

Jingjiang Liu, Jia Zhu, Hanghui Guo, Weijie Shi, Yue Cui, Xiaokang Jin, Yilin Wang, Qingyu Niu, Jiawei Shen, Guoqing Ma, Yidan Liang, Shimin Di, Jiajie Xu

Generating Attribution Reports for Manipulated Facial Images: A Dataset and Baseline (2026.acl-long)

Challenge:	Existing summarization methods compress content for gist browsing, but they break prerequisite logic in instructional videos.
Approach:	They propose a framework that decouples epistemic planning from content generation.
Outcome:	The proposed framework outperforms strong end-to-end baselines on Knowledge Progression Consistency and Learning Objective Coverage.

Copied to clipboard

Jingchun Lian, Lingyu Liu, Yaxiong Wang, Yujiao Wu, Lianwei Wu, Li Zhu, Zhedong Zheng

NCLS: Neural Cross-Lingual Summarization (D19-1)

Challenge:	Existing facial forgery detection methods focus on binary classification or pixel-level localization, providing little semantic insight into the nature of the manipulation.
Approach:	They propose a multimodal task that localizes forged regions and generates natural language explanations grounded in editing process.
Outcome:	The proposed task localizes forged regions and generates natural language explanations grounded in editing process.

Copied to clipboard

Junnan Zhu, Qian Wang, Yining Wang, Yu Zhou, Jiajun Zhang, Shaonan Wang, Chengqing Zong

SaCa: A Highly Compatible Reinforcing Framework for Knowledge Graph Embedding via Structural Pattern Contrast (2025.findings-emnlp)

Challenge:	Existing approaches to cross-lingual summarization divide the task into two steps: summarizing and translation.
Approach:	They propose to integrate two related tasks into the training process of CLS under multi-task learning to improve cross-lingual summarization.
Outcome:	The proposed framework improves on English-to-Chinese and Chinese-to English CLS human-corrected test sets.

Copied to clipboard

Jiashi Lin, Changhong Jiang, Yixiao Wang, Xinyi Zhu, Zhongtian Hu, Wei Zhang

QaRL: Rollout-Aligned Quantization-Aware RL for Fast and Stable Training under Training–Inference Mismatch (2026.findings-acl)

Challenge:	Existing knowledge Graph Embedding approaches lack structural semantics of knowledge graphs . structure-aware calibration (SaCa) is a framework designed to calibrate KGEs based on global structural patterns.
Approach:	a new framework is designed to calibrate knowledge graphs using global structural patterns.
Outcome:	a new framework can calibrate KGE models using global structural patterns . the framework consistently boosts performance across ten models on link prediction and entity classification tasks .

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.

DRA-GRPO: Your GRPO Needs to Know Diverse Reasoning Paths for Mathematical Reasoning (2026.findings-acl)

Copied to clipboard

Xiwen Chen, Wenhui Zhu, Peijie Qiu, Xuanzhao Dong, Hao Wang, Haiyu Wu, Huayu Li, Aris Sotiras, Yalin Wang, Abolfazl Razi

Mirror: Multiple-perspective Self-Reflection Method for Knowledge-rich Reasoning (2024.acl-long)

Challenge:	Existing methods for group-relative policy optimization rely on scalar correctness rewards that are often non-injective with respect to semantic content.
Approach:	They propose a framework that calibrates the reward signal using the semantic density of sampled groups.
Outcome:	The proposed framework outperforms strong baselines on five math benchmarks with 7,000 samples and 55 cost.

Copied to clipboard

Hanqi Yan, Qinglin Zhu, Xinyu Wang, Lin Gui, Yulan He

Advancing Parameter Efficiency in Fine-tuning via Representation Editing (2024.acl-long)

Challenge:	Large language models (LLMs) struggle with knowledge-rich problems without external resources.
Approach:	They propose a Multiple-perspective self-reflection method that allows LLMs to reflect from multiple-perceptive clues, achieved through a heuristic interaction between a Navigator and a Reasoner.
Outcome:	The proposed method is superior to other self-reflection methods on five reasoning datasets.

Copied to clipboard

Muling Wu, Wenhao Liu, Xiaohua Wang, Tianlong Li, Changze Lv, Zixuan Ling, Zhu JianHao, Cenyuan Zhang, Xiaoqing Zheng, Xuanjing Huang

ACE-M3: Automatic Capability Evaluator for Multimodal Medical Models (2025.coling-main)

Challenge:	Parameter Efficient Fine-Tuning (PEFT) has gained significant attention for its ability to achieve competitive results while updating only a small subset of trainable parameters.
Approach:	They propose a new approach to fine-tuning neural models that scales and biases the representation produced at each layer.
Outcome:	The proposed approach reduces the number of trainable parameters by a factor of 25,700 compared to full parameter fine-tuning and by . 32 compared with LoRA.

Copied to clipboard

Xiechi Zhang, Shunfan Zheng, Linlin Wang, Gerard de Melo, Zhu Cao, Xiaoling Wang, Liang He

DREAM: Disentangling Risks to Enhance Safety Alignment in Multimodal Large Language Models (2025.naacl-long)

Challenge:	Existing metrics for multimodal large language models only focus on token overlap and may not align with human judgment.
Approach:	They propose an open-source model that assesses the question answering abilities of multimodal large language models.
Outcome:	Experiments show that the ACE-M3 model performs better than existing models and is more reliable than existing metrics.

Copied to clipboard

Jianyu Liu, Hangyu Guo, Ranjie Duan, Xingyuan Bu, Yancheng He, Shilong Li, Hui Huang, Jiaheng Liu, Yucheng Wang, Chenchen Jing, Xingwei Qu, Xiao Zhang, Pei Wang, Yanan Wu, Jihao Gu, Yangguang Li, Jianke Zhu

HSCodeComp: A Realistic and Expert-level Agent Benchmark for Hierarchical Rule Application (2026.acl-long)

Challenge:	Multimodal Large Language Models (MLLMs) pose unique safety challenges due to their integration of visual and textual data.
Approach:	They propose a method to disentangle risks through step-by-step reasoning within multimodal inputs.
Outcome:	The proposed approach improves safety alignment in MLLMs by fine-tuning and iterative Reinforcement Learning from AI feedback.

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

SGDPO: Self-Guided Direct Preference Optimization for Language Model Alignment (2025.findings-acl)

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

Wenqiao Zhu, Ji Liu, Lulu Wang, Jun Wu, Yulun Zhang

SQL-Trail: Multi-Turn Reinforcement Learning with Interleaved Feedback for Text-to-SQL (2026.acl-long)

Challenge:	Existing methods for aligning Large Language Models with human values are limited and results of DPO are not resilient.
Approach:	They propose a self-guided direct preference optimization algorithm that incorporates a pilot term to steer the gradient flow during the optimization process.
Outcome:	The proposed method can generate human-preferred response up to 9.19% higher than previous methods.

Copied to clipboard

Harper Hua, Zhen Han, Zhengyuan Shen, Meng-Chieh Lee, Sheng Guan, Qi Zhu, Sullam Jeoung, Yueyan Chen, Yunfei Bai, Shuai Wang, Vassilis N. Ioannidis, Huzefa Rangwala

FARSS: Fisher-Optimized Adaptive Low-Rank and Singular-Vector Selection for Knowledge-Preserving Fine-Tuning (2026.findings-acl)

Challenge:	Recent large language models (LLMs) have significantly improved Text-to-SQL generation, but a gap remains between AI systems and human experts on challenging benchmarks such as BIRD-Sql.
Approach:	They propose a multi-turn reinforcement learning agentic framework for Text-to-SQL that uses execution feedback to iteratively refine its predictions.
Outcome:	The proposed framework outperforms proprietary systems on 7B and 14B models by **5% on average, underscoring the effectiveness of interactive, agentic workflows for robust Text-to-SQL generation.

Copied to clipboard

Renxing Chen, Ziwei Xiang, Peisong Wang, Hongjian Fang, Meng Li, Fanhu Zeng, Yanan Zhu, Peipei Yang, Xu-Yao Zhang, Jian Cheng

Propagation and Pitfalls: Reasoning-based Assessment of Knowledge Editing through Counterfactual Tasks (2024.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

Wenyue Hua, Jiang Guo, Mingwen Dong, Henghui Zhu, Patrick Ng, Zhiguo Wang

CoRAG: Enhancing Hybrid Retrieval-Augmented Generation through a Cooperative Retriever Architecture (2025.findings-emnlp)

Challenge:	Existing knowledge editing methods struggle to effectively propagate updates to interconnected facts, limiting the performance of reasoning tasks based on these updated facts.
Approach:	They propose a reasoning-based benchmark, ReCoE, which covers six common reasoning schemes in the real world.
Outcome:	The proposed reasoning-based benchmark shows that current models struggle to propagate updated knowledge within reasoning schemes.

Copied to clipboard

Zaiyi Zheng, Song Wang, Zihan Chen, Yaochen Zhu, Yinhan He, Liangjie Hong, Qi Guo, Jundong Li

On the Calibration of Large Language Models and Alignment (2023.findings-emnlp)

Challenge:	Existing methods only retrieve related documents from local neighbors or subgraphs in the knowledge base, which often miss relevant information located further away from a global view.
Approach:	Hybrid-RAG combines textual documents and graph-structured relational information for RAG . existing methods only retrieve related documents from local neighbors or subgraphs in the knowledge base .
Outcome:	Hybrid-RAG combines textual documents and graph-structured relational information . existing methods only retrieve related documents from local neighbors or subgraphs in the knowledge base .

Copied to clipboard

Chiwei Zhu, Benfeng Xu, Quan Wang, Yongdong Zhang, Zhendong Mao

Grammatical Error Correction via Mixed-Grained Weighted Training (2023.findings-emnlp)

Challenge:	Large language models are becoming more popular and are proving to be reliable . however, their reliability is often understudied due to their uncertainty and complex structure .
Approach:	They conduct a systematic examination of the calibration of aligned language models throughout the entire construction process including pretraining and alignment training.
Outcome:	The results shed light on whether popular large language models are well-calibrated and how the training process influences model calibration.

Copied to clipboard

Jiahao Li, Quan Wang, Chiwei Zhu, Zhendong Mao, Yongdong Zhang

Non-Autoregressive Neural Machine Translation with Consistency Regularization Optimized Variational Framework (2022.naacl-main)

Challenge:	Empirical evaluation shows that MainGEC achieves consistent and significant performance improvements on two benchmark datasets.
Approach:	They propose to use mixed-grained weighted training to improve the training effect for GEC by analyzing the inherent discrepancies in annotated training data.
Outcome:	Empirical results show that the proposed method achieves significant performance improvements on two benchmark datasets.

Copied to clipboard

Minghao Zhu, Junli Wang, Chungang Yan

MultiDx: A Multi-Source Knowledge Integration Framework towards Diagnostic Reasoning (2026.findings-acl)

Challenge:	Variational Autoencoder (VAE) is an effective framework to model the interdependency for non-autoregressive neural machine translation (NAT).
Approach:	They propose to use Variational Autoencoder to model interdependency for non-autoregressive neural machine translation (NAT) a posterior consistency regularization approach is proposed to improve translation quality .
Outcome:	The proposed model is 1.5/0.7 and 0.8/0.3 BLEU points faster than the baseline model.

Copied to clipboard

Yimin Deng, Zhenxi Lin, Yejing Wang, Guoshuai Zhao, Pengyue Jia, Zichuan Fu, Derong Xu, Yefeng Zheng, Xiangyu Zhao, Li Zhu, Xian Wu, Xueming Qian

VSCBench: Bridging the Gap in Vision-Language Model Safety Calibration (2025.findings-acl)

Challenge:	Existing approaches focus on diagnostic reasoning based on internal model knowledge or static knowledge bases.
Approach:	They propose a two-stage diagnostic reasoning framework that integrates multi-perspective evidence to generate a diagnostic prediction.
Outcome:	The proposed method generates suspected diagnoses and reasoning traces from web search, SOAP-formatted case, and clinical case database.

Copied to clipboard

Jiahui Geng, Qing Li, Zongxiong Chen, Yuxia Wang, Derui Zhu, Zhuohan Xie, Chenyang Lyu, Xiuying Chen, Preslav Nakov, Fakhri Karray

Development of Community-Oriented Text-to-Speech Models for Māori ‘Avaiki Nui (Cook Islands Māori) (2024.lrec-main)

Challenge:	Existing safety calibration methods focus on model undersafety, where the model responds to hazardous queries, while neglecting oversafetiness, where models refuse to answer safe queries.
Approach:	They propose safety calibration which addresses both undersafety and oversafetiness by comparing model responses to a novel dataset of 3,600 image-text pairs.
Outcome:	The proposed methods have been used to evaluate safety calibration across image-centric and text-centric scenarios.

Copied to clipboard

Jesin James, Rolando Coto-Solano, Sally Akevai Nicholas, Joshua Zhu, Bovey Yu, Fuki Babasaki, Jenny Tyler Wang, Nicholas Derby

IAPT: Instance-Aware Prompt Tuning for Large Language Models (2024.acl-long)

Challenge:	Text-to-speech synthesis is used to transform text into a synthesized voice for a specific language.
Approach:	They describe the development of a text-to-speech system for Mori ‘Avaiki Nui (Cook Islands Mi) they used two approaches to train the system, the HMM-system MaryTTS and the deep learning system FastSpeech2 .
Outcome:	The proposed system is based on the HMM-system MaryTTS and the deep learning system FastSpeech2 . the ground truth voice had the highest quality, but the fastspeech 2 voice had a significantly higher quality than the MaryTTs synthesized recordings.

Copied to clipboard

Wei Zhu, Aaron Tian, Congrui Yin, Yuan Ni, Xiaoling Wang, Guotong Xie

Link Prediction on N-ary Relational Facts: A Graph-based Approach (2021.findings-acl)

Challenge:	Existing methods for prompt tuning require many soft tokens to guarantee performance . large language models still require a large amount of GPU memory and computations to fine-tune .
Approach:	They propose to use a parameter-efficient soft prompt generator to generate idiosyncratic soft prompts for each input instruction.
Outcome:	The proposed method outperforms the baselines with comparable tunable parameters and is more efficient than LoRA under the single-backbone multi-tenant setting.

Copied to clipboard

Quan Wang, Haifeng Wang, Yajuan Lyu, Yong Zhu

HD-NDEs: Neural Differential Equations for Hallucination Detection in LLMs (2025.acl-long)

Challenge:	Existing work on knowledge graphs (KGs) focused on binary relations, but higher-arity relations are ubiquitous in real-world KGs.
Approach:	They propose a graph-based approach to link prediction on knowledge graphs using n-ary relational facts and edge-biased fully-connected attention.
Outcome:	The proposed approach performs substantially better than current state-of-the-art across a variety of n-ary relational benchmarks.

Copied to clipboard

Qing Li, Jiahui Geng, Zongxiong Chen, Derui Zhu, Yuxia Wang, Congbo Ma, Chenyang Lyu, Fakhri Karray

Improving Factual Consistency of Abstractive Summarization via Question Answering (2021.acl-long)

Challenge:	Hallucination is a significant challenge for large language models, but current methods struggle when non-factual information arises in the early or mid-sequence of outputs, reducing their reliability.
Approach:	They propose a method that captures the full dynamics of large language models by using neural differential equations to assess the truthfulness of statements.
Outcome:	The proposed method achieves 14% improvement in AUC-ROC on the True-False dataset compared to state-of-the-art methods.

Copied to clipboard

Feng Nan, Cicero Nogueira dos Santos, Henghui Zhu, Patrick Ng, Kathleen McKeown, Ramesh Nallapati, Dejiao Zhang, Zhiguo Wang, Andrew O. Arnold, Bing Xiang

Summarization

Challenge:	Recent studies show that about 30% of summaries generated by neural text summarization suffer from fact fabrication.
Approach:	They propose an automatic evaluation metric to measure factual consistency and a learning algorithm that maximizes the metric during model training.
Outcome:	The proposed method improves factual consistency and overall quality of summarization models.

Multimodal Joint Attribute Prediction and Value Extraction for E-commerce Product (2020.emnlp-main)

Copied to clipboard

Tiangang Zhu, Yue Wang, Haoran Li, Youzheng Wu, Xiaodong He, Bowen Zhou

Shallow-to-Deep Training for Neural Machine Translation (2020.emnlp-main)

Challenge:	In the real world, product attribute values are incomplete and vary over time, which hinders practical applications.
Approach:	They propose a multimodal method to jointly predict product attributes and extract values from product images using multimodal product information.
Outcome:	The proposed method can predict product attributes and extract values from product images with the help of product images.

Copied to clipboard

Bei Li, Ziyang Wang, Hui Liu, Yufan Jiang, Quan Du, Tong Xiao, Huizhen Wang, Jingbo Zhu

AdaPrompt: Adaptive Model Training for Prompt-based NLP (2022.findings-emnlp)

Challenge:	Experimental results show that deep training is 1:4 faster than training from scratch.
Approach:	They propose a shallow-to-deep training method that learns deep models by stacking shallow models.
Outcome:	The proposed method is 1:4 faster than training from scratch and achieves BLEU scores of 30:33 and 43:29 on two translation tasks.

Copied to clipboard

Yulong Chen, Yang Liu, Li Dong, Shuohang Wang, Chenguang Zhu, Michael Zeng, Yue Zhang

An Iterative Associative Memory Model for Empathetic Response Generation (2024.acl-long)

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

Zhou Yang, Zhaochun Ren, Wang Yufeng, Haizhou Sun, Chao Chen, Xiaofei Zhu, Xiangwen Liao

SCA: Selective Compression Attention for Efficiently Extending the Context Window of Large Language Models (2024.findings-emnlp)

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

Huanran Zheng, Wei Zhu, Xiaoling Wang

TurnBench-MS: A Benchmark for Evaluating Multi-Turn, Multi-Step Reasoning in Large Language Models (2025.findings-emnlp)

Challenge:	Existing methods to compress the KV cache of large language models are expensive and limited in their context window and cost.
Approach:	They propose a method to expand the context window and reduce memory footprint by compressing the KV cache of large language models.
Outcome:	The proposed method can reduce memory footprint and expand context window of large language models without training.

Copied to clipboard

Yiran Zhang, Mo Wang, Xiaoyang Li, Kaixuan Ren, Chencheng Zhu, Usman Naseem

Small Models are Valuable Plug-ins for Large Language Models (2024.findings-acl)

Challenge:	Existing benchmarks focus on single-turn or single-step tasks, failing to capture iterative reasoning in real-world settings.
Approach:	They propose a benchmark that evaluates multi-turn, multi-step reasoning through an interactive code-breaking task inspired by the "Turing Machine Board Game" the best model achieves 84% accuracy in Classic mode, but performance drops to 18% in Nightmare mode.
Outcome:	The new benchmark evaluates multi-turn, multi-step reasoning through an interactive code-breaking task inspired by the "Turing Machine Board Game" the best model achieves 84% accuracy in Classic mode, but performance drops to 18% in Nightmare mode.

Copied to clipboard

Canwen Xu, Yichong Xu, Shuohang Wang, Yang Liu, Chenguang Zhu, Julian McAuley

PRACTIQ: A Practical Conversational Text-to-SQL dataset with Ambiguous and Unanswerable Queries (2025.naacl-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

Mingwen Dong, Nischal Ashok Kumar, Yiqun Hu, Anuj Chauhan, Chung-Wei Hang, Shuaichen Chang, Lin Pan, Wuwei Lan, Henghui Zhu, Jiarong Jiang, Patrick Ng, Zhiguo Wang

MR-ALIGN: Meta-Reasoning Informed Factuality Alignment for Large Reasoning Models (2026.findings-acl)

Challenge:	Existing text-to-SQL systems focus on user questions with clear intentions that can be answered, but real user questions can be ambiguous with multiple interpretations or unanswerable due to a lack of relevant data.
Approach:	They construct a conversational text-to-SQL dataset called PRACTIQ, consisting of ambiguous and unanswerable questions inspired by real-world user questions.
Outcome:	The proposed system generates conversations with four turns, generating the user’s question, an assistant response seeking clarification, and the user's clarified SQL response with the natural language explanation of the execution results.

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

ChartMind: A Comprehensive Benchmark for Complex Real-world Multimodal Chart Question Answering (2025.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

Jingxuan Wei, Nan Xu, Junnan Zhu, null Haoyanni, Gaowei Wu, Qi Chen, Bihui Yu, Lei Wang

OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models (2025.acl-long)

Challenge:	Chart question answering (CQA) is a multimodal task for evaluating the reasoning capabilities of vision-language models.
Approach:	They propose a chart question answering benchmark that incorporates multilingual contexts and supports open-domain textual outputs.
Outcome:	The proposed framework outperforms the previous three common CQA paradigms: instruction-following, OCR-enhanced, and chain-of-thought.

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

Co2PT: Mitigating Bias in Pre-trained Language Models through Counterfactual Contrastive Prompt Tuning (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

Xiangjue Dong, Ziwei Zhu, Zhuoer Wang, Maria Teleki, James Caverlee

Visualize Before You Write: Imagination-Guided Open-Ended Text Generation (2023.findings-eacl)

Challenge:	Pre-trained language models can encode unfair social biases from large pre-training corpora and even amplify biase in downstream applications.
Approach:	They propose a debias-while-prompt tuning method for mitigating biases via counterfactual contrastive prompt tuning on downstream tasks.
Outcome:	The proposed method can mitigate biases on three extrinsic bias benchmarks and adapt to existing debiased language models.

Copied to clipboard

Wanrong Zhu, An Yan, Yujie Lu, Wenda Xu, Xin Wang, Miguel Eckstein, William Yang Wang

Generalized Category Discovery with Large Language Models in the Loop (2024.findings-acl)

Challenge:	Existing tools for text-to-image synthesis can visualize machine imaginations for a given context.
Approach:	They propose a framework that uses machine-generated images to guide language models in open-ended text generation.
Outcome:	The proposed framework is effective on open-ended text generation tasks while showing minor degeneration.

Copied to clipboard

Wenbin An, Wenkai Shi, Feng Tian, Haonan Lin, QianYing Wang, Yaqiang Wu, Mingxiang Cai, Luyan Wang, Yan Chen, Haiping Zhu, Ping Chen

KoCo-Bench: Can Large Language Models Leverage Domain Knowledge in Software Development? (2026.acl-long)

Challenge:	Generalized Category Discovery (GCD) is a crucial task that aims to recognize both known and novel categories from a set of unlabeled data.
Approach:	They propose a framework that introduces Large Language Models into the training loop to generate category names without human effort.
Outcome:	The proposed framework outperforms SOTA models on three benchmark datasets and generates accurate category names for the discovered clusters.

Copied to clipboard

Xue Jiang, Ge Li, Jiaru Qian, Xianjie Shi, Chenjie Li, Hao Zhu, Ziyu Wang, Jielun Zhang, Zeyu Zhao, Kechi Zhang, Jia Li, Wenpin Jiao, Zhi Jin, Yihong Dong

From Traits to Empathy: Personality-Aware Multimodal Empathetic Response Generation (2025.coling-main)

Challenge:	Existing domain-specific code benchmarks focus on assessing what knowledge LLMs possess rather than how they acquire and apply new knowledge.
Approach:	They propose a benchmark to evaluate domain specialization methods in real-world software development.
Outcome:	KOCO-bench is a new benchmark for evaluating domain specialization methods in real-world software development.

Copied to clipboard

Jiaqiang Wu, Xuandong Huang, Zhouan Zhu, Shangfei Wang

HeteroRAG: A Heterogeneous Retrieval-Augmented Generation Framework for Medical Vision Language Tasks (2026.findings-acl)

Challenge:	Existing approaches focus on acquiring affective and cognitive knowledge from text, but neglect the unique personality traits of individuals and the inherently multimodal nature of human face-to-face conversation.
Approach:	They propose a multimodal dialogue system that generates empathetic responses from a perspective that considers the personality traits of users.
Outcome:	The proposed system generates empathetic responses from a multimodal perspective and analyzes multimodal data to understand the user’s emotional state and situation.

Copied to clipboard

Zhe Chen, Yusheng Liao, Zhiyuan Zhu, Haolin Li, Hongcheng Liu, Yanfeng Wang, Yu Wang

AceGPT, Localizing Large Language Models in Arabic (2024.naacl-long)

Challenge:	Medical large vision-language models suffer from factual inaccuracies and unreliable outputs.
Approach:	They propose a framework that enhances Med-LVLMs through heterogeneous knowledge sources.
Outcome:	The proposed framework improves Med-LVLMs through heterogeneous knowledge sources.

Copied to clipboard

Huang Huang, Fei Yu, Jianqing Zhu, Xuening Sun, Hao Cheng, Song Dingjie, Zhihong Chen, Mosen Alharthi, Bang An, Juncai He, Ziche Liu, Junying Chen, Jianquan Li, Benyou Wang, Lian Zhang, Ruoyu Sun, Xiang Wan, Haizhou Li, Jinchao Xu

Theorem-Validated Reverse Chain-of-Thought Problem Generation for Geometric Reasoning (2025.emnlp-main)

Challenge:	Significant concerns emerge when addressing cultural sensitivity and local values.
Approach:	They propose a localized Large Language Model (LLM) specifically for Arabic, a language imbued with unique cultural characteristics inadequately addressed by current mainstream models.
Outcome:	The proposed model sets the state-of-the-art standard for open Arabic LLMs across various benchmarks.

Copied to clipboard

Deng Linger, Linghao Zhu, Yuliang Liu, Yu Wang, Qunyi Xie, Jingjing Wu, Gang Zhang, Yingying Zhu, Xiang Bai

InternLM-Law: An Open-Sourced Chinese Legal Large Language Model (2025.coling-main)

Challenge:	Existing methods for generating geometric reasoning data through Chain-of-Thought (CoT) frameworks face three fundamental limitations: 1) lack of high-quality annotations and domain-specific expertise to ensure theorem-grounded diagrams. 2) lack of a coherent model; 3) lack of coherent model.
Approach:	They propose a two-stage Theorem-Validated Reverse Chain-of-Thought Reasoning Synthesis framework that synthesizes theorematic diagrams with structured descriptions and properties.
Outcome:	The proposed framework expands theorem-type coverage, corrects misunderstandings, and enhances geometric reasoning.

Copied to clipboard

Zhiwei Fei, Songyang Zhang, Xiaoyu Shen, Dawei Zhu, Xiao Wang, Jidong Ge, Vincent Ng

DuQM: A Chinese Dataset of Linguistically Perturbed Natural Questions for Evaluating the Robustness of Question Matching Models (2022.emnlp-main)

Challenge:	InternLM-Law is a large language model (LLM) tailored for addressing diverse legal tasks related to Chinese laws.
Approach:	They introduce a large language model (LLM) tailored for addressing diverse legal tasks related to Chinese laws.
Outcome:	The proposed model performs better than existing models in a variety of legal tasks related to Chinese laws.

Copied to clipboard

Hongyu Zhu, Yan Chen, Jing Yan, Jing Liu, Yu Hong, Ying Chen, Hua Wu, Haifeng Wang

SportQA: A Benchmark for Sports Understanding in Large Language Models (2024.naacl-long)

Challenge:	a comprehensive evaluation of QM models should be conducted on natural texts, not on artificial adversarial examples . ral models are often not robust to adversarials, which means they predict unexpected outputs .
Approach:	They use a Chinese dataset to evaluate the robustness of QM models . they show that the effect of artificial adversarial examples does not work on natural texts .
Outcome:	The proposed model is more robust than other models on natural questions with 32 linguistic perturbations.

Copied to clipboard

Haotian Xia, Zhengbang Yang, Yuqing Wang, Rhys Tracy, Yun Zhao, Dongdong Huang, Zezhi Chen, Yan Zhu, Yuan-fang Wang, Weining Shen

A Hybrid Model of Classification and Generation for Spatial Relation Extraction (2022.coling-1)

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

Feng Wang, Peifeng Li, Qiaoming Zhu

Revisiting Cross-Lingual Summarization: A Corpus-based Study and A New Benchmark with Improved Annotation (2023.acl-long)

Challenge:	Existing studies only focus on spatial relations extraction as a classification task . spatial information is one kind of critical information for natural language understanding .
Approach:	They propose a hybrid model that generates null-role relations and extracts non-null-rol . they propose varying kinds of schemes to represent spatial relation .
Outcome:	The proposed model outperforms the baselines on the spatial relation extraction task on SpaceEval.

Copied to clipboard

Yulong Chen, Huajian Zhang, Yijie Zhou, Xuefeng Bai, Yueguan Wang, Ming Zhong, Jianhao Yan, Yafu Li, Judy Li, Xianchao Zhu, Yue Zhang

Exploring Hybrid Question Answering via Program-based Prompting (2024.acl-long)

Challenge:	Existing work on cross-lingual summarization (CLS) does not consider crosslingual sources for summarizing.
Approach:	They propose a cross-lingual conversation summarization benchmark that explicitly considers source context.
Outcome:	The proposed method surpasses baselines on ConvSumX and 3 widely-used manual annotations.

Copied to clipboard

Qi Shi, Han Cui, Haofeng Wang, Qingfu Zhu, Wanxiang Che, Ting Liu

Neural Hidden Markov Model for Machine Translation (P18-2)

Challenge:	Existing approaches to question answering over heterogeneous data are limited due to large scale of information and organic coupling of heterogenous data.
Approach:	They propose a program-based prompting framework for hybrid question answering tasks . it integrates various functions to perform hybrid information-seeking over data .
Outcome:	The proposed framework surpasses baseline systems and achieves the best performance under the fewshot settings.

Copied to clipboard

Weiyue Wang, Derui Zhu, Tamer Alkhouli, Zixuan Gan, Hermann Ney

Efficient End-to-End Visual Document Understanding with Rationale Distillation (2024.naacl-long)

Challenge:	Attention-based neural machine translation models selectively focus on specific source positions to produce a translation.
Approach:	They propose to replace the attention component with a neural hidden Markov model that selectively focuss on specific source positions to produce a translation.
Outcome:	The proposed model performs better than the state-of-the-art attention-based models on the GermanEnglish and ChineseEnglish translation tasks.

Copied to clipboard

Wang Zhu, Alekh Agarwal, Mandar Joshi, Robin Jia, Jesse Thomason, Kristina Toutanova

RedCoast: A Lightweight Tool to Automate Distributed Training of LLMs on Any GPU/TPUs (2024.naacl-demo)

Challenge:	Pre-processing tools such as optical character recognition (OCR) can map document image inputs to textual tokens, then large language models (LLMs) can reason over text.
Approach:	They propose a method that integrates outputs of OCR tools and larger multimodal models as intermediate "rationales" a student model is trained to predict rationales and answers based on visual documents .
Outcome:	The proposed model outperforms the base model on three visual document understanding benchmarks with only 1% higher computational cost.

Copied to clipboard

Bowen Tan, Yun Zhu, Lijuan Liu, Hongyi Wang, Yonghao Zhuang, Jindong Chen, Eric Xing, Zhiting Hu

Think Twice Before Trusting: Self-Detection for Large Language Models through Comprehensive Answer Reflection (2024.findings-emnlp)

Challenge:	Recent advances in machine learning (ML) are attributed to large language models (LLMs), but their escalating memory requirements require developers to partition a large model to distribute it across multiple GPUs or TPUs.
Approach:	They propose a lightweight and user-friendly tool to automate distributed training and inference for LLMs and to simplify ML pipeline development.
Outcome:	The proposed tool automates distributed training and inference for LLMs, and simplifies ML pipeline development.

Copied to clipboard

Moxin Li, Wenjie Wang, Fuli Feng, Fengbin Zhu, Qifan Wang, Tat-Seng Chua

Taming Language Models for Text-attributed Graph Learning with Decoupled Aggregation (2025.acl-long)

Challenge:	Existing approaches to self-detection only retrospectively evaluate LLM-generated answers, leading to over-trust in incorrectly generated answers.
Approach:	They propose a self-detection paradigm that considers the comprehensive answer space beyond LLM-generated answers to mitigate the over-trust in LLM generated incorrect answers.
Outcome:	The proposed framework can be integrated with existing approaches for superior self-detection.

Copied to clipboard

Chuang Zhou, Zhu Wang, Shengyuan Chen, Jiahe Du, Qiyuan Zheng, Zhaozhuo Xu, Xiao Huang

Maximal Clique Based Non-Autoregressive Open Information Extraction (2021.emnlp-main)

Challenge:	Existing approaches to learning text-attributed graphs neglect interaction between textual and structural information.
Approach:	They propose a framework that integrates textual and structural information into TAG learning . they propose combining semantic aggregation and structural aggregations to improve learning a .
Outcome:	The proposed framework outperforms state-of-the-art learning methods while requiring less resources.

Copied to clipboard

Bowen Yu, Yucheng Wang, Tingwen Liu, Hongsong Zhu, Limin Sun, Bin Wang

Tag-Evol: Achieving Efficient Instruction Evolving via Tag Injection (2025.findings-acl)

Challenge:	Open Information Extraction (OpenIE) aims to discover textual facts from a given sentence.
Approach:	They propose a non-autoregressive framework that generates a fact graph and a graph with an edge linking two nodes that belong to the same fact.
Outcome:	The proposed framework outperforms current state-of-the-art methods on two benchmark datasets and significantly outperformed the existing ones.

Copied to clipboard

Yixuan Wang, Shiqi Zhou, Chuanzhe Guo, Qingfu Zhu

An Effective and Efficient Entity Alignment Decoding Algorithm via Third-Order Tensor Isomorphism (2022.acl-long)

Challenge:	Existing methods rely on a fixed set of strategies to evolve, which requires manual design and is monolithic in form.
Approach:	They propose a method that uses diverse and specific knowledge tags to achieve controlled evolution by injecting different combinations of tags into original instructions.
Outcome:	The proposed method generates better evolved data than existing methods and is more diverse and challenging.

Copied to clipboard

Xin Mao, Meirong Ma, Hao Yuan, Jianchao Zhu, ZongYu Wang, Rui Xie, Wei Wu, Man Lan

ComRAG: Retrieval-Augmented Generation with Dynamic Vector Stores for Real-time Community Question Answering in Industry (2025.acl-industry)

Challenge:	Existing methods focus on graph representation learning, but decoding is a key part of the process.
Approach:	They propose an EA Decoding Algorithm via Third-order Tensor Isomorphism (DATTI) they combine two sets of isomorphic equations to enhance the decoding process .
Outcome:	The proposed algorithm can deliver significant performance improvements even on the most advanced methods while the extra required time is less than 3 seconds.

Copied to clipboard

Qinwen Chen, Wenbiao Tao, Zhiwei Zhu, Mingfan Xi, Liangzhong Guo, Yuan Wang, Wei Wang, Yunshi Lan

Cracking the Code of Hallucination in LVLMs with Vision-aware Head Divergence (2025.acl-long)

Challenge:	Existing methods for Community Question Answering (CQA) focus on static knowledge, limiting their applicability to real-world scenarios.
Approach:	They propose a retrieval-augmented generation framework for real-time industrial CQA that integrates static knowledge with dynamic historical QA pairs via a centroid-based memory mechanism.
Outcome:	The proposed framework outperforms baselines on three industrial CQA datasets and achieves 25.9% improvement in vector similarity, reducing latency by 8.7%–23.3%, and lowering chunk growth from 20.23% to 2.06% over iterations.

Copied to clipboard

Jinghan He, Kuan Zhu, Haiyun Guo, Junfeng Fang, Zhenglin Hua, Yuheng Jia, Ming Tang, Tat-Seng Chua, Jinqiao Wang

WenetSpeech-Wu: Datasets, Benchmarks, and Models for a Unified Chinese Wu Dialect Speech Processing Ecosystem (2026.findings-acl)

Challenge:	Existing methods focus on alignment training or decoding refinements but address symptoms at the generation stage without probing the underlying causes.
Approach:	They propose a training-free approach to mitigate hallucination by enhancing the role of vision-aware attention heads.
Outcome:	The proposed method achieves superior performance compared to state-of-the-art approaches in mitigating hallucinations while maintaining high efficiency with negligible additional time overhead.

Copied to clipboard

Chengyou Wang, Mingchen Shao, Jingbin Hu, Zeyu Zhu, Hongfei Xue, Bingshen Mu, Xin Xu, Xingyi Duan, Binbin Zhang, Zhu Pengcheng, Chuang Ding, Xiaojun Zhang, Hui Bu, Lei Xie

InheritSumm: A General, Versatile and Compact Summarizer by Distilling from GPT (2023.findings-emnlp)

Challenge:	despite its linguistic significance, the Wu dialect of Chinese has long been hindered by the lack of large-scale speech data, standardized evaluation benchmarks, and publicly available models.
Approach:	They propose to use WenetSpeech-Wu as a large-scale, multi-dimensionally annotated open-source speech corpus for the Wu dialect of Chinese.
Outcome:	The proposed dataset includes 8,000 hours of speech data and strong open-source models . the proposed dataset is competitive and empirically validated .

Copied to clipboard

Yichong Xu, Ruochen Xu, Dan Iter, Yang Liu, Shuohang Wang, Chenguang Zhu, Michael Zeng

Cognitive Policy-Driven LLM for Diagnosis and Intervention of Cognitive Distortions in Emotional Support Conversation (2026.acl-long)

Challenge:	Recent advances in large language models have revolutionized the way summarization is generated.
Approach:	They propose a summarization model derived from GPT-3.5 through distillation that is compact and has comparable summarizing capabilities to GPT-3.
Outcome:	The proposed model outperforms the established best small models in prefix-tuning and full-data fine-tuned scenarios.

Copied to clipboard

Lin Zhong, Renjin Zhu, Shujuan Ma, Jinhao Cui, Lingzhi Wang, Hao Chen, Qing Liao

Inventive Problem Solving with LLMs: A Benchmark for TRIZ Reasoning (2026.findings-acl)

Challenge:	Existing models for ESC ignore cognitive distortions in help-seekers' expressions . current models provide basic emotional comfort, rather than helping help- seekers address psychological distress at a deeper cognitive level.
Approach:	They propose a Large Language Model framework to enhance LLMs' ability to diagnose and intervene cognitive distortions in help-seekers.
Outcome:	The proposed framework outperforms 15 state-of-the-art baselines in terms of distortion diagnosis accuracy, intervention strategy effectiveness, and safety risk control.

Copied to clipboard

Zhu Wang, Brian Uzzi

HAT: Hardware-Aware Transformers for Efficient Natural Language Processing (2020.acl-main)

Challenge:	Large language models are increasingly used in inventive problem-solving but effective support requires more than open-ended idea generation.
Approach:	They propose a dataset and benchmark for TRIZ reasoning grounded in open technical sources and U.S. patents.
Outcome:	The proposed framework represents trade-offs and links them to standardized inventive principles.

Copied to clipboard

Hanrui Wang, Zhanghao Wu, Zhijian Liu, Han Cai, Ligeng Zhu, Chuang Gan, Song Han

RichRAG: Crafting Rich Responses for Multi-faceted Queries in Retrieval-Augmented Generation (2025.coling-main)

Challenge:	Extensive experiments on four machine translation tasks demonstrate that HAT can discover efficient models for different hardware (CPU, GPU, IoT device).
Approach:	They propose to construct a large design space with arbitrary encoder-decoder attention and heterogeneous layers and then train a SuperTransformer that efficiently produces many SubTransformers with weight sharing.
Outcome:	The proposed framework can find efficient models for different hardware (CPU, GPU, IoT device) it achieves 3 speedup, 3.7 smaller size over baseline Transformer; 2.7 speed up, 3.6 smaller sizes over Evolved Transformer with 12,041 less search cost and no performance loss.

Copied to clipboard

Shuting Wang, Xin Yu, Mang Wang, Weipeng Chen, Yutao Zhu, Zhicheng Dou

Embracing Imperfection: Simulating Students with Diverse Cognitive Levels Using LLM-based Agents (2025.acl-long)

Challenge:	Existing studies focus on question scenarios with clear user intents and concise answers, but it is prevalent that users issue broad, open-ended queries with diverse sub-intents.
Approach:	They propose a framework that includes a sub-aspect explorer and a multi-faceted retriever to build a candidate pool of diverse external documents related to these sub-intents.
Outcome:	The proposed framework provides comprehensive and satisfying responses to users on two publicly available datasets.

Copied to clipboard

Tao Wu, Jingyuan Chen, Wang Lin, Mengze Li, Yumeng Zhu, Ang Li, Kun Kuang, Fei Wu

Challenge:	Large language models (LLMs) are becoming increasingly popular in education, enabling researchers to simulate students' learning patterns and learning patterns.
Approach:	They propose a training-free framework for student simulation that takes into account student cognitive diversity and realism.
Outcome:	The proposed model outperforms baseline models and achieves 100% improvement in simulation accuracy and realism.

3DRP-Net: 3D Relative Position-aware Network for 3D Visual Grounding (2023.emnlp-main)

Copied to clipboard

Zehan Wang, Haifeng Huang, Yang Zhao, Linjun Li, Xize Cheng, Yichen Zhu, Aoxiong Yin, Zhou Zhao

Chain-of-Rewrite: Aligning Question and Documents for Open-Domain Question Answering (2024.findings-emnlp)

Challenge:	3D visual grounding aims to localize the desired objects in a 3D point cloud by a free-form language description.
Approach:	They propose a relation-aware framework which captures relative spatial relationships between objects and enhances object attributes.
Outcome:	The proposed framework outperforms state-of-the-art methods on three benchmarks . it captures relative spatial relationships between objects and enhances object attributes .

Copied to clipboard

Chunlei Xin, Yaojie Lu, Hongyu Lin, Shuheng Zhou, Huijia Zhu, Weiqiang Wang, Zhongyi Liu, Xianpei Han, Le Sun

Solving Math Word Problems via Cooperative Reasoning induced Language Models (2023.acl-long)

Challenge:	Existing approaches to answer open-domain question have encountered term mismatch and limited interaction between IR systems and large language models.
Approach:	They propose a method which leverages the guidance and feedback gained from the analysis to provide faithful and consistent extensions for effective question answering.
Outcome:	Experiments on four open-domain question answering datasets show the proposed method performs well under zero-shot settings.

Copied to clipboard

Xinyu Zhu, Junjie Wang, Lin Zhang, Yuxiang Zhang, Yongfeng Huang, Ruyi Gan, Jiaxing Zhang, Yujiu Yang

Candidate Soups: Fusing Candidate Results Improves Translation Quality for Non-Autoregressive Translation (2022.emnlp-main)

Challenge:	Large-scale pre-trained language models (PLMs) can be used to solve math word problems, but they lack fast adaptivity as humans.
Approach:	They propose a cooperative reasoning-induced PLM for solving the math word problem . they use system 1 as the generator and system 2 as the verifier to generate reasoning paths .
Outcome:	The proposed model improves on several mathematical reasoning datasets and achieves 9.6% improvement over baselines.

Copied to clipboard

Huanran Zheng, Wei Zhu, Pengfei Wang, Xiaoling Wang

HydraRAG: Structured Cross-Source Enhanced Large Language Model Reasoning (2025.emnlp-main)

Challenge:	Existing methods to improve NAT model's performance but do not fully utilize it.
Approach:	They propose a non-autoregressive translation method which can obtain high-quality translations while maintaining the inference speed of NAT models.
Outcome:	The proposed method outperforms the autoregressive translation model on three translation tasks with 7.6 speedup.

Copied to clipboard

Xingyu Tan, Xiaoyang Wang, Qing Liu, Xiwei Xu, Xin Yuan, Liming Zhu, Wenjie Zhang

LLMs + Persona-Plug = Personalized LLMs (2025.acl-long)

Challenge:	Current RAG system retrieves evidence from knowledge graphs and text documents but has limitations in multi-hop reasoning, multi-entity questions, and source verification.
Approach:	They propose a training-free framework that unifies graph topology, document semantics, and source reliability to support deep, faithful reasoning in large language models.
Outcome:	The proposed framework outperforms the current hybrid model-based model-driven system by 20.3% and 30.1% on seven benchmark datasets.

Copied to clipboard

Jiongnan Liu, Yutao Zhu, Shuting Wang, Xiaochi Wei, Erxue Min, Yu Lu, Shuaiqiang Wang, Dawei Yin, Zhicheng Dou

Retrieval-Augmented Process Reward Model for Generalizable Mathematical Reasoning (2025.findings-acl)

Challenge:	Large language models (LLMs) have demonstrated extraordinary capabilities in natural language understanding, generation, and reasoning.
Approach:	They propose a plug-and-play LLM model that embeds a user-specific embedding for each individual by modeling her historical contexts through a lightweight plug-in user embedder module.
Outcome:	Experiments on various tasks in the language model personalization (LaMP) benchmark show that the proposed model significantly outperforms existing personalized LLM approaches.

Copied to clipboard

Jiachen Zhu, Congmin Zheng, Jianghao Lin, Kounianhua Du, Ying Wen, Yong Yu, Jun Wang, Weinan Zhang

mmE5: Improving Multimodal Multilingual Embeddings via High-quality Synthetic Data (2025.findings-acl)

Challenge:	Large language models (LLMs) have advanced mathematical reasoning, but they still struggle with out-of-distribution (OOD) issues.
Approach:	They propose a framework to evaluate the logical validity of reasoning steps . they retrieves semantically similar questions and steps for PRM as a warmup .
Outcome:	The proposed framework outperforms baseline models on multiple real-world datasets.

Copied to clipboard

Haonan Chen, Liang Wang, Nan Yang, Yutao Zhu, Ziliang Zhao, Furu Wei, Zhicheng Dou

TableEval: A Real-World Benchmark for Complex, Multilingual, and Multi-Structured Table Question Answering (2025.emnlp-main)

Challenge:	Multimodal embedding models encode multimedia inputs into latent vector representations.
Approach:	They propose to synthesize multimodal multilingual data using a multimodal large language model . they identify three criteria for high-quality synthetic multimodal data .
Outcome:	The proposed model outperforms existing models on the MMEB Benchmark and the XTD benchmark.

Copied to clipboard

Junnan Zhu, Jingyi Wang, Bohan Yu, Xiaoyu Wu, Junbo Li, Lei Wang, Nan Xu

CoreCodeBench: Decoupling Code Intelligence via Fine-Grained Repository-Level Tasks (2026.acl-long)

Challenge:	Existing TableQA benchmarks focus on simple flat tables and suffer from data leakage . current benchmarks are monolingual and fail to capture cross-lingual variability .
Approach:	They propose a table-based TableQA benchmark to evaluate LLMs on real-world tasks.
Outcome:	The proposed benchmarks show that they achieve high agreement with human judgment . the proposed framework improves on the alignment between model responses and reference answers .

Copied to clipboard

Lingyue Fu, Hao Guan, Bolun Zhang, Haowei Yuan, Yaoming Zhu, Lin Qiu, ZongYu Wang, Xuezhi Cao, Xunliang Cai, Weiwen Liu, Weinan Zhang, Yong Yu

Challenge:	Existing large language models for software engineering rely on coarse-grained pass rates obscuring specific cognitive bottlenecks.
Approach:	They propose a repository-level benchmark that dissects coding capabilities through atomized tasks.
Outcome:	The proposed framework achieves a 78.55% validity yield, surpassing the 31.7% retention rate of SWE-bench-Verified.

LMGQS: A Large-scale Dataset for Query-focused Summarization (2023.findings-emnlp)

Copied to clipboard

Ruochen Xu, Song Wang, Yang Liu, Shuohang Wang, Yichong Xu, Dan Iter, Pengcheng He, Chenguang Zhu, Michael Zeng

Summarization

Challenge:	Lack of large-scale datasets for query-focused summarization hinders model development . lack of data limits the ability of QFS models to train robust neural models .
Approach:	They propose to generate a query for each summary sentence in a generic summarization annotation using a pretrained language model.
Outcome:	The proposed model achieves state-of-the-art zero-shot and supervised performance on multiple existing QFS benchmarks.

Faster and Better LLMs via Latency-Aware Test-Time Scaling (2025.findings-emnlp)

Copied to clipboard

Zili Wang, Tianyu Zhang, Haoli Bai, Lu Hou, Xianzhi Yu, Wulong Liu, Shiming Xiang, Lei Zhu

Challenge:	Existing research has overlooked the efficiency of TTS from a latency-sensitive perspective.
Approach:	They propose two approaches to achieve latency-optimal TTS by branch-wise parallelism and sequence-wise parallelism.
Outcome:	The proposed approach achieves latency-optimal TTS for large models . branch-wise parallelism and sequence-wise parallelism are key approaches .

DesignCLIP: Multimodal Learning with CLIP for Design Patent Understanding (2025.findings-emnlp)

Copied to clipboard

Zhu Wang, Homaira Huda Shomee, Sathya N. Ravi, Sourav Medya

VulAgent: Hypothesis-Validation Driven Multi-Agent Architecture for Vulnerability Detection (2026.findings-acl)

Challenge:	patent images often lack comprehensive visual context and semantic information, authors say . recent advances in vision-language models offer promising opportunities for patent analysis .
Approach:	They develop a framework for design patent analysis using large-scale patent dataset . they validate the effectiveness of DesignCLIP across various downstream tasks .
Outcome:	The proposed framework outperforms baseline and SOTA models on all tasks.

Copied to clipboard

Ziliang Wang, Ge Li, Jia Li, Hao Zhu, Zhi Jin

Challenge:	Recent reports indicate that software vulnerabilities caused by insecure coding practices remain a major security threat.
Approach:	They propose a multi-agent vulnerability detection framework based on hypothesis validation . they use multi-view analyzers to localize and localize security-sensitive operations .
Outcome:	The proposed framework reduces false positives and increases accuracy by 6.6 percentage points on PrimeVul and SVEN.

FlipGuard: Defending Preference Alignment against Update Regression with Constrained Optimization (2024.emnlp-main)

Copied to clipboard

Mingye Zhu, Yi Liu, Quan Wang, Junbo Guo, Zhendong Mao

Challenge:	Recent advances in preference alignment have significantly improved Large Language Models' ability to generate texts that align with human preferences and values.
Approach:	They propose a constrained optimization approach to detect and mitigate update regression with focal attention.
Outcome:	The proposed approach detects and mitigates update regression with focal attention while maintaining excellent overall performance.

ConU: Conformal Uncertainty in Large Language Models with Correctness Coverage Guarantees (2024.findings-emnlp)

Copied to clipboard

Zhiyuan Wang, Jinhao Duan, Lu Cheng, Yue Zhang, Qingni Wang, Xiaoshuang Shi, Kaidi Xu, Heng Tao Shen, Xiaofeng Zhu

MRT: Multi-modal Short- and Long-range Temporal Convolutional Network for Time-sync Comment Video Behavior Prediction (2024.lrec-main)

Challenge:	Uncertainty quantification (UQ) in natural language generation tasks remains an open challenge . however, black-box uncertainty measures require investigating with the proliferation of LLMs served via APIs.
Approach:	They propose a conformal uncertainty measure and a method to transform heuristic uncertainty notions into rigorous prediction sets.
Outcome:	Empirical results show that the proposed method outperforms state-of-the-art methods and can provide reliable guarantees for open-ended NLG tasks.

Copied to clipboard

Weihao Zhao, Weidong He, Hao Wang, Haoyang Bi, Han Wu, Chen Zhu, Tong Xu, Enhong Chen

Surprise Calibration for Better In-Context Learning (2025.emnlp-main)

Challenge:	Using time-sync comments, it is difficult to understand user behavior due to complexity of interactions between users, videos, and comments.
Approach:	They propose a novel time-sync comment behavior prediction model that takes historical behavior into account and optimizes it on the basis of user preferences.
Outcome:	The proposed model improves the performance of time-sync comments on visual frames and textual comments on two cats playing simultaneously.

Copied to clipboard

Zhihang Tan, Jingrui Hou, Ping Wang, Qibiao Hu, Peng Zhu

VRPO: Rethinking Value Modeling for Robust RL under Noisy Supervision in LLM Post-Training (2026.acl-long)

Challenge:	Existing methods for in-context learning apply fixed class priors across all inputs . existing methods rely on retraining and retrain models .
Approach:	They propose a Bayesian-based method to capture the temporal dynamics of class priors . they identify "surprise" as an informative signal for class prior shift .
Outcome:	The proposed method outperforms existing methods on a range of benchmark tasks.

Copied to clipboard

Dingwei Zhu, Shihan Dou, Zhiheng Xi, Senjie Jin, Guoqiang Zhang, Jiazheng Zhang, Junjie Ye, Mingxu Chai, Enyu Zhou, Ming Zhang, Yuhui Wang, Caishuang Huang, Chenhao Huang, Yunke Zhang, Yuran Wang, Tao Gui, Qi Zhang, Xipeng Qiu, Xuanjing Huang

Multi-Stage Balanced Distillation: Addressing Long-Tail Challenges in Sequence-Level Knowledge Distillation (2024.findings-emnlp)

Challenge:	Reinforcement Learning (RL) in real-world environments often suffers from ambiguous or incomplete supervision.
Approach:	They propose a framework that enhances value modeling for robust RL in LLM post-training by integrating auxiliary losses guided by entropy and perplexity from a frozen language model and variational information bottleneck.
Outcome:	The proposed framework outperforms baselines on multi-turn dialogue, math reasoning, and science QA with rule-based and model-based rewards.

Copied to clipboard

Yuhang Zhou, Jing Zhu, Paiheng Xu, Xiaoyu Liu, Xiyao Wang, Danai Koutra, Wei Ai, Furong Huang

GenProve: Learning to Generate Text with Fine-Grained Provenance (2026.acl-long)

Challenge:	Knowledge distillation (KD) is a promising solution for large language models, but their deployment remains computationally expensive.
Approach:	They propose a framework which iteratively balances training data within a fixed computational budget and enables the transfer of knowledge from expensive teacher LLMs to smaller student models.
Outcome:	The proposed framework achieves state-of-the-art performance across diverse long-tailed datasets, enhancing both the efficiency and efficacy of the distilled models.

Copied to clipboard

Jingxuan Wei, Xingyue Wang, Yanghaoyu Liao, Jie Dong, Yuchen Liu, Caijun Jia, Bihui Yu, Junnan Zhu

UAlign: Leveraging Uncertainty Estimations for Factuality Alignment on Large Language Models (2025.acl-long)

Challenge:	Existing methods for large language models (LLMs) are coarse-grained and fail to distinguish between direct quotes and complex reasoning.
Approach:	They propose a framework that combines supervised fine-tuning and group relative policy optimization to generate fluent answers while simultaneously producing sentence-level provenance triples.
Outcome:	The proposed framework outperforms 14 strong large language models in joint evaluation.

Copied to clipboard

Boyang Xue, Fei Mi, Qi Zhu, Hongru Wang, Rui Wang, Sheng Wang, Erxin Yu, Xuming Hu, Kam-Fai Wong

SARA: Unlocking Multilingual Knowledge in Mixture-of-Experts via Semantically Anchored Routing Alignment (2026.findings-acl)

Challenge:	Large Language Models (LLMs) often struggle to accurately express factual knowledge, especially in cases where the knowledge boundaries are ambiguous.
Approach:	They propose a framework that leverages Uncertainty estimations to represent knowledge boundaries and incorporates these representations into prompts for LLMs to Align with factual knowledge.
Outcome:	The proposed framework significantly improves the LLMs’ capacities to confidently answer known questions and refuse unknown questions on both in-domain and out-of-domain tasks.

Copied to clipboard

Tianyu Dong, Yangyang Liu, Jiang Zhou, Xinwei Wu, Xiaohu Zhao, Hao Wang, Heng Liu, Linlong Xu, Longyue Wang, Weihua Luo, Shaolin Zhu, Deyi Xiong

AdaptFlow: Adaptive Workflow Optimization via Meta-Learning (2025.findings-emnlp)

Challenge:	Low-resource language tokens are often routed to different experts than those activated by high-resourced inputs, which hinders their efficacy in multilingual contexts.
Approach:	They propose a framework to transfer specialized capabilities from high-resource languages as anchors to low-resourced languages by using a symmetric Jensen-Shannon constraint.
Outcome:	The proposed framework outperforms standard instruction tuning on 5 low-resource languages and 3 benchmarks.

Copied to clipboard

Runchuan Zhu, Bowen Jiang, Lingrui Mei, Fangkai Yang, Lu Wang, Haoxiang Gao, Fengshuo Bai, Pu Zhao, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang

Can MLLMs Reason Beyond Language? VisReason: A Comprehensive Benchmark for Vision-Centric Reasoning (2026.findings-acl)

Challenge:	Existing approaches to large language models rely on static templates or manual workflows.
Approach:	AdaptFlow is a language-based meta-learning framework inspired by model-agnostic meta- learning.
Outcome:	AdaptFlow outperforms manual and automated workflows on question answering, code generation and mathematical reasoning benchmarks.

Copied to clipboard

Longteng Guo, Yifan Wang, Pengkang Huo, Tailai Chen, Yuze Wu, Jing Liu, Xinxin Zhu

OAgents: An Empirical Study of Building Effective Agents (2025.findings-emnlp)

Challenge:	Recent advances in multimodal large language models demonstrate strong performance on visual reasoning benchmarks.
Approach:	They propose a benchmark for vision-centric reasoning that integrates visual and textual information for non-trivial reasoning.
Outcome:	The proposed benchmark exposes gaps between humans and current MLLMs and reveals limited benefits from test-time reasoning strategies.

Copied to clipboard

He Zhu, Tianrui Qin, King Zhu, Heyuan Huang, Yeyi Guan, Jinxiang Xia, Hanhao Li, Yi Yao, Ningning Wang, Pai Liu, Tianhao Peng, Xin Gui, Li Xiaowan, Yuhui Liu, Xiangru Tang, Jian Yang, Ge Zhang, Xitong Gao, Yuchen Eleanor Jiang, Changwang Zhang, Jun Wang, Jiaheng Liu, Wangchunshu Zhou

ControversialQA: Exploring Controversy in Question Answering (2024.lrec-main)

Challenge:	a recent study shows that agent research practices are far from standard, rigorous . lack of a standard evaluation protocol makes previous works not reproducible, authors say .
Approach:	They conduct an empirical study on the GAIA benchmark to investigate agent design choices . they find that lack of a standard evaluation protocol makes previous works not reproducible .
Outcome:	The proposed framework achieves state-of-the-art performance among open-source projects.

Copied to clipboard

Zhen Wang, Peide Zhu, Jie Yang

Question Answering

Challenge:	Existing studies on controversy define it based on vague assumptions of its relation to sentiment . experimental results show controversy detection is essential and challenging .
Approach:	They propose a question-answering dataset that defines content controversy by user perception . they show controversy detection is essential and challenging .
Outcome:	The proposed dataset defines controversy by user perception, i.e., votes from plenty of users.

LongEmbed: Extending Embedding Models for Long Context Retrieval (2024.emnlp-main)

Copied to clipboard

Dawei Zhu, Liang Wang, Nan Yang, Yifan Song, Wenhao Wu, Furu Wei, Sujian Li

Representation Learning

Challenge:	Existing embedding models support only 512 input tokens, hindering their application in scenarios requiring long inputs.
Approach:	They evaluate the performance of existing embedding models by using a new benchmark and a training-free context window extension strategy.
Outcome:	The proposed model extends the input window of existing models by several folds.

Planning, Creation, Usage: Benchmarking LLMs for Comprehensive Tool Utilization in Real-World Complex Scenarios (2024.findings-acl)

Copied to clipboard

Shijue Huang, Wanjun Zhong, Jianqiao Lu, Qi Zhu, Jiahui Gao, Weiwen Liu, Yutai Hou, Xingshan Zeng, Yasheng Wang, Lifeng Shang, Xin Jiang, Ruifeng Xu, Qun Liu

LIFBench: Evaluating the Instruction Following Performance and Stability of Large Language Models in Long-Context Scenarios (2025.acl-long)

Challenge:	Existing benchmarks focus on simple synthesized queries that do not reflect real-world complexity, thereby offering limited perspectives in evaluating tool utilization.
Approach:	They propose a benchmark to evaluate LLMs’ ability in tool utilization within real-world scenarios.
Outcome:	The proposed benchmark improves LLMs’ ability in tool utilization within real-world scenarios and eliminates the restriction of pre-defined toolset.

Copied to clipboard

Xiaodong Wu, Minhao Wang, Yichen Liu, Xiaoming Shi, He Yan, Lu Xiangju, Junmin Zhu, Wei Zhang

LayAlign: Enhancing Multilingual Reasoning in Large Language Models via Layer-Wise Adaptive Fusion and Alignment Strategy (2025.findings-naacl)

Challenge:	Existing benchmarks rarely focus on instruction-following in long-context scenarios or stability on different inputs.
Approach:	They propose a scalable dataset to evaluate LLMs’ instruction-following capabilities and stability across long contexts.
Outcome:	The proposed method evaluates LLMs’ instruction-following capabilities and stability across long contexts.

Copied to clipboard

Zhiwen Ruan, Yixia Li, He Zhu, Longyue Wang, Weihua Luo, Kaifu Zhang, Yun Chen, Guanhua Chen

TokenShapley: Token Level Context Attribution with Shapley Value (2025.findings-acl)

Challenge:	Large language models (LLMs) are pretrained on multilingual corpora but exhibit suboptimal performance on low-resource languages.
Approach:	They propose a framework that integrates representations from all encoder layers and an adaptive fusion-enhanced attention mechanism to enable layer-wise interaction between the LLM and the multilingual encoder.
Outcome:	Experiments on multilingual reasoning tasks show that the proposed framework outperforms baselines.

Copied to clipboard

Yingtai Xiao, Yuqing Zhu, Sirat Samyoun, Wanrong Zhang, Jiachen T. Wang, Jian Du

Large Margin Representation Learning for Robust Cross-lingual Named Entity Recognition (2025.acl-long)

Challenge:	Large language models (LLMs) have strong capabilities in in-context learning, but verifying the correctness of their generated responses remains a challenge.
Approach:	They propose a token-level attribution method that combines Shapley value-based data attribution with KNN-based retrieval techniques to improve attribution accuracy.
Outcome:	TokenShapley outperforms state-of-the-art methods on four benchmarks . it achieves an 11–23% improvement in accuracy on the benchmarks.

Copied to clipboard

Guangcheng Zhu, Ruixuan Xiao, Haobo Wang, Zhen Zhu, Gengyu Lyu, Junbo Zhao

xLAM: A Family of Large Action Models to Empower AI Agent Systems (2025.naacl-long)

Challenge:	Existing approaches to name entity recognition neglect distribution skewness and pseudo-label bias . despite promising results, current approaches neglect these problems .
Approach:	They propose a framework that optimizes an adaptively reweighted contrastive loss to handle class skewness and pseudo-label bias.
Outcome:	The proposed framework outperforms existing methods on multiple benchmarks.

Copied to clipboard

Jianguo Zhang, Tian Lan, Ming Zhu, Zuxin Liu, Thai Quoc Hoang, Shirley Kokane, Weiran Yao, Juntao Tan, Akshara Prabhakar, Haolin Chen, Zhiwei Liu, Yihao Feng, Tulika Manoj Awalgaonkar, Rithesh R N, Zeyuan Chen, Ran Xu, Juan Carlos Niebles, Shelby Heinecke, Huan Wang, Silvio Savarese, Caiming Xiong

Mutual Reinforcement of LLM Dialogue Synthesis and Summarization Capabilities for Few-Shot Dialogue Summarization (2025.findings-naacl)

Challenge:	Autonomous agents powered by large language models (LLMs) have attracted significant research interest, but there are few standards for developing specialized models for agent tasks.
Approach:	They propose a series of large action models with dense and mixture-of-expert architectures that unifies, augments, and synthesizes diverse datasets to enhance agent generalizability and performance.
Outcome:	The proposed models outperform GPT-4, Claude-3, and many other models in terms of tool use and outperformed GPT-based models on multiple agent ability benchmarks.

Copied to clipboard

Yen-Ju Lu, Ting-Yao Hu, Hema Swetha Koppula, Hadi Pouransari, Jen-Hao Rick Chang, Yin Xia, Xiang Kong, Qi Zhu, Xiaoming Simon Wang, Oncel Tuzel, Raviteja Vemulapalli

OssCSE: Overcoming Surface Structure Bias in Contrastive Learning for Unsupervised Sentence Embedding (2023.emnlp-main)

Challenge:	Empirical results demonstrate that our method improves dialogue summarization, achieving a 1.5% increase in ROUGE scores and a 0.3% improvement in BERT scores in few-shot settings.
Approach:	They propose Mutual Reinforcing Data Synthesis (MRDS) within large language models to enhance few-shot dialogue summarization task.
Outcome:	Empirical results show that the proposed method improves dialogue summarization, achieving a 1.5% increase in ROUGE scores and a 0.3% improvement in BERT scores in few-shot settings.

Copied to clipboard

Zhan Shi, Guoyin Wang, Ke Bai, Jiwei Li, Xiang Li, Qingjun Cui, Belinda Zeng, Trishul Chilimbi, Xiaodan Zhu

Rethinking Expert Trajectory Utilization in LLM Post-training for Mathematical Reasoning (2026.acl-long)

Challenge:	Recent studies show that contrastive learning is effective in sentence representation learning . but, the surface structure bias is a problem in the current model .
Approach:	They propose to combine a sentence with a sub-semantic sentence to investigate the surface structure bias.
Outcome:	The proposed model achieves state-of-the-art on standard semantic textual similarity tasks using different pre-trained backbones.

Copied to clipboard

Bowen Ding, Yuhan Chen, Jiayang Lyu, Jiyao Yuan, Qi Zhu, Shuangshuang Tian, Dantong Zhu, Futing Wang, Heyuan Deng, Fei Mi, Lifeng Shang, Tao Lin

FinEval: A Chinese Financial Domain Knowledge Evaluation Benchmark for Large Language Models (2025.naacl-long)

Challenge:	evolving generic Large Language Models into specialized Large Reasoning Models requires effective post-training.
Approach:	They propose a plasticity-ceiling framework to harness expert trajectories . they establish the Sequential SFT-then-RL pipeline as the superior standard .
Outcome:	The proposed framework overcomes stability and premature convergence deficits in synchronized approaches.

Copied to clipboard

Xin Guo, Haotian Xia, Zhaowei Liu, Hanyang Cao, Zhi Yang, Zhiqiang Liu, Sizhe Wang, Jinyi Niu, Chuqi Wang, Yanhui Wang, Xiaolong Liang, Xiaoming Huang, Bing Zhu, Zhongyu Wei, Yun Chen, Weining Shen, Liwen Zhang

Intention Knowledge Graph Construction for User Intention Relation Modeling (2026.eacl-long)

Challenge:	Large language models have demonstrated outstanding performance in various natural language processing tasks, but their security capabilities in the financial domain have not been explored.
Approach:	They propose to use a benchmark to evaluate large language models' financial domain knowledge and practical abilities.
Outcome:	The proposed benchmark evaluates large language models' financial domain knowledge and practical abilities.

Copied to clipboard

Jiaxin Bai, Zhaobo Wang, Junfei Cheng, Dan Yu, Zerui Huang, Weiqi Wang, Xin Liu, Chen Luo, Yanming Zhu, Bo Li, Yangqiu Song

RouteLMT: Learned Sample Routing for Hybrid LLM Translation Deployment (2026.acl-industry)

Challenge:	Existing knowledge graphs focus on connecting intentions but lacks the ability to model the relationships between different intentions.
Approach:	They propose a framework to automatically generate an intention knowledge graph, capturing connections between user intentions.
Outcome:	The proposed model outperforms state-of-the-art methods and shows its utility.

Copied to clipboard

Yingfeng Luo, Hongyu Liu, DingYang Lin, Kaiyan Chang, Chenglong Wang, Bei Li, Quan Du, Tong Xiao, JingBo Zhu

Learning Deep Transformer Models for Machine Translation (P19-1)

Challenge:	Existing routing strategies rely on heuristics, external predictors, or absolute quality estimation to capture whether the large model provides a worthwhile improvement over the small one.
Approach:	They propose a budget allocation problem for routing large model to large model . they propose heuristics, external predictors, or absolute quality estimation to determine the optimal signal for budgeted decisions.
Outcome:	The proposed model outperforms heuristics, quality/difficulty estimation baselines and achieves a superior quality–budget Pareto frontier.

Copied to clipboard

Qiang Wang, Bei Li, Tong Xiao, Jingbo Zhu, Changliang Li, Derek F. Wong, Lidia S. Chao

MeNTi: Bridging Medical Calculator and LLM Agent with Nested Tool Calling (2025.naacl-long)

Challenge:	Neural machine translation models have advanced the previous state-of-the-art by learning mappings between sequences via neural networks and attention mechanisms.
Approach:	They propose to use layer normalization to pass the combination of previous layers to the next layer to improve the model.
Outcome:	The proposed model outperforms the shallow Transformer-Big/Base baseline model on English-German and Chinese-English tasks by 0.4-2.4 BLEU points.

Copied to clipboard

Yakun Zhu, Shaohang Wei, Xu Wang, Kui Xue, Shaoting Zhang, Xiaofan Zhang

M2RC-EVAL: Massively Multilingual Repository-level Code Completion Evaluation (2025.acl-long)

Challenge:	Large Language Models (LLMs) have been widely used in medicine but are limited in their ability to fully address the complexities of the real world.
Approach:	They propose a universal agent architecture for Large Language Models that integrates a specialized medical toolkit and employs meta-tool and nested calling mechanisms to enhance LLM tool utilization.
Outcome:	The proposed framework improves the accuracy and performance of medical calculators in complex medical scenarios.

Copied to clipboard

Jiaheng Liu, Ken Deng, Congnan Liu, Jian Yang, Shukai Liu, He Zhu, Peng Zhao, Linzheng Chai, Yanan Wu, JinKe JinKe, Ge Zhang, Zekun Moore Wang, Guoan Zhang, Yingshui Tan, Bangyu Xiang, Zhaoxiang Zhang, Wenbo Su, Bo Zheng

Role Prompting Guided Domain Adaptation with General Capability Preserve for Large Language Models (2024.findings-naacl)

Challenge:	Existing repository-level code completion benchmarks focus on a limited number of languages . existing benchmarks report overall average scores of different languages ignoring fine-grained abilities .
Approach:	They propose to use repository-level code completion benchmarks to evaluate general code intelligence abilities across languages for existing code Large Language Models.
Outcome:	The proposed benchmarks improve the code completion abilities of existing LLMs by using two types of annotations on the parsed syntax tree.

Copied to clipboard

Rui Wang, Fei Mi, Yi Chen, Boyang Xue, Hongru Wang, Qi Zhu, Kam-Fai Wong, Ruifeng Xu

CONSTRUCTURE: Benchmarking CONcept STRUCTUre REasoning for Multimodal Large Language Models (2024.findings-emnlp)

Challenge:	Large Language Models (LLMs) suffer catastrophic forgetting when tailored to specific domains . authors present a novel approach to manage multi-domain LLM adaptation .
Approach:	They propose a strategy to manage multi-domain LLM adaptation using self-distillation and role integration.
Outcome:	The proposed model alleviates catastrophic forgetting and inter-domain confusion while maintaining robust general capabilities.

Copied to clipboard

Zhiwei Zha, Xiangru Zhu, Yuanyi Xu, Chenghua Huang, Jingping Liu, Zhixu Li, Xuwu Wang, Yanghua Xiao, Bei Yang, Xiaoxiao Xu

KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answering (2022.acl-long)

Challenge:	Existing multimodal large language models lack the ability to perceive the visual world with a deep concept structure cognition.
Approach:	They propose a concept-level benchmark to assess MLLMs’ hierarchical concept understanding and reasoning abilities.
Outcome:	The proposed model outperforms state-of-the-art models in concept structure reasoning evaluation.

Copied to clipboard

Donghan Yu, Chenguang Zhu, Yuwei Fang, Wenhao Yu, Shuohang Wang, Yichong Xu, Xiang Ren, Yiming Yang, Michael Zeng

Coupling Distant Annotation and Adversarial Training for Cross-Domain Chinese Word Segmentation (2020.acl-main)

Challenge:	Open-Domain Question Answering (ODQA) models typically include a retrieving module and a reading module.
Approach:	They propose a new open-domain question-answering framework that uses a knowledge-enhanced version of FiD to improve the approach.
Outcome:	The proposed model improves on ODQA benchmark datasets with less than 40% computation cost.

Copied to clipboard

Ning Ding, Dingkun Long, Guangwei Xu, Muhua Zhu, Pengjun Xie, Xiaobin Wang, Haitao Zheng

ToolHop: A Query-Driven Benchmark for Evaluating Large Language Models in Multi-Hop Tool Use (2025.acl-long)

Challenge:	Fully supervised neural approaches have achieved significant progress in the task of Chinese word segmentation (CWS) however, they suffer from the cross-domain issue when they come to processing of out-of-domain data.
Approach:	They propose to use Chinese word as a target domain for distant annotation and adversarial training to reduce noise and maximize utilization of the source domain information.
Outcome:	The proposed method outperforms existing state-of-the-art methods on real-world datasets and significantly outperformed previous state- of-the art methods.

Copied to clipboard

Junjie Ye, Zhengyin Du, Xuesong Yao, Weijian Lin, Yufei Xu, Zehui Chen, Zaiyuan Wang, Sining Zhu, Zhiheng Xi, Siyu Yuan, Tao Gui, Qi Zhang, Xuanjing Huang, Jiecao Chen

Improving Demonstration Diversity by Human-Free Fusing for Text-to-SQL (2024.findings-emnlp)

Challenge:	Effective evaluation of multi-hop tool use is critical for analyzing the understanding, reasoning, and function-calling capabilities of large language models.
Approach:	They propose a dataset that provides rigorous evaluation of multi-hop tool use.
Outcome:	The proposed model achieves 49.04% accuracy across five model families.

Copied to clipboard

Dingzirui Wang, Longxu Dou, Xuanliang Zhang, Qingfu Zhu, Wanxiang Che

Task Compass: Scaling Multi-task Pre-training with Task Prefix (2022.findings-emnlp)

Challenge:	Existing studies have explored selecting relevant demonstrations from a human-labeled demonstration pool, but these methods lack diversity and incur high labeling costs.
Approach:	They propose a method that iteratively fuses demonstrations to create a diverse demonstration pool based on human labeling or even from scratch with LLMs, reducing labeling costs.
Outcome:	The proposed method achieves an average improvement of 2.1% based on existing labeling and 5.5% from scratch on mainstream datasets.

Copied to clipboard

Zhuosheng Zhang, Shuohang Wang, Yichong Xu, Yuwei Fang, Wenhao Yu, Yang Liu, Hai Zhao, Chenguang Zhu, Michael Zeng

BeamAggR: Beam Aggregation Reasoning over Multi-source Knowledge for Multi-hop Question Answering (2024.acl-long)

Challenge:	Existing studies show that multi-task learning with large-scale supervised tasks suffers from negative effects across tasks.
Approach:	They propose a task prefix guided multi-task pre-training framework to explore the relationships among tasks.
Outcome:	The proposed model can be used as a foundation backbone for a wide range of tasks and as augmentation tool for data augmentation with complementary tasks.

Copied to clipboard

Zheng Chu, Jingchang Chen, Qianglong Chen, Haotian Wang, Kun Zhu, Xiyuan Du, Weijiang Yu, Ming Liu, Bing Qin

Improving Fake News Detection of Influential Domain via Domain- and Instance-Level Transfer (2022.coling-1)

Challenge:	Large language models (LLMs) have demonstrated strong reasoning capabilities, but they still suffer from factual errors when tackling knowledge-intensive tasks.
Approach:	They propose a reasoning framework for knowledge-intensive multi-hop QA that prioritizes promising answers at each hop of question.
Outcome:	The proposed framework outperforms SOTA methods on four open-domain multi-hop reasoning datasets by 8.5%.

Copied to clipboard

Qiong Nan, Danding Wang, Yongchun Zhu, Qiang Sheng, Yuhui Shi, Juan Cao, Jintao Li

Transferable and Efficient: Unifying Dynamic Multi-Domain Product Categorization (2023.acl-industry)

Challenge:	Social media spreads both real news and fake news in various domains including politics, health, entertainment, etc.
Approach:	They propose a Domain- and Instance-level Transfer Framework for Fake News Detection which could improve the performance of specific target domains.
Outcome:	The proposed framework improves performance of target domains by hurting other domains, resulting in unsatisfactory performance in the target domain.

Copied to clipboard

Shansan Gong, Zelin Zhou, Shuo Wang, Fengjiao Chen, Xiujie Song, Xuezhi Cao, Yunsen Xian, Kenny Zhu

When Gradient Descent Meets Derivative-Free Optimization: A Match Made in Black-Box Scenario (2023.findings-acl)

Challenge:	e-commerce platforms are encountering increasingly complex product categorization scenarios . multiple business domains correspond to different category taxonomies, with different depths and distinct literal expressions of category names.
Approach:	They propose a taxonomy-agnostic framework that calculates semantic relatedness between product titles and category names in the vector space.
Outcome:	The proposed framework outperforms strong baselineson three dynamic multi-domain product categorization tasks.

Copied to clipboard

Chengcheng Han, Liqing Cui, Renyu Zhu, Jianing Wang, Nuo Chen, Qiushi Sun, Xiang Li, Ming Gao

ProMed: Shapley Information Gain Guided Reinforcement Learning for Proactive Medical LLMs (2026.acl-long)

Challenge:	Large pre-trained language models (PLMs) are expensive and may not be open-sourced due to commercial considerations and potential risks of misuse.
Approach:	They propose to introduce gradient descent into black-box tuning scenario . they propose a method which integrates gradient descent and derivative-free optimization .
Outcome:	The proposed method achieves significant performance gains over previous state-of-the-art methods.

Copied to clipboard

Hongxin Ding, Baixiang Huang, Yue Fang, Weibin Liao, Xinke Jiang, Jinyang Zhang, Yinghao Zhu, Zheng Li, Liantao Ma, Junfeng Zhao, Yasha Wang

Challenge:	Existing medical Large Language Models (LLMs) follow a reactive paradigm, risking diagnostic errors by answering before seeking sufficient details.
Approach:	They propose a reinforcement learning framework that transitions LLMs toward a proactive paradigm, enabling them to ask clinically valuable questions before decision-making.
Outcome:	Experiments on partial-information medical benchmarks show that ProMed outperforms state-of-the-art methods by 6.29% on average and delivers a 54.45% gain over the reactive paradigm.

Knowledge-Enhanced Named Entity Disambiguation for Short Text (2020.aacl-main)

Copied to clipboard

Zhifan Feng, Qi Wang, Wenbin Jiang, Yajuan Lyu, Yong Zhu

Knowledge Representation

Challenge:	Existing methods for named entity disambiguation are weak for short text . performance of existing methods drops dramatically for short texts .
Approach:	They propose a knowledge-enhanced method for named entity disambiguation . they use factual knowledge graph and conceptual knowledge graph to provide additional knowledge .
Outcome:	The proposed method achieves significant improvement on a large manually annotated short-text dataset and the state-of-the-art on three standard datasets.

Multimodal Text Style Transfer for Outdoor Vision-and-Language Navigation (2021.eacl-main)

Copied to clipboard

Wanrong Zhu, Xin Wang, Tsu-Jui Fu, An Yan, Pradyumna Narayana, Kazoo Sone, Sugato Basu, William Yang Wang

On-Policy Self-Distillation for Efficient Diffusion Language Models with Early-Stage Calibration (2026.findings-acl)

Challenge:	Outdoor vision-and-language navigation (VLN) tasks require visual grounding to generate correct actions.
Approach:	They propose a multimodal text style transfer learning approach to mitigate data scarcity in outdoor vision-and-language navigation tasks.
Outcome:	The proposed approach outperforms baseline models on the outdoor vision-and-language navigation task, improving task completion rate by 8.7% relative to the baseline models.

Copied to clipboard

Huaisheng Zhu, MingYu Liu, Junze Liu, Zhen Ge, Tian Wang, Jiri Gesi, Dakuo Wang, Weiqi Zhang, Houyu Zhang, Yufan Guo, Xian Li, Bing Yin, Sujay Sanghavi

Counter-Interference Adapter for Multilingual Machine Translation (2021.findings-emnlp)

Challenge:	Recent studies have demonstrated that masked diffusion models (MDMs) can surpass autoregressive models (ARMs) in various tasks.
Approach:	They propose a method to calibrate early token predictions without demonstration data by distilling an unnormalized target distribution into the original model.
Outcome:	Experiments on math, planning, and RLHF tasks show that COPSD improves both effectiveness and efficiency, and further enhances performance when combined with supervised fine-tuning.

Copied to clipboard

Yaoming Zhu, Jiangtao Feng, Chengqi Zhao, Mingxuan Wang, Lei Li

TPLinker: Single-stage Joint Extraction of Entities and Relations Through Token Pair Linking (2020.coling-main)

Challenge:	Existing approaches to multilingual machine translation suffer from performance degradation, resulting in a single model being inferior to separately trained bilingual models on resource-rich languages.
Approach:	They propose a transformer-based model with a small parameter overhead for multilingual machine translation that outperforms strong multilingual baselines on 64 of 66 language directions.
Outcome:	The proposed model outperforms strong multilingual baselines on 64 of 66 language directions, 42 of which have above 0.5 BLEU improvement.

Copied to clipboard

Yucheng Wang, Bowen Yu, Yueyang Zhang, Tingwen Liu, Hongsong Zhu, Limin Sun

CMNEE:A Large-Scale Document-Level Event Extraction Dataset Based on Open-Source Chinese Military News (2024.lrec-main)

Challenge:	Existing methods to extract entities and relations from unstructured text are susceptible to cascading errors due to the separation of entity detection and relation classification.
Approach:	They propose a one-stage joint extraction model that detects overlapping relations while being immune from exposure bias.
Outcome:	The proposed model can identify overlapping relations while being immune from exposure bias.

Copied to clipboard

Mengna Zhu, Zijie Xu, Kaisheng Zeng, Kaiming Xiao, Mao Wang, Wenjun Ke, Hongbin Huang

From Awareness to Adaptability: Enhancing Tool Utilization for Scientific Reasoning (2025.findings-acl)

Challenge:	Current research focuses on the general news or financial domains, with relatively few studies for military domain.
Approach:	They propose to annotate Chinese military news events from documents using a schema for the military domain.
Outcome:	The proposed dataset is large-scale, document-level open-source for the military domain . it contains 17,000 documents and 29,223 events, which are all manually annotated .

Copied to clipboard

Wenjing Xie, Xiaobo Liang, Juntao Li, Wanfu Wang, Kehai Chen, Qiaoming Zhu, Min Zhang

TextFlint: Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing (2021.acl-demo)

Challenge:	Existing approaches enhance reasoning through Chain-of-Thought, Program-ofThough, and Tool-Integration.
Approach:	They propose a tool-awareness training method that leverages both forward and backward data generation strategies to strengthen the model’s conscious and selective tool utilization in multi-step reasoning tasks.
Outcome:	The proposed method improves the model's tool utilization capabilities, including proactivity and execution success rates.

Copied to clipboard

Xiao Wang, Qin Liu, Tao Gui, Qi Zhang, Yicheng Zou, Xin Zhou, Jiacheng Ye, Yongxin Zhang, Rui Zheng, Zexiong Pang, Qinzhuo Wu, Zhengyan Li, Chong Zhang, Ruotian Ma, Zichu Fei, Ruijian Cai, Jun Zhao, Xingwu Hu, Zhiheng Yan, Yiding Tan, Yuan Hu, Qiyuan Bian, Zhihua Liu, Shan Qin, Bolin Zhu, Xiaoyu Xing, Jinlan Fu, Yue Zhang, Minlong Peng, Xiaoqing Zheng, Yaqian Zhou, Zhongyu Wei, Xipeng Qiu, Xuanjing Huang

G-Eval: NLG Evaluation using Gpt-4 with Better Human Alignment (2023.emnlp-main)

Challenge:	Existing approaches to textual robustness evaluation focus on slightly modifying the input data, which maintains the original meaning and results in a different prediction.
Approach:	They propose a multilingual robustness evaluation toolkit for NLP that integrates universal text transformations, task-specific transformations and adversarial attack.
Outcome:	The toolkit includes universal text transformation, task-specific transformation, adversarial attack, subpopulation, and their combinations to provide comprehensive robustness analyses.

Copied to clipboard

Yang Liu, Dan Iter, Yichong Xu, Shuohang Wang, Ruochen Xu, Chenguang Zhu

Sparse Latents Steer Retrieval-Augmented Generation (2025.acl-long)

Challenge:	Conventional reference-based metrics have low correlation with human judgments, especially for open-ended generation tasks.
Approach:	They propose to use large language models as reference-free NLG evaluators to assess the quality of NLG outputs.
Outcome:	The proposed framework outperforms all previous methods in two generation tasks, and has a Spearman correlation of 0.514 with human on summarization task, and a large variance in human judgments.

Copied to clipboard

Chunlei Xin, Shuheng Zhou, Huijia Zhu, Weiqiang Wang, Xuanang Chen, Xinyan Guan, Yaojie Lu, Hongyu Lin, Xianpei Han, Le Sun

Mapping Long-term Causalities in Psychiatric Symptomatology and Life Events from Social Media (2024.naacl-long)

Challenge:	In this study, we uncover interpretable latents that govern RAG behavior in large language models . Sparse Autoencoders are used to control large language model (LLM) behavior .
Approach:	They leverage Sparse Autoencoders within the LLaMA Scope to uncover latents that govern RAG behaviors.
Outcome:	The proposed model can be used to control large language models without architectural modifications.

Copied to clipboard

Siyuan Chen, Meilin Wang, Minghao Lv, Zhiling Zhang, Juqianqian Juqianqian, Dejiyangla Dejiyangla, Yujia Peng, Kenny Zhu, Mengyue Wu

Challenge:	Existing studies focus on the semantic content of social media posts, overlooking the evolving nature of mental disorders and symptoms.
Approach:	They extract causality between psychiatric symptoms and life events from social media posts and extract temporal attributes to improve diagnosis and treatment planning.
Outcome:	The extracted causality features improve diagnostic and treatment planning and improve performance in tasks such as depression and diagnosis point detection.

CodeMEM: AST-Guided Adaptive Memory for Repository-Level Iterative Code Generation (2026.findings-acl)

Copied to clipboard

Peiding Wang, Li Zhang, Fang Liu, Chongyang Tao, Yinghao Zhu

RelayAttention for Efficient Large Language Model Serving with Long System Prompts (2024.acl-long)

Challenge:	Existing memory management approaches show promise but remain limited by natural language-centric representations.
Approach:	They propose an AST-guided dynamic memory management system for repository-level iterative code generation that maintains and updates repository context through AST operations.
Outcome:	The proposed system improves instruction following by 12.2% and reduces interaction rounds by 2–3 while maintaining competitive inference latency and token efficiency.

Copied to clipboard

Lei Zhu, Xinjiang Wang, Wayne Zhang, Rynson Lau

Generate then Select: Open-ended Visual Question Answering Guided by World Knowledge (2023.findings-acl)

Challenge:	a long system prompt causes throughput/latency bottlenecks as the cost of generating the next token increases w.r.t the sequence length.
Approach:	They propose an attention algorithm that reads hidden state from DRAM exactly once for a batch of input tokens.
Outcome:	The proposed algorithm reduces the need for redundant memory accesses in existing algorithms.

Copied to clipboard

Xingyu Fu, Sheng Zhang, Gukyeong Kwon, Pramuditha Perera, Henghui Zhu, Yuhao Zhang, Alexander Hanbo Li, William Yang Wang, Zhiguo Wang, Vittorio Castelli, Patrick Ng, Dan Roth, Bing Xiang

HoLLMwood: Unleashing the Creativity of Large Language Models in Screenwriting via Role Playing (2024.findings-emnlp)

Challenge:	Open-ended Visual Question Answering (VQA) requires models to reason over visual and natural language inputs using world knowledge.
Approach:	They propose a new VQA pipeline that deploys a generate-then-select strategy guided by world knowledge for the first time.
Outcome:	The proposed pipeline expands the knowledge coverage from in-domain training data by 4.1% on OK-VQA, without additional computation cost.

Copied to clipboard

Jing Chen, Xinyu Zhu, Cheng Yang, Chufan Shi, Yadong Xi, Yuxiang Zhang, Junjie Wang, Jiashu Pu, Tian Feng, Yujiu Yang, Rongsheng Zhang

Training Data is More Valuable than You Think: A Simple and Effective Method by Retrieving from Training Data (2022.acl-long)

Challenge:	Generative AI has demonstrated unprecedented creativity in the field of computer vision, yet such phenomena have not been observed in the realm of literary creation.
Approach:	They propose a framework for unleashing the creativity of large language models (LLMs) they assign LLMs to different roles involved in real-world scenario, they write .
Outcome:	The proposed framework outperforms baselines in terms of coherence, relevance, interestingness and overall quality on automatically generated screenplays.

Copied to clipboard

Shuohang Wang, Yichong Xu, Yuwei Fang, Yang Liu, Siqi Sun, Ruochen Xu, Chenguang Zhu, Michael Zeng

SpeechFake: A Large-Scale Multilingual Speech Deepfake Dataset Incorporating Cutting-Edge Generation Methods (2025.acl-long)

Challenge:	Experimental results show that REtrieving from the traINing datA only can lead to significant gains on multiple NLG and NLU tasks.
Approach:	They propose to retrieve training instances from traINing datA and concatenate them with input to generate output.
Outcome:	The proposed method achieves state-of-the-art results on XSum, BigPatent, and CommonsenseQA.

Copied to clipboard

Wen Huang, Yanmei Gu, Zhiming Wang, Huijia Zhu, Yanmin Qian

Promoting Data and Model Privacy in Federated Learning through Quantized LoRA (2024.findings-emnlp)

Challenge:	Existing speech deepfake datasets are limited in scale and diversity, making it challenging to train models that can generalize well to unseen deepfakkes.
Approach:	They propose a large-scale speech deepfake dataset that includes over 3 million deepfak samples, totaling more than 3,000 hours of audio, generated using 40 different speech synthesis tools.
Outcome:	The proposed dataset includes over 3 million deepfake samples, totaling more than 3,000 hours of audio, generated using 40 different speech synthesis tools.

Copied to clipboard

Zhu JianHao, Changze Lv, Xiaohua Wang, Muling Wu, Wenhao Liu, Tianlong Li, Zixuan Ling, Cenyuan Zhang, Xiaoqing Zheng, Xuanjing Huang

Missing Modality meets Meta Sampling (M3S): An Efficient Universal Approach for Multimodal Sentiment Analysis with Missing Modality (2022.aacl-main)

Challenge:	Existing federated learning frameworks require substantial data and computational resources to develop large language models.
Approach:	They propose a method that distributes a quantized version of the model’s parameters during training and combine it with a popular fine-tuning method to significantly reduce communication costs.
Outcome:	The proposed method enables accurate estimations for parameter updates while preventing clients from accessing a model whose performance is comparable to the centrally hosted one.

Copied to clipboard

Haozhe Chi, Minghua Yang, Junhao Zhu, Guanhong Wang, Gaoang Wang

Towards Accurate and Consistent Evaluation: A Dataset for Distantly-Supervised Relation Extraction (2020.coling-main)

Challenge:	Existing methods to address missing modalities often assume a particular modality is completely missing due to recording or transmission error.
Approach:	They propose a missing modality-based meta-sampling approach for multimodal sentiment analysis with missing modalities . they conduct experiments on IEMOCAP, SIMS and CMU-MOSI datasets .
Outcome:	The proposed method significantly improves on existing models with a mixture of missing modalities.

Copied to clipboard

Tong Zhu, Haitao Wang, Junjie Yu, Xiabing Zhou, Wenliang Chen, Wei Zhang, Min Zhang

Divide-Then-Aggregate: An Efficient Tool Learning Method via Parallel Tool Invocation (2025.acl-long)

Challenge:	Distant Supervision (DS) generates large-scale annotated data but has wrong labels that result in incorrect evaluation scores during testing.
Approach:	They build a dataset using DS-generated data as training data and hire annotators to label test data.
Outcome:	The proposed dataset NYTH has a much larger test set and performs more accurate and consistent evaluation.

Copied to clipboard

Dongsheng Zhu, Weixian Shi, Zhengliang Shi, Zhaochun Ren, Shuaiqiang Wang, Lingyong Yan, Dawei Yin

BeautifulPrompt: Towards Automatic Prompt Engineering for Text-to-Image Synthesis (2023.emnlp-industry)

Challenge:	Large Language Models (LLMs) demonstrate remarkable capabilities but their ability to autonomously execute complex real-world tasks remains limited.
Approach:	They propose a parallel tool invocation framework that decomposes tasks into parallel tool-using subtasks while aggregating results for subsequent decisions.
Outcome:	The proposed method significantly improves task performance while reducing token consumption and inference time.

Copied to clipboard

Tingfeng Cao, Chengyu Wang, Bingyan Liu, Ziheng Wu, Jinhui Zhu, Jun Huang

Turning Trash into Treasure: Accelerating Inference of Large Language Models with Token Recycling (2025.acl-long)

Challenge:	Recent text-to-image models require multiple passes of prompt engineering by humans to produce satisfactory results for real-world applications.
Approach:	They propose a deep generative model to generate high-quality prompts from raw descriptions using visual feedback.
Outcome:	The proposed model produces high-quality prompts from simple raw descriptions . it can be integrated to a cloud-native AI platform to provide better image generation service in the cloud.

Copied to clipboard

Xianzhen Luo, Yixuan Wang, Qingfu Zhu, Zhiming Zhang, Xuanyu Zhang, Qing Yang, Dongliang Xu

TROJail: Trajectory-Level Optimization for Multi-Turn Large Language Model Jailbreaks with Process Rewards (2026.acl-long)

Challenge:	Large Language Models (LLMs) generate only one token at each decoding step, leading to high latency.
Approach:	They propose a speculative decoding paradigm that stores tokens in an adjacency matrix and employs a breadth-first-search algorithm to construct a draft tree.
Outcome:	The proposed method outperforms existing train-free methods by 30% and even a training method by 25%.

Copied to clipboard

Xiqiao Xiong, Ouxiang Li, Zhuo Liu, Moxin Li, Wentao Shi, Fengbin Zhu, Qifan Wang, Fuli Feng

Stance Detection with Hierarchical Attention Network (C18-1)

Challenge:	Existing approaches to training multi-turn attackers to probe model safety vulnerabilities rely on turn-level optimization, which is insufficient for learning long-term attack strategies.
Approach:	They propose a multi-turn reinforcement learning problem that optimizes the harmfulness of the final-turn response as the outcome reward.
Outcome:	The proposed approach improves attack success rates across multiple models and benchmarks, highlighting the effectiveness of the proposed approach.

Copied to clipboard

Qingying Sun, Zhongqing Wang, Qiaoming Zhu, Guodong Zhou

MULTITAT: Benchmarking Multilingual Table-and-Text Question Answering (2025.findings-emnlp)

Challenge:	Recent studies have focused on document-level opinion mining, but linguistic information is correlated with the stance of the document.
Approach:	They propose a hierarchical attention neural model to employ various linguistic information to construct the document representation.
Outcome:	The proposed model can detect stance of documents on two datasets.

Copied to clipboard

Xuanliang Zhang, Dingzirui Wang, Keyan Xu, Qingfu Zhu, Wanxiang Che

VisLingInstruct: Elevating Zero-Shot Learning in Multi-Modal Language Models with Autonomous Instruction Optimization (2024.naacl-long)

Challenge:	Existing TATQA datasets are limited to English, leading to drawbacks . existing datasets overlook challenges of multilingual TAT-QA and do not reflect real-world multilingual scenarios .
Approach:	They propose a multilingual TATQA dataset that can be translated into 10 languages . they use data from 3 mainstream TATQ datasets and analyze the results .
Outcome:	The proposed dataset outperforms other baselines by an average of 3.3 .

Copied to clipboard

Dongsheng Zhu, Daniel Tang, Weidong Han, Jinghui Lu, Yukun Zhao, Guoliang Xing, Junfeng Wang, Dawei Yin

Mobile-R1: Towards Interactive Capability for VLM-Based Mobile Agent via Systematic Training (2026.acl-long)

Challenge:	Current MMLMs show impressive zero-shot abilities in multi-modal tasks, but their performance depends heavily on the quality of instructions.
Approach:	They propose a novel approach to advancing multi-modal language models in zero-shot learning by evaluating and optimizing instructional texts through In-Context Learning.
Outcome:	The proposed approach improves zero-shot performance in multi-modal tasks by evaluating and optimizing instructional texts.

Copied to clipboard

Jihao Gu, Qihang Ai, Yingyao Wang, Pi Bu, Jingxuan Xing, Yue Cao, Zekun Zhu, Wei Jiang, Ziming Wang, Yingxiu Zhao, Ming-Liang Zhang, Jun Song, Yuning Jiang, Bo Zheng

LANG: Reinforcement Learning for Multilingual Reasoning with Language-Adaptive Hint Guidance (2026.acl-long)

Challenge:	Existing approaches to training agents for visual-language models trap them in local optima, hindering exploration and error correction with the environment.
Approach:	They propose a hierarchical training recipe that bridges atomic action execution and strategic task completion.
Outcome:	The proposed training recipe bridges atomic action execution and strategic task completion.

Copied to clipboard

Yuchun Fan, Bei Li, Peiguang Li, Yilin Wang, Yongyu Mu, Jian Yang, Xin Chen, Rongxiang Weng, Jingang Wang, Xunliang Cai, JingBo Zhu, Tong Xiao

CTAP for Chinese:A Linguistic Complexity Feature Automatic Calculation Platform (2022.lrec-1)

Challenge:	Existing methods for enhancing multi-step reasoning have not fully translated to multilingual contexts.
Approach:	They propose a framework that leverages language-conditioned hints to guide exploration in non-English reasoning tasks.
Outcome:	Empirical results show that the proposed framework improves reasoning performance without compromising language consistency.

Copied to clipboard

Yue Cui, Junhui Zhu, Liner Yang, Xuezhi Fang, Xiaobin Chen, Yujie Wang, Erhong Yang

CYCLE-INSTRUCT: Fully Seed-Free Instruction Tuning via Dual Self-Training and Cycle Consistency (2025.emnlp-main)

Challenge:	Existing tools to analyze linguistic complexity are limited and different because of different research purposes.
Approach:	They propose to integrate Chinese component into CTAP to analyze linguistic complexity . they propose to use 196 linguistic complex indexes to calculate linguistic characteristics .
Outcome:	The proposed indexes are compared with three linguistic complexity tools for Chinese . the proposed index sets include four levels of 196 linguistic complex indexe .

Copied to clipboard

Zhanming Shen, Hao Chen, Yulei Tang, Shaolin Zhu, Wentao Ye, Xiaomeng Hu, Haobo Wang, Gang Chen, Junbo Zhao