Papers by Wen Wang

Multimodal Fusion and Coherence Modeling for Video Topic Segmentation (2025.findings-acl)

Challenge:	Existing neural audio codecs are not capable of handling multi-domain audio data . et al., 2023) integrate speech modality with text-based large language models .
Approach:	They propose a unified audio codec with a single codebook to support multi-domain audio data . they propose combining a mix-of-experts strategy and a partitioned domain-adaptive codebook method .
Outcome:	The proposed codec outperforms existing codecs on acoustic and semantic representation capabilities.

Copied to clipboard

Hai Yu, Chong Deng, Qinglin Zhang, Jiaqing Liu, Qian Chen, Wen Wang

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

Challenge:	Traditional video topic segmentation methods struggle to discern topical transitions . supervised approaches have improved performance on video action or scene segmentation .
Approach:	They propose a new task for video topic segmentation that enhances multimodality alignment and fusion by exploring different architectures using Cross-Attention and Mixture of Experts.
Outcome:	The proposed model improves on educational videos, in the form of lectures . it combines cross-attention and mixture of experts to strengthen multimodality alignment and fusion .

Copied to clipboard

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

Speech & Audio in NLP

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

CharacterBox: Evaluating the Role-Playing Capabilities of LLMs in Text-Based Virtual Worlds (2025.naacl-long)

Copied to clipboard

Lei Wang, Jianxun Lian, Yi Huang, Yanqi Dai, Haoxuan Li, Xu Chen, Xing Xie, Ji-Rong Wen

Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning (2026.findings-acl)

Challenge:	Evaluating role-playing capabilities in large language models is challenging due to complex dynamics involved in role-playering.
Approach:	They propose a simulation sandbox that generates situational fine-grained character behavior trajectories to enhance LLM performance.
Outcome:	The proposed model generates situational fine-grained character behavior trajectories to enhance performance.

Copied to clipboard

Yibo Yan, Shen Wang, Jiahao Huo, Jingheng Ye, Zhendong Chu, Xuming Hu, Philip S. Yu, Carla P Gomes, Bart Selman, Qingsong Wen

AMANDA: Agentic Medical Knowledge Augmentation for Data-Efficient Medical Visual Question Answering (2025.findings-emnlp)

Challenge:	Current scientific reasoning models struggle with generalization across domains and fall short of multimodal perception.
Approach:	They propose to use multimodal large language models to integrate text, images, and other modalities to enhance scientific reasoning.
Outcome:	The proposed models can integrate text, images, and other modalities and improve reasoning across disciplines.

Copied to clipboard

Ziqing Wang, Chengsheng Mao, Xiaole Wen, Yuan Luo, Kaize Ding

Stop Looking for “Important Tokens” in Multimodal Language Models: Duplication Matters More (2025.emnlp-main)

Challenge:	Existing Med-MLLMs fail when deployed in low-resource settings where abundant labeled data is unavailable.
Approach:	They propose a training-free agentic framework that performs medical knowledge augmentation via LLM agents.
Outcome:	The proposed framework performs medical knowledge augmentation via LLM agents.

Copied to clipboard

Zichen Wen, Yifeng Gao, Shaobo Wang, Junyuan Zhang, Qintong Zhang, Weijia Li, Conghui He, Linfeng Zhang

Backdoor Collapse: Eliminating Unknown Threats Via Known Backdoor Aggregation In Language Models (2026.acl-long)

Challenge:	Vision tokens in multimodal large language models often dominate computational overhead due to excessive length compared to linguistic modality.
Approach:	They propose a token pruning method which defines an importance criterion for vision tokens and prunes the unimportant vision token during inference.
Outcome:	The proposed method can prune 88.9% of vision tokens while maintaining comparable performance.

Copied to clipboard

Liang Lin, Miao Yu, Moayad Aloqaily, Zhenhong Zhou, Kun Wang, Linsey Pang, Prakhar Mehrotra, Qingsong Wen

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

Challenge:	Existing defenses rely on impractical assumptions about trigger settings to mitigate backdoor attacks . a recent study found that small amounts of training data can systematically induce harmful behaviors in large language models.
Approach:	They propose a backdoor defense framework that requires no prior knowledge of trigger settings . they use a two-stage process to aggregate backdoor representations and fine-tune recovery .
Outcome:	The proposed defense reduces the average Attack Success Rate to 4.41% across multiple benchmarks . the proposed framework generalizes across different types of backdoors, confirming its robustness in practical deployment scenarios.

Copied to clipboard

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

Learning Task Decomposition to Assist Humans in Competitive Programming (2024.acl-long)

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

Copied to clipboard

Jiaxin Wen, Ruiqi Zhong, Pei Ke, Zhihong Shao, Hongning Wang, Minlie Huang

Improving Long Document Topic Segmentation Models With Enhanced Coherence Modeling (2023.emnlp-main)

Challenge:	Using language models (LMs) to solve complex problems, humans might struggle to understand and repair flawed ones.
Approach:	They propose to automatically decompose complex problems into simpler pieces that correspond to specific subtasks and measure their assistive value.
Outcome:	The proposed method enables non-experts to solve 33.3% more problems and speeds them up by 3.3x .

Copied to clipboard

Hai Yu, Chong Deng, Qinglin Zhang, Jiaqing Liu, Qian Chen, Wen Wang

Masked Thought: Simply Masking Partial Reasoning Steps Can Improve Mathematical Reasoning Learning of Language Models (2024.acl-long)

Challenge:	Recent supervised neural models have greatly promoted the development of topic segmentation, but the deeper relationship between coherence and topic segmenting is underexplored.
Approach:	They propose to use topic-aware Sentence Structure Prediction and Contrastive Semantic Similarity Learning to capture coherence from logical structure and semantic similarity perspectives to further improve topic segmentation performance.
Outcome:	The proposed approach outperforms state-of-the-art methods on WIKI-727K and achieves an average relative reduction of 4.3% on Pk on WikiSection.

Copied to clipboard

Changyu Chen, Xiting Wang, Ting-En Lin, Ang Lv, Yuchuan Wu, Xin Gao, Ji-Rong Wen, Rui Yan, Yongbin Li

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

Challenge:	Despite the advances in large language models, they still face difficulties with multi-step reasoning tasks.
Approach:	They propose a method that randomly masks certain tokens within the chain of thought to improve model accuracy by 5% over standard supervised fine-tuning.
Outcome:	The proposed method improves accuracy and accuracy by 5% over standard fine-tuning with a few codes modified.

Copied to clipboard

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

Dual-Axis Generative Reward Model Toward Semantic and Turn-taking Robustness in Interactive Spoken Dialogue Models (2026.acl-long)

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

Copied to clipboard

Yifu Chen, Shengpeng Ji, Zhengqing Liu, Qian Chen, Wen Wang, Ziqing Wang, Yangzhuo Li, Tianle Liang, Zhou Zhao

Automatic Table Union Search with Tabular Representation Learning (2023.findings-acl)

Challenge:	Reinforcement learning (RL) has improved text- and vision-language models, but its application in SDMs is hindered.
Approach:	They propose a dual-axis Generative Reward Model that provides semantic quality and interaction timing for SDMs.
Outcome:	The proposed model achieves state-of-the-art performance on interaction-quality assessment across a wide spectrum of datasets.

Copied to clipboard

Xuming Hu, Shen Wang, Xiao Qin, Chuan Lei, Zhengyuan Shen, Christos Faloutsos, Asterios Katsifodimos, George Karypis, Lijie Wen, Philip S. Yu

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

Challenge:	Existing methods to identify uniability based on column representations are insufficient to reveal latent relational features to describe column relation between pair of columns.
Approach:	They propose a self-supervised table union search framework called AutoTUS to learn column relational representations in a multi-stage manner.
Outcome:	The proposed framework improves on the SOTA baseline and on real-world datasets.

Copied to clipboard

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

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

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

Copied to clipboard

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

Encode Errors: Representational Retrieval of In-Context Demonstrations for Multilingual Grammatical Error Correction (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

Guangyue Peng, Wei Li, Wen Luo, Houfeng Wang

Representation Learning

Challenge:	a novel method for encoding fine-grained error patterns improves performance on GEC.
Approach:	They propose a method for encoding grammatical errors from LLMs' internal states using a GER method.
Outcome:	The proposed method significantly boosts performance in ICL settings on multilingual GEC datasets.

Calibration-Aware Policy Optimization for Reasoning LLMs (2026.acl-long)

Copied to clipboard

Ziqi Wang, Xingzhou Lou, Meiqi Wu, Zhengqi Wen, Junge Zhang

UniEDU: Toward Unified and Efficient Large Multimodal Models for Educational Tasks (2025.emnlp-industry)

Challenge:	Existing approaches to model calibration are limited or sacrifice gains in reasoning accuracy.
Approach:	They propose a method that improves calibration by 15% while boosting accuracy by 5% . they propose GRPO-style algorithms that misalign uncertainty-agnostic advantage estimation .
Outcome:	The proposed approach improves calibration by 15% while achieving comparable to or better than GRPO on multiple mathematical reasoning benchmarks.

Copied to clipboard

Zhendong Chu, Jian Xie, Shen Wang, Zichao Wang, Qingsong Wen

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

Challenge:	Existing research has focused on plain text, while real-world K-12 scenarios often involve multimodal data.
Approach:	They propose a unified language and vision assistant called UniEDU for educational applications . it excels across multiple educational tasks while maintaining strong generalization capabilities . authors propose to use UniEDu for industry-scale deployment .
Outcome:	The proposed model excels across multiple educational tasks while maintaining strong generalization capabilities.

Copied to clipboard

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

Programming Languages in NLP

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

Explanation based In-Context Demonstrations Retrieval for Multilingual Grammatical Error Correction (2025.naacl-long)

Copied to clipboard

Wei Li, Wen Luo, Guangyue Peng, Houfeng Wang

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

Challenge:	Grammatical error correction (GEC) aims to correct grammatical, spelling, and semantic errors in natural language text.
Approach:	They propose a retrieval method based on natural language grammatical error explanations to match inputs with pre-constructed databases where explanations for erroneous samples are generated by LLMs.
Outcome:	The proposed method outperforms existing semantic and BM25-based retrieval techniques without additional training or language adaptation.

Copied to clipboard

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

ZoFia: Zero-Shot Fake News Detection with Entity-Guided Retrieval and Multi-LLM Interaction (2026.findings-acl)

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

Copied to clipboard

Lvhua Wu, Xuefeng Jiang, Sheng Sun, Yan Lei, Tian Wen, Yuwei Wang, Min Liu

MDERank: A Masked Document Embedding Rank Approach for Unsupervised Keyphrase Extraction (2022.findings-acl)

Challenge:	Large language models (LLMs) are limited by knowledge cutoff and can generate factual hallucinations when handling time-sensitive news.
Approach:	They propose a two-stage zero-shot fake news detection framework that uses a hierarchical salience and saliency-calibrated minimum margin of relevance algorithm to extract core entities accurately.
Outcome:	The proposed framework outperforms existing zero-shot baselines and even most few-shot methods on two public datasets.

Copied to clipboard

Linhan Zhang, Qian Chen, Wen Wang, Chong Deng, ShiLiang Zhang, Bing Li, Wei Wang, Xin Cao

SDiaReward: Modeling and Benchmarking Spoken Dialogue Rewards with Modality and Colloquialness (2026.acl-long)

Challenge:	Keyphrase extraction (KPE) extracts phrases in a document that provide a concise summary of the core content.
Approach:	They propose an unsupervised keyphrase extraction method that ranks candidates by similarity between embeddings of source document and masked document.
Outcome:	The proposed method outperforms state-of-the-art methods on six benchmarks . it achieves average 3.53 improvement over the existing method .

Copied to clipboard

Jingyu Lu, Yuhan Wang, Fan Zhuo, Xize Cheng, Changhao Pan, Xueyi Pu, Yifu Chen, Chenyuhao Wen, Tianle Liang, Zhou Zhao

Speech & Audio in NLP

Challenge:	SDiaReward is an end-to-end spoken dialogue system that integrates paralinguistic nuances and spontaneous nature of human conversation.
Approach:	They propose an end-to-end multi-turn reward model trained on SDiaReward-Dataset . it is a collection of episode-level preference pairs targeting modality and colloquiality gaps .
Outcome:	The proposed model outperforms general-purpose audio LLMs in episode-level evaluation.

Towards Robust Neural Machine Translation with Iterative Scheduled Data-Switch Training (2022.coling-1)

Copied to clipboard

Zhongjian Miao, Xiang Li, Liyan Kang, Wen Zhang, Chulun Zhou, Yidong Chen, Bin Wang, Min Zhang, Jinsong Su

TOME: A Two-stage Approach for Model-based Retrieval (2023.acl-long)

Challenge:	Existing methods on robust neural machine translation (NMT) construct adversarial examples by injecting noise into authentic examples and indiscriminately exploit two types of examples.
Approach:	They propose an iterative scheduled data-switch training framework to mitigate this problem by injecting noise into authentic examples and indiscriminately exploiting two types of examples.
Outcome:	The proposed model outperforms several competitive benchmarks on four translation benchmarks.

Copied to clipboard

Ruiyang Ren, Wayne Xin Zhao, Jing Liu, Hua Wu, Ji-Rong Wen, Haifeng Wang

IterAlign: Iterative Constitutional Alignment of Large Language Models (2024.naacl-long)

Challenge:	Recent research has focused on model-based retrieval, which discards the index in the traditional retrieval model and memorizes the candidate corpora using model parameters.
Approach:	They propose a model-based retrieval approach that discards the index in the traditional retrieval model and memorizes the candidate corpora using model parameters.
Outcome:	The proposed approach eliminates the index in the traditional retrieval model and memorizes the candidate corpora using model parameters.

Copied to clipboard

Xiusi Chen, Hongzhi Wen, Sreyashi Nag, Chen Luo, Qingyu Yin, Ruirui Li, Zheng Li, Wei Wang

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

Challenge:	Empirical results show that iterAlign improves truthfulness, helpfulness, harmlessness and honesty, improving the LLM alignment by up to 13.5% in harmlessness.
Approach:	They propose a data-driven constitution discovery and self-alignment framework called IterAlign to overcome these drawbacks by leveraging red teaming to uncover weaknesses of an LLM.
Outcome:	Empirical results show that iterAlign improves truthfulness, helpfulness, harmlessness and honesty by up to 13.5%.

Copied to clipboard

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

Data Whisperer: Efficient Data Selection for Task-Specific LLM Fine-Tuning via Few-Shot In-Context Learning (2025.acl-long)

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

Copied to clipboard

Shaobo Wang, Xiangqi Jin, Ziming Wang, Jize Wang, Jiajun Zhang, Kaixin Li, Zichen Wen, Zhong Li, Conghui He, Xuming Hu, Linfeng Zhang

Leveraging Dual Process Theory in Language Agent Framework for Real-time Simultaneous Human-AI Collaboration (2025.acl-long)

Challenge:	Using fine-tuning on task-specific data is essential for large language models to be effective in specialized tasks.
Approach:	They propose a method that leverages few-shot in-context learning with the model to be fine-tuned.
Outcome:	The proposed method outperforms existing methods with a 3.1-point improvement and a 7.4 speedup on the Llama-3-8B-Instruct model using just 10% of the dataset.

Copied to clipboard

Shao Zhang, Xihuai Wang, Wenhao Zhang, Chaoran Li, Junru Song, Tingyu Li, Lin Qiu, Xuezhi Cao, Xunliang Cai, Wen Yao, Weinan Zhang, Xinbing Wang, Ying Wen

Linguistic Theories

Challenge:	Large language models (LLMs) excel in turn-by-turn human-AI collaboration but struggle with simultaneous tasks requiring real-time interaction.
Approach:	They propose a language agent framework that integrates System 1 and System 2 for efficient real-time simultaneous human-AI collaboration.
Outcome:	The proposed framework improves on existing LLM-based agents and human collaborators by integrating Theory of Mind and asynchronous reflection to infer human intentions and perform reasoning-based autonomous decisions.

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

Copied to clipboard

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

DI-BENCH: Benchmarking Large Language Models on Dependency Inference with Testable Repositories at Scale (2025.findings-acl)

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

Copied to clipboard

Linghao Zhang, Junhao Wang, Shilin He, Chaoyun Zhang, Yu Kang, Bowen Li, Jiaheng Wen, Chengxing Xie, Maoquan Wang, Yufan Huang, Elsie Nallipogu, Qingwei Lin, Yingnong Dang, Saravan Rajmohan, Dongmei Zhang, Qi Zhang

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

Challenge:	Existing studies highlight that dependency-related issues cause over 40% of observed runtime errors on the generated repository.
Approach:	They propose a large-scale benchmark and evaluation framework specifically designed to assess LLMs’ capability on dependency inference.
Outcome:	The proposed model achieves only a 48% execution pass rate on Python, indicating room for improvement.

Copied to clipboard

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

MISC: A Mixed Strategy-Aware Model integrating COMET for Emotional Support Conversation (2022.acl-long)

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

Copied to clipboard

Quan Tu, Yanran Li, Jianwei Cui, Bin Wang, Ji-Rong Wen, Rui Yan

Improving Preference Alignment of LLM with Inference-Free Self-Refinement (2025.findings-emnlp)

Challenge:	Existing methods for emotional support conversation are too coarse-grained to capture user’s instant mental state and focus on expressing empathy in the response rather than gradually reducing user’ s distress.
Approach:	They propose a model which firstly infers the user’s fine-grained emotional status and then responds skillfully using a mixture of strategy.
Outcome:	The proposed model infers the user’s fine-grained emotional status and responds skillfully using mixed-up strategy modeling.

Copied to clipboard

Fukun Ma, Kaibin Tian, Jieting Xue, Xiaoyi Wang, Ye Ma, Quan Chen, Peng Jiang, Lijie Wen

Challenge:	Large language models (LLMs) develop in-context learning capability through pretraining and instruction tuning.
Approach:	Large language models (LLMs) develop in-context learning capability through pretraining and instruction tuning.
Outcome:	Experiments show that incorporating IFSR into preference alignment yields performance improvement over 10%.

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

Copied to clipboard

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

Low-Resource NLP

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

Evaluating Object Hallucination in Large Vision-Language Models (2023.emnlp-main)

Copied to clipboard

Yifan Li, Yifan Du, Kun Zhou, Jinpeng Wang, Xin Zhao, Ji-Rong Wen

DAWN-ICL: Strategic Planning of Problem-solving Trajectories for Zero-Shot In-Context Learning (2025.naacl-long)

Challenge:	Large vision-language models (LVLMs) suffer from object hallucinations, i.e., they tend to generate objects inconsistent with the target images in the descriptions.
Approach:	They propose to integrate powerful large vision-language models (LVLMs) they propose a polling-based query method to evaluate object hallucination .
Outcome:	The proposed model can evaluate object hallucination in a more stable and flexible way.

Copied to clipboard

Xinyu Tang, Xiaolei Wang, Xin Zhao, Ji-Rong Wen

DiffLM: Controllable Synthetic Data Generation via Diffusion Language Models (2025.findings-acl)

Challenge:	Existing methods to conduct in-context learning without using human-annotated demonstrations are unreliable and lead to error accumulation.
Approach:	They propose a method to conduct in-context learning without using human-annotated demonstrations.
Outcome:	The proposed method outperforms existing methods using human-annotated demonstrations.

Copied to clipboard

Ying Zhou, Xinyao Wang, Yulei Niu, Yaojie Shen, Lexin Tang, Fan Chen, Ben He, Le Sun, Longyin Wen

Unveiling the Flaws: Exploring Imperfections in Synthetic Data and Mitigation Strategies for Large Language Models (2024.findings-emnlp)

Challenge:	Recent advances in large language models (LLMs) have significantly enhanced their knowledge and generative capabilities, leading to a surge of interest in leveraging LLMs for high-quality data synthesis.
Approach:	They propose a controllable data synthesis framework based on variational autoencoder which leverages diffusion models to reserve more information of original distribution and format structure in the learned latent distribution.
Outcome:	The proposed framework generates high-quality data with performance exceeding that of real data by 2%–7% on seven real-world datasets.

Copied to clipboard

Jie Chen, Yupeng Zhang, Bingning Wang, Xin Zhao, Ji-Rong Wen, Weipeng Chen

Cocktail: A Comprehensive Information Retrieval Benchmark with LLM-Generated Documents Integration (2024.findings-acl)

Challenge:	acquiring large amounts of high-quality data can be challenging due to data scarcity, privacy concerns, and high costs.
Approach:	They propose a method which reverses instruction-following issues caused by uniform format of synthetic data and proposes unlearning techniques to mitigate these flaws.
Outcome:	The proposed method reverses instruction-following issues caused by pattern overfitting without compromising performance on benchmarks at relatively low cost.

Copied to clipboard

Sunhao Dai, Weihao Liu, Yuqi Zhou, Liang Pang, Rongju Ruan, Gang Wang, Zhenhua Dong, Jun Xu, Ji-Rong Wen

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

Challenge:	Large Language Models (LLMs) have led to an influx of AI-generated content on the internet, transforming corpus of Information Retrieval (IR) systems from human-written to a coexistence with LLM-generated contents.
Approach:	They propose a benchmark named Cocktail that compares IR models with LLMs to find relevant documents and passages from a corpus.
Outcome:	The proposed benchmark aims to evaluate IR models in the mixed-sourced data landscape of the LLM era.

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

DisCal: Distribution-Aware Calibration for Mathematical Reasoning Under Character-Level Noisy Inputs (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

Bo Zhang, Jiawei Zhang, Cong Gao, Bingxu Han, Minghao Hu, Jun Zhang, Yunbo Cao, Zhunchen Luo, Wen Yao, Guotong Geng, Zhong Wang

Mitigating Posterior Salience Attenuation in Long-Context LLMs with Positional Contrastive Decoding (2025.acl-short)

Challenge:	Existing methods for calibration of large reasoning models (LRMs) focus on clean inputs, leaving noise unexplored.
Approach:	They propose a confidence calibration framework for character-level noisy inputs that extracts uncertainty signals from both the empirical answer distribution and the model’s predictive distribution and integrates them via a learned calibrator.
Outcome:	Experiments on multiple mathematical reasoning benchmarks show that DisCal outperforms existing calibration methods under noisy inputs, reducing expected calibration error (ECE) by up to 39.21% and improving Area Under the Receiver Operating Characteristic Curve (AUROC) by 31.44%.

Copied to clipboard

Zikai Xiao, Ziyang Wang, Wen Ma, Yan Zhang, Wei Shen, WangYan WangYan, Luqi Gong, Zuozhu Liu

Challenge:	Current solutions incur prohibitive training costs, leaving statistical behaviors and cost-effective approaches underexplored.
Approach:	They propose a positional contrast decoding technique that contrasts long-aware attention with designed local-awn attention.
Outcome:	The proposed model achieves state-of-the-art performance on long-context benchmarks.

Beyond Fully Random Masking: Attention-Guided Denoising and Optimization for Diffusion Language Models (2026.acl-long)

Copied to clipboard

Jia Deng, Junyi Li, Xin Zhao, Jinpeng Wang, Hongyu Lu, Ji-Rong Wen

MindMap: Knowledge Graph Prompting Sparks Graph of Thoughts in Large Language Models (2024.acl-long)

Challenge:	Existing methods for full-attention dLLMs rely on random masking strategies that overlook intrinsic token dependencies.
Approach:	They propose an attention-guided denoising and optimization framework that aligns training and optimization with attention-derived dependencies.
Outcome:	The proposed framework outperforms state-of-the-art methods on mathematical and coding benchmarks.

Copied to clipboard

Yilin Wen, Zifeng Wang, Jimeng Sun

LLM Critics Help Catch Bugs in Mathematics: Towards a Better Mathematical Verifier with Natural Language Feedback (2025.findings-acl)

Challenge:	Large language models suffer from limitations such as difficulty in incorporating new knowledge, generating hallucinations, and explaining their reasoning process.
Approach:	They propose a pipeline that leverages knowledge graphs to enhance LLMs’ inference and transparency by eliciting the mind map of LLM's, which reveals their reasoning pathways based on the ontology of knowledge.
Outcome:	The proposed pipeline enables LLMs to comprehend KG inputs and infer with a combination of implicit and external knowledge.

Copied to clipboard

Bofei Gao, Zefan Cai, Runxin Xu, Peiyi Wang, Ce Zheng, Runji Lin, Keming Lu, Dayiheng Liu, Chang Zhou, Wen Xiao, Tianyu Liu, Baobao Chang

R2D2: Recursive Transformer based on Differentiable Tree for Interpretable Hierarchical Language Modeling (2021.acl-long)

Challenge:	Existing mathematical verifiers are trained with binary classification labels, which are not informative enough for the model to accurately assess the solutions.
Approach:	They propose a natural language feedback-enhanced verifier that can validate the correctness of response generated by policy models by constructing automatically generated training data and a two-stage training paradigm.
Outcome:	The proposed verifier significantly improves in verification and reinforcement learning and alleviates data-demanding problems of the reward model.

Copied to clipboard

Xiang Hu, Haitao Mi, Zujie Wen, Yafang Wang, Yi Su, Jing Zheng, Gerard de Melo

GenPilot: A Multi-Agent System for Test-Time Prompt Optimization in Image Generation (2025.findings-emnlp)

Challenge:	Existing models with stacked layers do not explicitly model hierarchical structure of language understanding.
Approach:	They propose a recursive Transformer model based on differentiable CKY style binary trees to emulate hierarchical composition process.
Outcome:	The proposed model can predict words given their left and right abstraction nodes.

Copied to clipboard

Wen Ye, Zhaocheng Liu, Gui Yuwei, Tingyu Yuan, Yunyue Su, Bowen Fang, Chaoyang Zhao, Qiang Liu, Liang Wang

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

Challenge:	Existing methods for text-to-image synthesis lack systematic error analysis and refinement strategies, resulting in limited reliability and effectiveness.
Approach:	They propose a plug-and-play multi-agent system called GenPilot that integrates error analysis, clustering-based adaptive exploration, fine-grained verification and a memory module for iterative optimization.
Outcome:	The proposed method improves text consistency and structural coherence on images with a plug-and-play system.

Copied to clipboard

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

ErrorRadar: Benchmarking Complex Mathematical Reasoning of Multimodal Large Language Models Via Error Detection (2026.findings-acl)

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

Copied to clipboard

Yibo Yan, Shen Wang, Jiahao Huo, Hang Li, Boyan Li, Jiamin Su, Xiong Gao, YiFan Zhang, Tianlong Xu, Zhendong Chu, Aoxiao Zhong, Kun Wang, Hui Xiong, Philip S. Yu, Xuming Hu, Qingsong Wen

MAGI: Multi-Agent Guided Interview for Psychiatric Assessment (2025.findings-acl)

Challenge:	Current mathematical benchmarks focus on evaluating MLLMs’ problem-solving ability, yet there is a crucial gap in addressing more complex scenarios such as error detection.
Approach:	They propose to evaluate multimodal error detection by evaluating two sub-tasks error step identification and error categorization.
Outcome:	The proposed task evaluates MLLMs' ability to handle multimodal questions compared to text-only models.

Copied to clipboard

Guanqun Bi, Zhuang Chen, Zhoufu Liu, Hongkai Wang, Xiyao Xiao, Yuqiang Xie, Wen Zhang, Yongkang Huang, Yuxuan Chen, Libiao Peng, Minlie Huang

MT-Video-Bench: A Holistic Video Understanding Benchmark for Evaluating Multimodal LLMs in Multi-Turn Dialogues (2026.findings-acl)

Challenge:	Existing large language models (LLMs) do not align with psychiatric diagnostic protocols.
Approach:	They propose a framework that transforms the Mini International Neuropsychiatric Interview into automatic computational workflows through coordinated multi-agent collaboration.
Outcome:	The proposed framework transforms the gold-standard Mini International Neuropsychiatric Interview (MINI) into automatic computational workflows through coordinated multi-agent collaboration.

Copied to clipboard

Yaning Pan, Qianqian Xie, Guohui Zhang, Zekun Moore Wang, Yongqian Wen, Yuanxing Zhang, Haoxuan Hu, Zhiyu Pan, Yibing Huang, Zhidong Gan, Yonghong Lin, An Ping, Shihao Li, Yanghai Wang, Tianhao Peng, Jiaheng Liu

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

Challenge:	Existing evaluation benchmarks for Multimodal Large Language Models (MLLMs) focus on single-turn question answering, overlooking the complexity of multi-turn dialogues in real-world scenarios.
Approach:	They propose a video understanding benchmark for MLLMs in multi-turn dialogues that assesses six core competencies that focus on perceptivity and interactivity.
Outcome:	The MT-Video-Bench evaluates 1,000 multi-turn dialogues from diverse domains and reveals significant performance discrepancies and limitations in handling multi-turned video dialogues.

Copied to clipboard

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

M3: A Multi-View Fusion and Multi-Decoding Network for Multi-Document Reading Comprehension (2022.emnlp-main)

Challenge:	a lack of high-quality English privacy policy corpus optimized for legal clarity and readability is limiting translation of privacy policies . 139 privacy policies are often considered "incomprehensible" due to technical jargon, legal language, and convoluted grammatical structures.
Approach:	They propose a high-quality English privacy policy corpus annotated by domain experts . they propose APPSI-139 to summarize and interpret privacy policies in English .
Outcome:	The proposed framework outperforms large language models in terms of readability and accuracy.

Copied to clipboard

Liang Wen, Houfeng Wang, Yingwei Luo, Xiaolin Wang

Decode with Template: Content Preserving Sentiment Transfer (2020.lrec-1)

Challenge:	Existing methods for multi-document reading comprehension cannot make full of the advantages of both approaches.
Approach:	They propose a multi-view fusion and multi-decoding method that integrates multiple documents for answering questions.
Outcome:	The proposed method improves on two mainstream multi-document reading comprehension datasets.

Copied to clipboard

Zhiyuan Wen, Jiannong Cao, Ruosong Yang, Senzhang Wang

Sentiment Analysis

Challenge:	Existing methods to transfer sentiments for text use only explicit sentiments and templates to remove them from input sentences.
Approach:	They propose a method to transfer sentiments from input sentences to output sentences using templates.
Outcome:	The proposed model significantly outperforms state-of-the-art models in content preservation.

AlignBench: Benchmarking Chinese Alignment of Large Language Models (2024.acl-long)

Copied to clipboard

Xiao Liu, Xuanyu Lei, Shengyuan Wang, Yue Huang, Andrew Feng, Bosi Wen, Jiale Cheng, Pei Ke, Yifan Xu, Weng Lam Tam, Xiaohan Zhang, Lichao Sun, Xiaotao Gu, Hongning Wang, Jing Zhang, Minlie Huang, Yuxiao Dong, Jie Tang

ReasoningGuard: Safeguarding Large Reasoning Models with Inference-time Safety Aha Moments (2026.acl-long)

Challenge:	Effective evaluation of alignment for emerging Chinese LLMs is still significantly lacking, calling for real-scenario grounded, open-ended, challenging and automatic evaluations tailored for alignment.
Approach:	They propose a multi-dimensional benchmark for evaluating LLMs’ alignment in Chinese with 8 main categories, 683 real-scenario rooted queries and corresponding human verified references.
Outcome:	The benchmark uses a human-in-the-loop data curation pipeline, 683 real-scenario rooted queries and human verified references.

Copied to clipboard

Yuquan Wang, Mi Zhang, Yining Wang, Geng Hong, Mi Wen, Xiaoyu You, Min Yang

VENUS: A VLLM-driven Video Content Discovery System for Real Application Scenarios (2025.emnlp-industry)

Challenge:	Existing defenses for Large Reasoning Models (LRMs) depend on costly fine-tuning and additional expert knowledge, which limits their scalability.
Approach:	They propose an inference-time safeguard for Large Reasoning Models that injects safety aha moments into the reasoning process to guide the model towards harmless yet helpful reasoning.
Outcome:	The proposed safeguard outperforms nine existing safeguards while avoiding common exaggerated safety issues.

Copied to clipboard

Minyi Zhao, Yi Liu, Jianfeng Wen, Boshen Zhang, Hailang Chang, Zhiheng Ouyang, Jie Wang, Wensong He, Shuigeng Zhou

Visual Data in NLP

Challenge:	Video Content Discovery (VCD) is to identify specific videos defined by a pre-specified text policy.
Approach:	They propose a Vision-Language Large Model-driven video content discovery system called VENUS to solve these problems.
Outcome:	The proposed system generates high-quality, VCD-specific data for model training and extends it to support it better.

TrendSim: Simulating Trending Topics in Social Media Under Poisoning Attacks with LLM-based Multi-agent System (2025.findings-naacl)

Copied to clipboard

Zeyu Zhang, Jianxun Lian, Chen Ma, Yaning Qu, Ye Luo, Lei Wang, Rui Li, Xu Chen, Yankai Lin, Le Wu, Xing Xie, Ji-Rong Wen

Time-RA: Towards Time Series Reasoning for Anomaly Diagnosis with LLM Feedback (2026.findings-acl)

Challenge:	Trending topics bring in a new channel for poisoning attacks, resulting in negative impacts on society.
Approach:	They propose an LLM-based multi-agent system to simulate trending topics in social media . they propose a time-aware interaction mechanism, centralized message dissemination, and an interactive system .
Outcome:	The proposed system simulates trending topics under poisoning attacks on social media platforms.

Copied to clipboard

Yiyuan Yang, Zichuan Liu, Lei Song, Kai Ying, Stephen Wang, Joshua Thomas Bamford, Svitlana Vyetrenko, Jiang Bian, Qingsong Wen

Are We Using the Right Benchmark: An Evaluation Framework for Visual Token Compression Methods (2026.acl-long)

Challenge:	Time series anomaly detection (TSAD) has traditionally focused on binary classification and lacks the fine-grained categorization and explanatory reasoning required for transparent decision-making.
Approach:	They propose a time-series reasoning task that reformulates TSAD from discriminative to reasoning-intensive paradigm.
Outcome:	The proposed task reformulates TSAD from discriminative to reasoning-intensive paradigm.

Copied to clipboard

Chenfei Liao, Wensong Wang, Zichen Wen, Xu Zheng, Yiyu Wang, Haocong He, Yuanhuiyi Lyu, Lutao Jiang, Xin Zou, Yuqian Fu, Bin Ren, Linfeng Zhang, Xuming Hu

DoTAT: A Domain-oriented Text Annotation Tool (2022.acl-demo)

Challenge:	Recent efforts to accelerate inference in Multimodal Large Language Models have focused on visual token compression.
Approach:	They propose a framework that leverages downsampling as a discriminator to denoise existing benchmarks.
Outcome:	The proposed evaluation framework leverages downsampling as a discriminator to denoise existing benchmarks.

Copied to clipboard

Yupian Lin, Tong Ruan, Ming Liang, Tingting Cai, Wen Du, Yi Wang

Challenge:	DoTAT is a domain-oriented text annotation tool that can reduce the time for event annotation by 19.7% . the tool supports multi-person collaborative process with automatically merging and review .
Approach:	They propose a domain-oriented text annotation tool called DoTAT . it provides multi-person collaborative process with automatic merging and review .
Outcome:	The proposed tool can reduce the time for event annotation by 19.7% compared with existing tools.

PACE: Prefix-Protected and Difficulty-Aware Compression for Efficient Reasoning (2026.findings-acl)

Copied to clipboard

Ruixiang Feng, Yuntao Wen, Silin Zhou, Ke Shi, Yifan Wang, Ran Le, Zhenwei An, Zongchao Chen, Chen Yang, Guangyue Peng, Yiming Jia, Dongsheng Wang, Tao Zhang, Lisi Chen, Yang Song, Shen Gao, Shuo Shang

HammerBench: Fine-Grained Function-Calling Evaluation in Real Mobile Assistant Scenarios (2025.findings-acl)

Challenge:	Existing LRMs often suffer from "overthinking" and excessively long reasoning traces . a dual-level framework for length compression of LRM is proposed .
Approach:	They propose a framework for prefix-protected and difficulty-aware compression under hierarchical supervision.
Outcome:	The proposed framework reduces token usage while improving accuracy on math benchmarks.

Copied to clipboard

Jun Wang, Jiamu Zhou, Xihuai Wang, Xiaoyun Mo, Haoyu Zhang, Qiqiang Lin, Jincheng Jincheng, Muning Wen, Weinan Zhang, Qiuying Peng, Jun Wang

Virtual Data Augmentation: A Robust and General Framework for Fine-tuning Pre-trained Models (2021.emnlp-main)

Challenge:	Evaluating the performance of LLMs in multi-turn interactions presents significant challenges due to the complexity and variability of user behavior.
Approach:	They propose a benchmark framework for assessing LLMs’ function-calling capabilities in multi-turn dialogues.
Outcome:	The proposed framework is based on a dataset derived from popular mobile apps and anonymized user logs.

Copied to clipboard

Kun Zhou, Wayne Xin Zhao, Sirui Wang, Fuzheng Zhang, Wei Wu, Ji-Rong Wen

ToolPRM: Fine-Grained Inference Scaling of Structured Outputs for Function Calling (2026.acl-long)

Challenge:	Recent studies have shown that powerful pre-trained language models can be fooled by small perturbations or intentional attacks.
Approach:	They propose a framework for fine-tuning PLMs using a masked language model and Gaussian noise to augment semantically relevant examples with sufficient diversity.
Outcome:	The proposed framework improves the robustness of pre-trained language models and alleviates performance degradation under adversarial attacks.

Copied to clipboard

Jianghao Lin, Yuanyuan Shi, Xin Peng, Renjie Ding, Hairui Wang, Yuxuan Peng, Bizhe Bai, Weixi Song, Fengshuo Bai, Huacan Chai, Weinan Zhang, Fei Huang, Ying Wen

Challenge:	Existing research on inference scaling focuses on unstructured output generation tasks, such as mathematical problems.
Approach:	They propose an inference-scaling framework that combines fine-grained beam search with ToolPRM, a process reward model scoring each intra-call decision.
Outcome:	The proposed framework outperforms outcome and coarse-grained reward models in predictive accuracy and yields consistent test-time gains on multiple function-calling benchmarks.

Learning Invariant Representation Improves Robustness for MRC Models (2022.findings-emnlp)

Copied to clipboard

Yu Hai, Liang Wen, Haoran Meng, Tianyu Liu, Houfeng Wang

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

Challenge:	Existing approaches to improve machine reading comprehension models are vulnerable and not robust to adversarial examples.
Approach:	They propose to construct positive example pairs which have same answer by augmentation and then introduce stability and contrastive loss to improve invariance of representation.
Outcome:	The proposed approach boosts the robustness of QA models across different tasks and attack sets significantly and consistently.

Copied to clipboard

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

Wasserstein Distance Regularized Sequence Representation for Text Matching in Asymmetrical Domains (2020.emnlp-main)

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

Weijie Yu, Chen Xu, Jun Xu, Liang Pang, Xiaopeng Gao, Xiaozhao Wang, Ji-Rong Wen

Representation Learning

Challenge:	Asymmetrical text matching is a fundamental problem in information retrieval and natural language processing.
Approach:	They propose a method that regularizes features vectors projected from different domains . WD-Match can be used to improve different text matching methods .
Outcome:	The proposed method outperforms existing methods and benchmarks on four datasets.

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

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

CRSLab: An Open-Source Toolkit for Building Conversational Recommender System (2021.acl-demo)

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

Kun Zhou, Xiaolei Wang, Yuanhang Zhou, Chenzhan Shang, Yuan Cheng, Wayne Xin Zhao, Yaliang Li, Ji-Rong Wen

Mitigating Action-Relation Hallucinations in LVLMs via Relation-aware Visual Enhancement (2026.acl-long)

Challenge:	Existing studies on conversational recommender systems lack a unified and standardized implementation or comparison.
Approach:	They propose to use a unified framework and highly-decoupled modules to develop CRSs.
Outcome:	The proposed framework collects 6 commonly used human-annotated CRS datasets and implements 19 models that include advanced techniques such as graph neural networks and pre-training models.

Copied to clipboard

Zhenxin Qin, Qiang Li, Qingzhuo Wang, Ruiyang Qin, Zhihua Wei, Wen Shen

Odysseus Navigates the Sirens’ Song: Dynamic Focus Decoding for Factual and Diverse Open-Ended Text Generation (2025.acl-long)

Challenge:	Existing research has focused on mitigating object hallucinations but often overlooks more complex relation hallucines, especially action relations involving interactions between objects.
Approach:	They propose a framework to locate action-relevant image regions and enhance the LVLM’s attention to those regions by using a Relation-aware Visual Enhancement method.
Outcome:	The proposed method achieves superior performance in mitigating action-relation hallucinations with negligible additional inference cost.

Copied to clipboard

Wen Luo, Feifan Song, Wei Li, Guangyue Peng, Shaohang Wei, Houfeng Wang

Text Generation

Challenge:	Existing decoding methods struggle to balance factuality and diversity . Deterministic decoding approaches suffer from degeneration and lack of diversity - a problem that is not addressed by the current literature.
Approach:	They propose a plug-and-play stochastic approach that adjusts decoding focus based on distributional differences across layers, leveraging the modular nature of factual knowledge within LLMs.
Outcome:	Extensive experiments on seven datasets show that DFD significantly improves performance.

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

Copied to clipboard

Xuexiang Wen, Hang Yu, Linchao Zhu, Gaoang Wang

RESIN: A Dockerized Schema-Guided Cross-document Cross-lingual Cross-media Information Extraction and Event Tracking System (2021.naacl-demos)

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

Haoyang Wen, Ying Lin, Tuan Lai, Xiaoman Pan, Sha Li, Xudong Lin, Ben Zhou, Manling Li, Haoyu Wang, Hongming Zhang, Xiaodong Yu, Alexander Dong, Zhenhailong Wang, Yi Fung, Piyush Mishra, Qing Lyu, Dídac Surís, Brian Chen, Susan Windisch Brown, Martha Palmer, Chris Callison-Burch, Carl Vondrick, Jiawei Han, Dan Roth, Shih-Fu Chang, Heng Ji

Visual Data in NLP

Challenge:	We present a new information extraction system that can construct temporal event graphs from news documents.
Approach:	They propose a temporal event graph extraction system that can extract news documents . they extend the system from sentence-level event extraction to cross-document cross-media event extraction .
Outcome:	The proposed system can extract temporal event graphs from news documents in multiple languages and multiple data modalities.

Detecting Stealthy Backdoor Samples based on Intra-class Distance for Large Language Models (2025.findings-emnlp)

Copied to clipboard

Jinwen Chen, Hainan Zhang, Fei Sun, Qinnan Zhang, Sijia Wen, Ziwei Wang, Zhiming Zheng

Attribution-Based Analysis and Optimization of Modular Agentic Workflows (2026.findings-acl)

Challenge:	Existing detectors use classifier-style probability signals or rely on rewriting, which can degrade quality and introduce new triggers.
Approach:	They propose to efficiently remove poisoned examples before or during fine-tuning .
Outcome:	The proposed method outperforms prior detectors on two machine translation datasets and one QA dataset.

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.

Beyond Hard Masks: Progressive Token Evolution for Diffusion Language Models (2026.acl-long)

Copied to clipboard

Linhao Zhong, Linyu Wu, Bozhen Fang, Tianjian Feng, Chenchen Jing, Wen Wang, Jiaheng Zhang, Hao Chen, Chunhua Shen

Advancing Precise Outline-Conditioned Text Generation with Task Duality and Explicit Outline Control (2024.eacl-long)

Challenge:	Existing Diffusion Language Models rely on hard binary masking and discrete token assignments, which hinder the revision of early decisions.
Approach:	They propose a diffusion-based language modeling approach that replaces hard binary masks with evolving soft token distributions.
Outcome:	The proposed approach outperforms existing DLMs on multiple benchmarks.

Copied to clipboard

Yunzhe Li, Qian Chen, Weixiang Yan, Wen Wang, Qinglin Zhang, Hari Sundaram

FaithLM: Towards Faithful Explanations for Large Language Models (2026.eacl-long)

Challenge:	Existing studies on outline-conditioned text generation focus on generating text using provided outlines as rough sketches, but lack of clarity and rationality of the rough outlines hampers quality of the generated text.
Approach:	They propose a novel task that requires generating stories based on specific, sentence-level outlines.
Outcome:	The proposed framework improves the quality of precise outline-conditioned text generation.

Copied to clipboard

Yu-Neng Chuang, Guanchu Wang, Chia-Yuan Chang, Ruixiang Tang, Shaochen Zhong, Fan Yang, Andrew Wen, Mengnan Du, Xuanting Cai, Vladimir Braverman, Xia Hu

Explainability & Interpretability in NLP

Challenge:	Large language models (LLMs) produce natural language explanations, but they lack faithfulness and do not reflect the evidence the model uses to decide.
Approach:	They propose a model-agnostic framework that evaluates and improves the faithfulness of LLM explanations without token masking or task-specific heuristics.
Outcome:	The proposed framework improves faithfulness of large language models without masking or heuristics.

Logic-Thinker: Teaching Large Language Models to Think more Logically. (2025.findings-emnlp)

Copied to clipboard

Chengyao Wen, Qiang Cheng, Shaofei Wang, Zhizhen Liu, Deng Zhao, Lei Liang

RESIN-11: Schema-guided Event Prediction for 11 Newsworthy Scenarios (2022.naacl-demo)

Challenge:	Recent Large Reasoning Models (LRMs) have demonstrated the ability to generate long chains of thought (LongCoT) LongCoT still faces challenges such as redundancy and logical incoherence.
Approach:	They propose a neural-symbolic reasoning framework that generates chains of thought . they propose Logic-Thinker, which transforms symbolic solvers into chains of thoughts .
Outcome:	The proposed framework outperforms models fine-tuned with ThinkerCoT on logic reasoning tasks.

Copied to clipboard

Xinya Du, Zixuan Zhang, Sha Li, Pengfei Yu, Hongwei Wang, Tuan Lai, Xudong Lin, Ziqi Wang, Iris Liu, Ben Zhou, Haoyang Wen, Manling Li, Darryl Hannan, Jie Lei, Hyounghun Kim, Rotem Dror, Haoyu Wang, Michael Regan, Qi Zeng, Qing Lyu, Charles Yu, Carl Edwards, Xiaomeng Jin, Yizhu Jiao, Ghazaleh Kazeminejad, Zhenhailong Wang, Chris Callison-Burch, Mohit Bansal, Carl Vondrick, Jiawei Han, Dan Roth, Shih-Fu Chang, Martha Palmer, Heng Ji

PKAG-DDI: Pairwise Knowledge-Augmented Language Model for Drug-Drug Interaction Event Text Generation (2025.acl-long)

Challenge:	Existing methods for event prediction are incomplete and noisy.
Approach:	They propose to use news-related event schemas to extract newsworthy events . they build a demo website and include a video demonstrating the framework .
Outcome:	The proposed framework can be applied to a wide variety of newsworthy scenarios.

Copied to clipboard

Ziyan Wang, Zhankun Xiong, Feng Huang, Wen Zhang

PAIR: Leveraging Passage-Centric Similarity Relation for Improving Dense Passage Retrieval (2021.findings-acl)

Challenge:	Drug-drug interactions arise when multiple drugs are administered concurrently.
Approach:	They propose a pairwise knowledge-augmented generative method for DDIE text generation that integrates biological functions from a knowledge set into a language model.
Outcome:	The proposed method outperforms existing methods in DDIE text generation on two professional datasets.

Copied to clipboard

Ruiyang Ren, Shangwen Lv, Yingqi Qu, Jing Liu, Wayne Xin Zhao, QiaoQiao She, Hua Wu, Haifeng Wang, Ji-Rong Wen

Pay More Attention to Relation Exploration for Knowledge Base Question Answering (2023.findings-acl)

Challenge:	Recent studies only consider query-centric similarity relation when learning the dual-encoder retriever.
Approach:	They propose a query-centric and PAssage-centric approach to capture more comprehensive similarity relations for dense passage retrieval.
Outcome:	The proposed approach significantly outperforms existing models on both MSMARCO and Natural Questions datasets.

Copied to clipboard

Yong Cao, Xianzhi Li, Huiwen Liu, Wen Dai, Shuai Chen, Bin Wang, Min Chen, Daniel Hershcovich

Training Language Model to Critique for Better Refinement (2025.findings-acl)

Challenge:	Existing approaches focus on entity representation and final answer reasoning, which results in limited supervision for this task.
Approach:	They propose a framework that utilizes relations to enhance entity representation and introduce additional supervision.
Outcome:	The proposed framework improves the F1 score on two benchmark datasets by 5.8% . it improves by 6.7% on WebQSP, better than state-of-the-art methods .

Copied to clipboard

Tianshu Yu, Chao Xiang, Mingchuan Yang, Pei Ke, Bosi Wen, Cunxiang Wang, Jiale Cheng, Li Zhang, Xinyu Mu, Chuxiong Sun, Minlie Huang

Demons in the Detail: On Implementing Load Balancing Loss for Training Specialized Mixture-of-Expert Models (2025.acl-long)

Challenge:	Large language models (LLMs) have remarkable evaluation and critique capabilities, providing insightful feedback and identifying flaws in various tasks.
Approach:	They propose a framework to train critic models using refinement signals to generate feedback loops where critiques guide the model in refining its responses.
Outcome:	The proposed framework outperforms traditional methods and open-source models in terms of critique quality and refinement outcomes.

Copied to clipboard

Zihan Qiu, Zeyu Huang, Bo Zheng, Kaiyue Wen, Zekun Wang, Rui Men, Ivan Titov, Dayiheng Liu, Jingren Zhou, Junyang Lin

Programming Languages in NLP

Challenge:	Existing Mixture-of-Experts training frameworks use a micro-batch to calculate LBL . micro-batches are restricted to a single sequence, preventing expert specialization .
Approach:	They propose to use a global-batch to loosen the load balance constraint for MoEs models . they propose to synchronize fi across micro-batches and then use it to calculate the LBL .
Outcome:	The proposed global-batch LBL improves the domain specialization of experts . the micro-battery LBL is almost at the sequence level, and the router is pushed to distribute the token evenly .

From Unaligned to Aligned: Scaling Multilingual LLMs with Multi-Way Parallel Corpora (2025.emnlp-main)

Copied to clipboard

Yingli Shen, Wen Lai, Shuo Wang, Ge Gao, Kangyang Luo, Alexander Fraser, Maosong Sun

Breaking the Evaluation Paradox: Evaluating High-Entropy Search with Computationally Irreducible Constraints (2026.findings-acl)

Challenge:	Experiments show that models trained on multi-way parallel data outperform those trained on unaligned data.
Approach:	They propose a large-scale, high-quality multi-way parallel corpus based on TED Talks that spans 113 languages with up to 50 languages aligned in parallel.
Outcome:	The proposed model outperforms models trained on unaligned multilingual data on six multilingual benchmarks.

Copied to clipboard

Juntao Wu, Wei Wen, Xianting Huang, Shuai Pang, Ruizhi Qiao, Xing Sun, Ke Wang

Efficient Self-Evaluation for Diffusion Language Models via Sequence Regeneration (2026.acl-long)

Challenge:	a new framework for evaluation of exhaustive search capabilities is needed . high-entropy enumeration tasks make such ground truth impossible for humans to create . VERITAS is a framework built on the principle of computationally irreducible constraints .
Approach:	They propose a framework that uses non-optimizable constraints to create verifiable searches . VERITAS can generate infinite number of test cases with perfect ground truth and precise difficulty control .
Outcome:	a new evaluation framework for large language models is based on non-optimizable constraints . the framework can generate infinite number of test cases with perfect ground truth and precise difficulty control .

Copied to clipboard

Linhao Zhong, Linyu Wu, Wen Wang, Yuling Xi, Chenchen Jing, Jiaheng Zhang, Hao Chen, Chunhua Shen

Illusions of the Gold Standard: A Large-scale Analysis of Human Evaluation Protocols for Long-form Text Generation (2026.acl-long)

Challenge:	Non-sequential and bidirectional nature of diffusion large language models makes direct likelihood-based self-evaluation challenging.
Approach:	They propose a self-evaluation confidence quantification method for diffusion large language models that quantifies confidence by computing the probability of regenerating tokens in the entire generated sequence, given the full context.
Outcome:	The proposed method is correlated with semantic coherence and answer accuracy.

Copied to clipboard

Katelyn X. Mei, Yi-Li Hsu, Minjoon Choi, Zongwan Cao, Chenjun Xu, Bingbing Wen, Su Lin Blodgett, Lucy Lu Wang

Text Generation

Challenge:	a large-scale analysis of human evaluation protocols for long-form generation tasks is lacking in current practice . current protocols lack proper standardization and operationalization, which can limit validity of evaluation .
Approach:	They conduct a large-scale analysis of human evaluation protocols for long-form generation tasks in *CL conference papers from 2023–2025.
Outcome:	The proposed evaluation protocols lack standardization and operationalization, the authors show . they also find that the evaluation protocols are inadequate for specific domains and tasks .

Original Content Is All You Need! an Empirical Study on Leveraging Answer Summary for WikiHowQA Answer Selection Task (2022.coling-1)

Copied to clipboard

Liang Wen, Juan Li, Houfeng Wang, Yingwei Luo, Xiaolin Wang, Xiaodong Zhang, Zhicong Cheng, Dawei Yin

MoDULA: Mixture of Domain-Specific and Universal LoRA for Multi-Task Learning (2024.emnlp-main)

Challenge:	Existing answer selection approaches for community question answering lack additional answer summaries due to redundancy and lengthiness issues of crowdsourced answers.
Approach:	They constructed a dataset which contains a corresponding reference summary for each original lengthy answer.
Outcome:	The proposed model improves the performance of a question and candidate answer on a WikiHowQA dataset.

Copied to clipboard

Yufei Ma, Zihan Liang, Huangyu Dai, Ben Chen, Dehong Gao, Zhuoran Ran, Wang Zihan, Linbo Jin, Wen Jiang, Guannan Zhang, Xiaoyan Cai, Libin Yang

MMATH: A Multilingual Benchmark for Mathematical Reasoning (2025.findings-emnlp)

Challenge:	Recent advances in open-source Large Language Models (LLMs) have achieved notable successes in natural language processing.
Approach:	They propose a Parameter Efficient Fine-Tuning paradigm for improved fine-tuning and parameter efficiency in multi-task learning.
Outcome:	The proposed model outperforms existing methods on multi-task learning while reducing training costs by over 80% without losing general capability.

Copied to clipboard

Wenyang Luo, Xin Zhao, Jing Sha, Shijin Wang, Ji-Rong Wen

Time-MQA: Time Series Multi-Task Question Answering with Context Enhancement (2025.acl-long)

Challenge:	a benchmark for multilingual complex reasoning spans 374 high-quality math problems across 10 typologically diverse languages.
Approach:	They propose a benchmark for multilingual complex reasoning across 10 languages . they show reasoning in English and answering in target languages can enhance performance .
Outcome:	The proposed benchmark demonstrates that models with high-quality reasoning can perform in multiple languages.

Copied to clipboard

Yaxuan Kong, Yiyuan Yang, Yoontae Hwang, Wenjie Du, Stefan Zohren, Zhangyang Wang, Ming Jin, Qingsong Wen

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

Challenge:	Existing time series models focus on a narrow spectrum of tasks, such as forecasting or anomaly detection.
Approach:	They propose a framework that enables natural language queries across multiple time series tasks such as numerical analytical tasks and open-ended question answering with reasoning.
Outcome:	The proposed framework enables natural language queries across multiple time series tasks and allows for more advanced and intuitive interactions with temporal data.

Copied to clipboard

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

OpenS2S: Advancing Fully Open-Source End-to-End Empathetic Large Speech Language Model (2025.emnlp-demos)

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

Chen Wang, Tianyu Peng, Wen Yang, YiNan Bai, Guangfu Wang, Jun Lin, Lanpeng Jia, Lingxiang Wu, Jinqiao Wang, Chengqing Zong, Jiajun Zhang

Unlocking Data-free Low-bit Quantization with Matrix Decomposition for KV Cache Compression (2024.acl-long)

Challenge:	Empathetic speech models are increasingly closed off, leaving details about the architecture, data and development opaque to researchers.
Approach:	They propose an open-source empathetic speech-to-text model with a streaming interleaved decoding architecture and a data pipeline to enable end-to end training.
Outcome:	The proposed model is open-source and transparent, with no data or data required to build it.

Copied to clipboard

Peiyu Liu, Ze-Feng Gao, Xin Zhao, Yipeng Ma, Tao Wang, Ji-Rong Wen

Green & Sustainable NLP

Challenge:	Existing methods to compress KV cache compromise precision or require extra data for calibration, limiting their practicality in LLM deployment.
Approach:	They propose a low-bit quantization technique based on tensor decomposition to effectively compress KV cache.
Outcome:	The proposed method reduces memory footprint and performance by 75% . it is compared with existing methods that compromise precision or require extra data for calibration .

DetermLR: Augmenting LLM-based Logical Reasoning from Indeterminacy to Determinacy (2024.acl-long)

Copied to clipboard

Hongda Sun, Weikai Xu, Wei Liu, Jian Luan, Bin Wang, Shuo Shang, Ji-Rong Wen, Rui Yan

T3-Vis: visual analytic for Training and fine-Tuning Transformers in NLP (2021.emnlp-demo)

Challenge:	Recent advances in large language models (LLMs) have revolutionized the landscape of reasoning tasks.
Approach:	They propose a new approach that rethinks the reasoning process as an evolution from indeterminacy to determinacy.
Outcome:	The proposed model surpasses all baselines on various logical reasoning benchmarks.

Copied to clipboard

Raymond Li, Wen Xiao, Lanjun Wang, Hyeju Jang, Giuseppe Carenini

A Survey of Large Language Models for Text-Guided Molecular Discovery: From Molecule Generation to Optimization (2026.acl-long)

Challenge:	Existing visual analytics tools have been shown to support the analysis and interpretation of deep learning models due to the inherent black-box nature of the models.
Approach:	They propose to use visual analytic framework to help researchers understand the model's intrinsic properties and behaviours through interactive visualization.
Outcome:	The proposed framework provides valuable insights about the model’s intrinsic properties and behaviours through interactive visualization and a suite of built-in algorithms.

Copied to clipboard

Ziqing Wang, Kexin Zhang, Zihan Zhao, Yibo Wen, Abhishek Pandey, Han Liu, Kaize Ding

Model-Based Imaginative Planning for Embodied Agents (2026.acl-long)

Challenge:	Large language models (LLMs) are introducing a paradigm shift in molecular discovery by enabling text-guided interaction with chemical spaces through natural language and symbolic notations.
Approach:	They analyze the current LLM learning paradigms to tackle four critical evaluation dimensions that have emerged as critical dimensions in recent studies.
Outcome:	The proposed models are able to interact with chemical spaces through natural language and symbolic notations, and have emerging extensions to incorporate multi-modal inputs.

Copied to clipboard

Junru Song, Hengzhe Jin, Yucong Huang, Tingsong Jiang, Weien Zhou, Feifei Wang, Yang Yang, Ying Wen, Wen Yao

NetSafe: Exploring the Topological Safety of Multi-agent System (2025.findings-acl)

Challenge:	a lightweight world model converts raw pixels into object-centric symbolic states amenable to language-based reasoning . IMPLEMENT is a framework for grounding language agents in visual embodied environments .
Approach:	They propose a model-based reasoning framework that enables frozen large language models to perform imaginative planning.
Outcome:	The proposed framework can be used to ground language agents in visual embodied environments.

Copied to clipboard

Miao Yu, Shilong Wang, Guibin Zhang, Junyuan Mao, Chenlong Yin, Qijiong Liu, Kun Wang, Qingsong Wen, Yang Wang

Challenge:	Large language models (LLMs) have fueled significant progress in intelligent Multi-agent Systems (MAS), with expanding academic and industrial applications.
Approach:	They propose a framework that unifies diverse MAS workflows via iterative RelCom interactions to enable generalized analysis.
Outcome:	The proposed framework unifies diverse MAS workflows via iterative RelCom interactions to enable generalized analysis.

DR-HM: Distill-then-Reinforce Training with Cognition-Aware Data Synthesis for Harmful Meme Detection (2026.findings-acl)

Copied to clipboard

Zihan Cheng, Jianxiang Ma, Xiaocui Yang, Peidong Wang, Wen Zhang, Shi Feng, Daling Wang, Yifei Zhang, Mingfu Zhang

OmniFlatten: An End-to-end GPT Model for Seamless Voice Conversation (2025.acl-long)

Challenge:	Current methods for harmful meme detection lack the knowledge required to identify such hate . current methods lack the ability to identify cultural stereotypes and visual metaphors .
Approach:	They propose a framework that decomposes meme analysis into a human-inspired reasoning process . they propose DR-HM to transfer knowledge from closed-source models while mitigating biases .
Outcome:	The proposed framework outperforms existing methods on three benchmark datasets.

Copied to clipboard

Qinglin Zhang, Luyao Cheng, Chong Deng, Qian Chen, Wen Wang, Siqi Zheng, Jiaqing Liu, Hai Yu, Chao-Hong Tan, Zhihao Du, ShiLiang Zhang

Direct Large Language Model Alignment Through Self-Rewarding Contrastive Prompt Distillation (2024.acl-long)

Challenge:	Full-duplex spoken dialogue systems allow simultaneous bidirectional communication . low latency and natural interactions in full-duplice systems remains a challenge .
Approach:	They propose a multi-stage post-training scheme that adapts a text large language model into a speech-text dialogue LLM.
Outcome:	The proposed model can model human conversation behaviors with low latency and natural interactions with low delay.

Copied to clipboard

Aiwei Liu, Haoping Bai, Zhiyun Lu, Xiang Kong, Xiaoming Wang, Jiulong Shan, Meng Cao, Lijie Wen

Extracting and Combining Abilities For Building Multi-lingual Ability-enhanced Large Language Models (2025.emnlp-main)

Challenge:	Existing methods to evaluate preference data without human annotations are difficult . et al., 2022b) is effective for aligning large language models with human expectations .
Approach:	They propose a method to evaluate the response preference using output probabilities under contrastive prompts.
Outcome:	The proposed method could surpass the RLHF method without human-annotated preference data.

Copied to clipboard

Zhipeng Chen, Kun Zhou, Liang Song, Xin Zhao, Bingning Wang, Weipeng Chen, Ji-Rong Wen

Finding Influential Instances for Distantly Supervised Relation Extraction (2022.coling-1)

Challenge:	Existing work relies on training with multi-lingual ability-related data, which may not be available for low-resource languages.
Approach:	They propose a multi-lingual ability-enhanced LLM that extracts language-agnostic ability-related weights from LLMs and combine them across different languages by simple addition and subtraction operations without training.
Outcome:	The proposed approach extracts language-agnostic ability-related weights from LLMs and combine them across different languages without training.

Copied to clipboard

Zifeng Wang, Rui Wen, Xi Chen, Shao-Lun Huang, Ningyu Zhang, Yefeng Zheng

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

Challenge:	Distant supervision models suffer from high label noise and are not reliable for DS.
Approach:	They propose a model-agnostic instance sampling method for relation extraction (RE) by influence function, namely REIF.
Outcome:	The proposed method reduces the computational complexity from O(mn) to O(1), with analyzing its robustness on the selected sampling function.

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

Attention Weights as an Indicator: Analyzing and Improving Document Utilization in Retrieval-Augmented Generation (2026.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

Jing Jin, Yuhan Song, Wen Luo, Houfeng Wang

Learning to Detect Noisy Labels Using Model-Based Features (2022.findings-emnlp)

Challenge:	In traditional RAG models, documents are grouped into categories based on their quality and order, and the quality of inputs is variable due to ineffective retrievers or misalignment between the retriever and generator.
Approach:	They propose to use attention weights to enhance document utilization from three perspectives: document ranking, placement, and filtering.
Outcome:	The proposed method outperforms baselines and improves document utilization effectiveness in a training-free manner.

Copied to clipboard

Zhihao Wang, Zongyu Lin, Junjie Wen, Xianxin Chen, Peiqi Liu, Guidong Zheng, Yujun Chen, Zhilin Yang

Unveiling Factual Recall Behaviors of Large Language Models through Knowledge Neurons (2024.emnlp-main)

Challenge:	Existing approaches to reduce label noise rely on heuristics and sample losses.
Approach:	They propose a method that transfers the noise distribution to a clean set and trains a model to distinguish noisy labels from clean ones using model-based features.
Outcome:	Empirically, the proposed approach improves over strong baselines on a wide range of tasks including text classification and speech recognition.

Copied to clipboard

Yifei Wang, Yuheng Chen, Wanting Wen, Yu Sheng, Linjing Li, Daniel Zeng

Logic-guided Semantic Representation Learning for Zero-Shot Relation Classification (2020.coling-main)

Challenge:	Recent advances in Large Language Models have underscored their exceptional reasoning prowess with natural language understanding across a broad spectrum of tasks.
Approach:	They examine whether Large Language Models actively recall or retrieve their internal repositories of factual knowledge when faced with reasoning tasks.
Outcome:	The proposed model improves reasoning performance while suppressing it leads to notable degradation.

Copied to clipboard

Juan Li, Ruoxu Wang, Ningyu Zhang, Wen Zhang, Fan Yang, Huajun Chen

CaM-HG: Causal-Enhanced MoE and Hypergraphs Network for Incomplete Multimodal Emotion Recognition in Conversations (2026.findings-acl)

Challenge:	Existing methods to zero-shot relation classification can only identify seen relations . existing methods rely on descriptive information to improve understandability of relation types .
Approach:	They propose a logic-guided semantic representation learning model for zero-shot relation classification that builds connections between seen and unseen relations via implicit and explicit semantic representations with knowledge graph embeddings and logic rules.
Outcome:	The proposed model can generalize to unseen relation types and achieve promising improvements.

Copied to clipboard

Mingjian Yang, Yong Wang, Peng Liu, Wen Yin

Human Guided Exploitation of Interpretable Attention Patterns in Summarization and Topic Segmentation (2022.emnlp-main)

Challenge:	Existing methods that focus on statistical reconstruction often fail to bridge these gaps, effectively leaving semantic holes.
Approach:	They propose a Causal-Enhanced Mixture-of-Experts and Hypergraph Network to bridge missing features . they use experts to synthesize missing features that are realistic and causally consistent .
Outcome:	The proposed model synthesizes missing features that are realistic and causally consistent . it surpasses benchmarks on IEMOCAP, CMU-MOSI, and CMU MOSEI by 1.43% and 1.25% .

Copied to clipboard

Raymond Li, Wen Xiao, Linzi Xing, Lanjun Wang, Gabriel Murray, Giuseppe Carenini

Integrating Audio, Visual, and Semantic Information for Enhanced Multimodal Speaker Diarization on Multi-party Conversation (2025.acl-long)

Challenge:	Existing studies have investigated the multi-head self-attention mechanism of transformers.
Approach:	They propose to use a human-in-the-loop pipeline to discover task-specific attention patterns and inject them into transformer models to improve their accuracy.
Outcome:	The proposed methods improve the performance of transformer models by incorporating predefined patterns into their attention matrices.

Copied to clipboard

Luyao Cheng, Hui Wang, Chong Deng, Siqi Zheng, Yafeng Chen, Rongjie Huang, Qinglin Zhang, Qian Chen, Xihao Li, Wen Wang

Sticker-TTS: Learn to Utilize Historical Experience with a Sticker-driven Test-Time Scaling Framework (2025.emnlp-main)

Challenge:	Mainstream speaker diarization systems rely only on acoustic information, making it challenging in complex aural environments.
Approach:	They propose a multimodal approach that integrates audio, visual, and semantic cues to enhance speaker diarization.
Outcome:	The proposed approach outperforms state-of-the-art methods on multi-party conversations . it integrates audio-visual-semantic cues into the clustering process for acoustic speaker embeddings .

Copied to clipboard

Jie Chen, Jinhao Jiang, Yingqian Min, Zican Dong, Shijie Wang, Xin Zhao, Ji-Rong Wen

FEA-Bench: A Benchmark for Evaluating Repository-Level Code Generation for Feature Implementation (2025.acl-long)

Challenge:	Large reasoning models have exhibited strong performance on complex reasoning tasks, but current test-time scaling methods rely on redundant sampling and ignore historical experience utilization.
Approach:	They propose a test-time scaling framework that coordinates three collaborative LRMs to iteratively explore and refine solutions guided by historical attempts.
Outcome:	The proposed framework surpasses strong baselines on three mathematical reasoning benchmarks, including AIME-24, AIME-25, and OlymMATH.

Copied to clipboard

Wei Li, Xin Zhang, Zhongxin Guo, Shaoguang Mao, Wen Luo, Guangyue Peng, Yangyu Huang, Houfeng Wang, Scarlett Li

Programming Languages in NLP

Challenge:	Existing benchmarks focus on standalone programming problems, such as HumanEval, MBPP, and LiveCodeBench.
Approach:	They propose to use large language models to evaluate their ability to perform incremental development within code repositories by collecting pull requests from 83 GitHub repositorias and using rule-based and intent-based filtering to construct task instances focused on new feature development.
Outcome:	The proposed benchmarks show that large language models perform significantly worse in the FEA-Bench, highlighting considerable challenges in repository-level incremental code development.

Mnemis: Dual-Route Retrieval on Hierarchical Graphs for Long-Term LLM Memory (2026.acl-long)

Copied to clipboard

Zihao Tang, Xin Yu, Ziyu Xiao, Zengxuan Wen, Zelin Li, Jiaxi Zhou, Hualei Wang, Haohua Wang, Haizhen Huang, Weiwei Deng, Feng Sun, Qi Zhang

On Transferability of Prompt Tuning for Natural Language Processing (2022.naacl-main)

Challenge:	Existing methods for retrieving historical messages are based on similarity-based mechanisms.
Approach:	They propose a system that integrates System-1 similarity search with a complementary System-2 mechanism, termed Global Selection.
Outcome:	The proposed framework achieves state-of-the-art on long-term memory benchmarks and 93.9 on LoCoMo and 91.6 on LongMemEval-S.

Copied to clipboard

Yusheng Su, Xiaozhi Wang, Yujia Qin, Chi-Min Chan, Yankai Lin, Huadong Wang, Kaiyue Wen, Zhiyuan Liu, Peng Li, Juanzi Li, Lei Hou, Maosong Sun, Jie Zhou

Learn to Memorize: Scalable Continual Learning in Semiparametric Models with Mixture-of-Neighbors Induction Memory (2025.acl-long)

Challenge:	Pre-trained language models (PLMs) can achieve comparable performance to full-parameter fine-tuning by tuning a few soft prompts, but require much more training time than fine-timing.
Approach:	They empirically investigate the transferability of soft prompts across different downstream tasks and PLMs to determine what decides prompt transferability.
Outcome:	The proposed method can achieve comparable performance to full-parameter fine-tuning by tuning a few soft prompts, but requires much more training time than fine-timing.

Copied to clipboard

Guangyue Peng, Tao Ge, Wen Luo, Wei Li, Houfeng Wang

Gamma-Guard: Lightweight Residual Adapters for Robust Guardrails in Large Language Models (2025.emnlp-main)

Challenge:	Semiparametric language models (LMs) use static storage, which lacks learning capability and is disconnected from the internal information flow of the parametric models.
Approach:	They reconceptualize the non-parametric memory represented by kNN-LM as a learnable Mixture-of-Neighbors Induction Memory (MoNIM) this synergizes the induction capabilities of attention heads with the memorization strength of feed-forward networks .
Outcome:	The proposed model is a learnable Mixture-of-neighbors induction memory (MoNIM) it synergizes the induction capabilities of attention heads with the memorization strength of feed-forward networks (FFNs).

Copied to clipboard

Lijia Lv, Yuanshu Zhao, Guan Wang, Xuehai Tang, Wen Jie, Jizhong Han, Songlin Hu

Exploring All-In-One Knowledge Distillation Framework for Neural Machine Translation (2023.emnlp-main)

Challenge:	Large language models (LLMs) are widely deployed as zero-shot evaluators for answer grading, content moderation, and document ranking.
Approach:	They propose a system that trains LLMs with adapters to denoise embeddings and refocus attention.
Outcome:	The proposed model lifts adversarial accuracy from 5% to 95% a 90 percentage-point gain while reducing clean-data accuracy by just 8 percentage points.

Copied to clipboard

Zhongjian Miao, Wen Zhang, Jinsong Su, Xiang Li, Jian Luan, Yidong Chen, Bin Wang, Min Zhang

Toolscaler: Scalable Generative Tool Calling via Structure-Aware Semantic Tokenization (2025.findings-emnlp)

Challenge:	Existing knowledge distillation methods only obtain one lightweight student each time . this could be resource-intensive and resulting in multiple students not being optimally utilized .
Approach:	They propose a knowledge distillation framework which generates multiple satisfactory students at once.
Outcome:	The proposed framework generates multiple satisfactory students at once.

Copied to clipboard

Yunyue Su, Zhang Jinshuai, Bowen Fang, Wen Ye, Jinghao Zhang, Bowen Song, Weiqiang Wang, Qiang Liu, Liang Wang

Syntactic Text Processing

Challenge:	Extensive experiments demonstrate the effectiveness of SGTC across various tasks.
Approach:	They propose a generative tool invocation framework that introduces structure-aware semantic tokenization to encode tools as discrete code sequences.
Outcome:	The proposed framework reduces the size of the representation space and underutilizes collaborative signals among tools in downstream tasks.

Label-Free Distant Supervision for Relation Extraction via Knowledge Graph Embedding (D18-1)

Copied to clipboard

Guanying Wang, Wen Zhang, Ruoxu Wang, Yalin Zhou, Xi Chen, Wei Zhang, Hai Zhu, Huajun Chen

Filter-And-Refine: A MLLM Based Cascade System for Industrial-Scale Video Content Moderation (2025.acl-industry)

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

Zixuan Wang, Jinghao Shi, Hanzhong Liang, Xiang Shen, Vera Wen, Zhiqian Chen, Yifan Wu, Zhixin Zhang, Hongyu Xiong

LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Models (2026.acl-long)

Challenge:	Effective content moderation is essential for video platforms to safeguard user experience and uphold community standards.
Approach:	They propose a method to transform a generative MLLM into a multimodal classifier using minimal discriminative training data.
Outcome:	The proposed method improves F1 score by 66.50% over traditional classifiers while requiring only 2% of the fine-tuning data.

Copied to clipboard

Fengqi Zhu, Rongzhen Wang, Shen Nie, Xiaolu Zhang, Chunwei Wu, Jun Zhou, Yankai Lin, Ji-Rong Wen, Chongxuan Li

MPPO: Multi Pair-wise Preference Optimization for LLMs with Arbitrary Negative Samples (2025.coling-main)

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

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.

On Synthetic Data Strategies for Domain-Specific Generative Retrieval (2025.acl-long)

Copied to clipboard

Haoyang Wen, Jiang Guo, Yi Zhang, Jiarong Jiang, Zhiguo Wang

Query Distillation: BERT-based Distillation for Ensemble Ranking (2020.coling-industry)

Challenge:	Generative retrieval models can be used to generate ranked lists of potentially relevant document identifiers for a user query.
Approach:	They propose a synthetic data generation strategy for a two-stage training framework that focuses on learning to decode document identifiers from queries and a strategy for mining hard negatives based on initial model's predictions.
Outcome:	The proposed model can generate ranked lists of potentially relevant document identifiers for a user query and then refine ranking through preference learning.

Copied to clipboard

Wangshu Zhang, Junhong Liu, Zujie Wen, Yafang Wang, Gerard de Melo

GenesisFunc: Multi-Agent Data Generation for Accurate and Generalizable Function-Calling (2026.acl-long)

Challenge:	Recent years have witnessed substantial progress in the development of neural ranking networks, but an increasingly heavy computational burden due to growing numbers of parameters and the adoption of model ensembles.
Approach:	They propose a two-stage distillation method that allows a smaller student model to be trained while benefiting from the better performance of the teacher model.
Outcome:	The proposed method shows higher-quality rankings compared to the teacher model.

Copied to clipboard

Hao-Xiang Xu, Chong Deng, Jiaqing Liu, Wen Wang, Qian Chen, Lujia Bao, Xiangang Li, Zhen-Hua Ling

Challenge:	Large Language Models (LLMs) extend their capabilities through function-calling (FC) however, obtaining and annotating real function-called data is challenging, and synthetic data from existing pipelines suffers from unreliable APIs, limited tool scalability, insufficient diversity, and weak quality control.
Approach:	They propose a pipeline for generating FC training data using reliable tools and a multi-agent framework that supports a dialogue generation system that produces conversations spanning diverse scenarios.
Outcome:	The proposed pipeline outperforms open-source models in in-domain FC performance and out-of-domain generalization while reaching FC capabilities comparable to some of the latest API-based models.

JX4MEI: Multimodal Semantically-Enhanced LLM for Joint Multimodal Emotion-Intent Explanation and Classification (2026.findings-acl)

Copied to clipboard

YiJie Huang, Xiaocui Yang, Shi Feng, Daling Wang, Yifei Zhang, Ning Yuan, Zhuoyue Jia, Wen Zhang

Finding Skill Neurons in Pre-trained Transformer-based Language Models (2022.emnlp-main)

Challenge:	Existing multimodal emotion and intent recognition tasks focus on classification, not rationale and intrinsic connections between these states.
Approach:	They propose a task that requires models to jointly predict emotion and intent while generating natural language explanations for why they co-occur.
Outcome:	The proposed model outperforms baseline models in prediction and explanation generation.

Copied to clipboard

Xiaozhi Wang, Kaiyue Wen, Zhengyan Zhang, Lei Hou, Zhiyuan Liu, Juanzi Li

Towards Effective and Efficient Continual Pre-training of Large Language Models (2025.acl-long)

Challenge:	Pre-trained language models have demonstrated superior performance on various natural language processing tasks.
Approach:	They find that after prompt tuning, some neurons encode task-specific skills . they also show that skill neurons are most likely generated in pre-training .
Outcome:	The neurons are highly predictive of task labels after prompt tuning for specific tasks.

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

IF-CRITIC: Towards a Fine-Grained LLM Critic for Instruction-Following Evaluation (2026.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

Bosi Wen, Yilin Niu, Cunxiang Wang, Pei Ke, Xiaoying Ling, Ying Zhang, Aohan Zeng, Hongning Wang, Minlie Huang

Challenge:	Existing evaluation models for instruction-following have many shortcomings, such as substantial costs and unreliable assessments.
Approach:	They propose an LLM critic for fine-grained instruction-following evaluation using a checklist generator and a constraint-level preference optimization method.
Outcome:	The proposed model beats strong LLM-as-a-Judge baselines in evaluations under lower computational overhead compared to baselines.

IF-RewardBench: Benchmarking Judge Models for Instruction-Following Evaluation (2026.acl-long)

Copied to clipboard

Bosi Wen, Yilin Niu, Cunxiang Wang, Xiaoying Ling, Ying Zhang, Pei Ke, Hongning Wang, Minlie Huang

Challenge:	Existing benchmarks for instruction-following lack data coverage and oversimplified pairwise evaluation paradigms that misalign with model optimization scenarios.
Approach:	They propose a meta-evaluation benchmark for instruction-following that covers diverse instruction and constraint types and a preference graph for each instruction.
Outcome:	Extensive experiments on IF-RewardBench show that the proposed benchmark achieves a stronger positive correlation with downstream task performance compared to existing benchmarks.

PlanGPT-VL: Enhancing Urban Planning with Domain-Specific Vision-Language Models (2025.emnlp-industry)

Copied to clipboard

He Zhu, Junyou Su, Minxin Chen, Wen Wang, Yijie Deng, Guanhua Chen, Wenjia Zhang

SDGO: Self-Discrimination-Guided Optimization for Consistent Safety in Large Language Models (2025.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

Peng Ding, Wen Sun, Dailin Li, Wei Zou, Jiaming Wang, Jiajun Chen, Shujian Huang

Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentation (2025.coling-main)

Challenge:	Large Language Models (LLMs) excel at various tasks but are vulnerable to jailbreak attacks that induce harmful content generation.
Approach:	They propose a reinforcement learning framework that leverages the model’s own discrimination capabilities as a reward signal to enhance generation safety through iterative self-improvement.
Outcome:	The proposed framework improves model safety by iterative self-improvement without additional annotated data or external models during training phase.

Copied to clipboard

Ruiyang Ren, Yuhao Wang, Yingqi Qu, Wayne Xin Zhao, Jing Liu, Hua Wu, Ji-Rong Wen, Haifeng Wang

OmniEval: An Omnidirectional and Automatic RAG Evaluation Benchmark in Financial Domain (2025.emnlp-main)

Challenge:	Large language models (LLMs) have shown impressive prowess in solving a wide range of tasks with world knowledge, but it remains unclear how well they perceive their factual knowledge boundaries.
Approach:	They propose to use a retrieval augmentation approach to enhance LLMs' awareness of factual knowledge boundaries to analyze factual and factual information in open-domain question answering (QA)
Outcome:	The proposed method improves LLMs’ QA and judgemental capabilities by integrating supporting documents with the questions.

Copied to clipboard

Shuting Wang, Jiejun Tan, Zhicheng Dou, Ji-Rong Wen

How to Make Large Language Models Generate 100% Valid Molecules? (2025.emnlp-main)

Challenge:	a new benchmark for RAG is developed for the financial domain . omnidirectional and automatic benchmarks are difficult to build in vertical domains .
Approach:	They propose an omnidirectional and automatic RAG benchmark for the financial domain . they categorize RAG scenarios by task classes and 16 financial topics .
Outcome:	The proposed benchmark achieves an 87.47% acceptance ratio in human evaluations of generated instances.

Copied to clipboard

Wen Tao, Jing Tang, Alvin Chan, Bryan Hooi, Baolong Bi, Nanyun Peng, Yuansheng Liu, Yiwei Wang

GRACE: Gradient-guided Controllable Retrieval for Augmenting Attribute-based Text Generation (2023.findings-acl)

Challenge:	Large language models (LLMs) can learn to perform a wide range of tasks, but generating valid molecules using representations like SMILES is challenging in few-shot settings.
Approach:	They propose a language framework that converts invalid SMILES to SELFIES and LLMs as post-hoc correctors to ensure that the molecules generated by LLM are 100% valid.
Outcome:	The proposed model performs worse with SELFIES than with SMILES and improves on other metrics.

Copied to clipboard

Zhihua Wen, Zhiliang Tian, Zhen Huang, Yuxin Yang, Zexin Jian, Changjian Wang, Dongsheng Li

AutoAlign: Get Your LLM Aligned with Minimal Annotations (2025.acl-demo)

Challenge:	Existing methods for controlling the generation of pre-trained language models infuse domain bias into the generation process, making it difficult to generate out-of-domain texts.
Approach:	They propose a retrieval-augmented generation framework that uses retrieval to generate fluent sentences with high attribute relevance.
Outcome:	The proposed method can generate fluent sentences with high attribute relevance while keeping domain bias out of the model.

Copied to clipboard

Xinyu Lu, Dong Xu, Chunkang Zhang, Xinyan Guan, Junxiang Wang, Qingyu Zhang, Pengbo Wang, Yingzhi Mao, Hao Xiang, Xueru Wen, Zichao Li, Yaojie Lu, Hongyu Lin, Le Sun, Xianpei Han

Ditto: A Simple and Efficient Approach to Improve Sentence Embeddings (2023.emnlp-main)

Challenge:	Automated Alignment (ALM) is a set of algorithms designed to align Large Language Models (LLMs) with human intentions and values while minimizing manual intervention.
Approach:	They propose an open-source toolkit that integrates mainstream automated algorithms through a consistent interface and an accessible workflow supporting one-click execution for prompt synthesis and automatic alignment signal construction.
Outcome:	The proposed framework enables easy reproduction of existing results through extensive benchmarks and facilitates the development of novel approaches via modular components.

Copied to clipboard

Qian Chen, Wen Wang, Qinglin Zhang, Siqi Zheng, Chong Deng, Hai Yu, Jiaqing Liu, Yukun Ma, Chong Zhang

Beyond the Surface: A Solution-Aware Retrieval Model for Competition-level Code Generation (2025.findings-emnlp)

Challenge:	Prior studies diagnose the anisotropy problem in sentence embeddings from pre-trained language models without fine-tuning.
Approach:	They propose an unsupervised method that weights words with model-based importance estimations and computes the weighted average of word representations from pre-trained models as sentence embeddings.
Outcome:	Empirical evaluations show that the proposed method can alleviate the anisotropy problem and improve various pre-trained models on the STS benchmarks.

Copied to clipboard

Shiwen Zhang, Lingxiang Wang, Hainan Zhang, Ziwei Wang, Sijia Wen, Zhiming Zheng

Text Generation

Challenge:	Existing retrieval models emphasize surface-level semantic similarity, neglecting deeper solution-level logical similarities.
Approach:	They propose a solution-aware ranking model empowered by synthetic data for competitive programming tasks.
Outcome:	The proposed ranking model outperforms existing retrieval models in precision and recall metrics.

Active Listening: Personalized Question Generation in Open-Domain Social Conversation with User Model Based Prompting (2024.findings-emnlp)

Copied to clipboard

Kevin Bowden, Yue Fan, Winson Chen, Wen Cui, Davan Harrison, Xin Wang, Marilyn Walker

Low-Resource NLP

Challenge:	Existing work shows that users of conversational systems want a more personalized experience . Question Generation tasks focus on factual questions from textual excerpts .
Approach:	They hypothesize that conversational systems want a more personalized experience . they use large language models capable of casual conversation to generate PQs .
Outcome:	The proposed model produces the most natural and engaging responses against competing models.

RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-ranking (2021.emnlp-main)

Copied to clipboard

Ruiyang Ren, Yingqi Qu, Jing Liu, Wayne Xin Zhao, QiaoQiao She, Hua Wu, Haifeng Wang, Ji-Rong Wen

The Agent’s First Day: Benchmarking Learning, Exploration, and Scheduling in the Workplace Scenarios (2026.findings-acl)

Challenge:	Recent studies show that passage retrieval and passage reranking are important for achieving mutual improvement.
Approach:	They propose a unified listwise training approach for passage retrieval and passage reranking that incorporates a retrieval procedure and a hybrid data augmentation strategy.
Outcome:	The proposed approach improves on both MSMARCO and Natural Questions datasets.

Copied to clipboard

Daocheng Fu, Jianbiao Mei, Rong Wu, Xuemeng Yang, Jia Xu, Ding Wang, Pinlong Cai, Yong Liu, Licheng Wen, Botian Shi

Challenge:	Existing research mainly focuses on performance upper bounds in static environments, overlooking stochastic real-world deployment.
Approach:	They propose a dynamic evaluation environment that simulates a "trainee" agent continuously exploring a novel setting.
Outcome:	The proposed model evaluates agents in a dynamic evaluation environment that simulates a "trainee" agent continuously exploring a novel setting.

Continual Pre-training of Language Models for Math Problem Understanding with Syntax-Aware Memory Network (2022.acl-long)

Copied to clipboard

Zheng Gong, Kun Zhou, Xin Zhao, Jing Sha, Shijin Wang, Ji-Rong Wen

DynamicNER: A Dynamic, Multilingual, and Fine-Grained Dataset for LLM-based Named Entity Recognition (2025.emnlp-main)

Challenge:	a fundamental challenge in modeling math problems is how to fuse semantics of textual description and formulas.
Approach:	They propose a method to continually pre-train language models for improving understanding of math problems with syntax-aware memory networks.
Outcome:	The proposed approach outperforms competitive baselines on four math tasks.

Copied to clipboard

Hanjun Luo, Yingbin Jin, Yiran Wang, Xinfeng Li, Tong Shang, Xuecheng Liu, Ruizhe Chen, Kun Wang, Hanan Salam, Qingsong Wen, Zuozhu Liu

HearSay Benchmark: Do Audio LLMs Leak What They Hear? (2026.findings-acl)

Challenge:	Existing datasets designed for Named Entity Recognition methods are inadequate for LLMs.
Approach:	They propose a dataset that is multilingual and multi-granular and enables LLMs to be applied to Named Entity Recognition methods.
Outcome:	The proposed dataset is multilingual and multi-granular, covering 8 languages and 155 entity types, with corpora spanning a diverse range of domains.

Copied to clipboard

Jin Wang, Kaiwen Luo, Liang Lin, Weiliu Wang, Yitian Chen, Moayad Aloqaily, Xuehai Tang, Zhenhong Zhou, Kun Wang, Li Sun, Qingsong Wen

ControlSpeech: Towards Simultaneous and Independent Zero-shot Speaker Cloning and Zero-shot Language Style Control (2025.acl-long)

Challenge:	Recent advances in audio large language models have led to their potential privacy implications unexplored.
Approach:	They propose a benchmark to examine whether ALLMs leak user privacy through acoustic voiceprints.
Outcome:	The proposed benchmark is constructed from over 22,000 real-world audio clips.

Copied to clipboard

Shengpeng Ji, Qian Chen, Wen Wang, Jialong Zuo, Minghui Fang, Ziyue Jiang, Hai Huang, Zehan Wang, Xize Cheng, Siqi Zheng, Zhou Zhao

RAGLAB: A Modular and Research-Oriented Unified Framework for Retrieval-Augmented Generation (2024.emnlp-demo)

Challenge:	Prior zero-shot TTS models only mimic the speaker’s voice without further control and adjustment capabilities while prior controllable TTS systems cannot perform speaker-specific voice generation.
Approach:	They propose a style control module that captures codec representations corresponding to timbre, content, and style in a discrete decoupling codec space.
Outcome:	The proposed system can fully clone the speaker's voice and perform speech-specific adjustment and control functions.

Copied to clipboard

Xuanwang Zhang, Yun-Ze Song, Yidong Wang, Shuyun Tang, Xinfeng Li, Zhengran Zeng, Zhen Wu, Wei Ye, Wenyuan Xu, Yue Zhang, Xinyu Dai, Shikun Zhang, Qingsong Wen

Digging out Discrimination Information from Generated Samples for Robust Visual Question Answering (2023.findings-acl)

Challenge:	Existing research on Retrieval Augmented Generation (RAG) does not address the problem of hallucinations and real-time updating of knowledge.
Approach:	They propose a modular open-source library to equip LLMs with external knowledge.
Outcome:	The proposed approach reduces the need for expensive open-source tools and lacks fair comparisons between novel RAG algorithms.

Copied to clipboard

Zhiquan Wen, Yaowei Wang, Mingkui Tan, Qingyao Wu, Qi Wu

Towards Topic-Guided Conversational Recommender System (2020.coling-main)

Challenge:	Existing methods to solve this problem rely on additional annotations and generate negative samples .
Approach:	They propose a method to Dig out Discrimination information from Generated samples to address these limitations.
Outcome:	The proposed method improves on the visual question-answering datasets.

Copied to clipboard

Kun Zhou, Yuanhang Zhou, Wayne Xin Zhao, Xiaoke Wang, Ji-Rong Wen

REAR: A Relevance-Aware Retrieval-Augmented Framework for Open-Domain Question Answering (2024.emnlp-main)

Challenge:	Existing CRS datasets focus on immediate requests from users, while lack proactive guidance to the recommendation scenario.
Approach:	They propose a topic-guided conversational recommendation dataset . it incorporates topic threads to enforce natural semantic transitions towards the recommendation scenario .
Outcome:	The proposed approach is more reasonable and controllable than previous approaches.

Copied to clipboard

Yuhao Wang, Ruiyang Ren, Junyi Li, Xin Zhao, Jing Liu, Ji-Rong Wen

Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding (2025.findings-acl)

Challenge:	Existing methods to extend knowledge scope of large language models (LLMs) lack internal parametric knowledge, resulting in misusing external knowledge.
Approach:	They propose a retrieval-augmented approach that provides LLMs with potentially relevant documents through a module.
Outcome:	The proposed approach outperforms existing methods on four open-domain QA tasks.

Copied to clipboard

Feifan Song, Shaohang Wei, Wen Luo, Yuxuan Fan, Tianyu Liu, Guoyin Wang, Houfeng Wang

Improving Retrospective Language Agents via Joint Policy Gradient Optimization (2025.naacl-long)

Challenge:	Low-resource methods for LLM alignment have been popular, but still face challenges in obtaining high-quality and aligned content.
Approach:	They propose a framework to enhance alignment ability of base models by the guidance of a small aligned model.
Outcome:	The proposed framework outperforms baseline methods while avoiding degradation on downstream tasks.

Copied to clipboard

Xueyang Feng, Bo Lan, Quanyu Dai, Lei Wang, Jiakai Tang, Xu Chen, Zhenhua Dong, Ji-Rong Wen

A Survey of Mathematical Reasoning in the Era of Multimodal Large Language Model: Benchmark, Method & Challenges (2025.findings-acl)

Challenge:	Recent advances in large language models have sparked interest in creating autonomous agents.
Approach:	They propose a framework that jointly optimizes both task-planning and self-reflective evolution capabilities in language agents.
Outcome:	The proposed framework improves task planning and self-reflective evolution capabilities in language agents.

Copied to clipboard

Yibo Yan, Jiamin Su, Jianxiang He, Fangteng Fu, Xu Zheng, Yuanhuiyi Lyu, Kun Wang, Shen Wang, Qingsong Wen, Xuming Hu

Implicit Cross-Lingual Rewarding for Efficient Multilingual Preference Alignment (2025.findings-acl)

Challenge:	This survey provides the first comprehensive analysis of mathematical reasoning in the era of multimodal large language models . integrating large language model with mathematical reasoning tasks is becoming significant as AI advances .
Approach:	They review over 200 studies published since 2021 and examine the state-of-the-art developments in Math-LLMs . they identify five major challenges hindering the realization of AGI in this domain .
Outcome:	The authors examine the state-of-the-art developments in Math-LLMs with a focus on multimodal settings.

Copied to clipboard

Wen Yang, Junhong Wu, Chen Wang, Chengqing Zong, Jiajun Zhang

Progressive Self-Training with Discriminator for Aspect Term Extraction (2021.emnlp-main)

Challenge:	Existing approaches to align English LLMs with human preferences rely on expensive human annotations or advanced multilingual preference alignment models.
Approach:	They propose a method that captures learned preferences from English models by implicit rewards . they annotate preference relations in cross-lingual instruction-following pairs using English .
Outcome:	The proposed approach captures learned preferences from well-aligned English models by implicit rewards and transfers them to other languages through iterative training.

Copied to clipboard

Qianlong Wang, Zhiyuan Wen, Qin Zhao, Min Yang, Ruifeng Xu

Adaptive Schema-aware Event Extraction with Retrieval-Augmented Generation (2025.findings-emnlp)

Challenge:	Existing approaches to extract aspect terms from review sentences are limited due to lack of annotated data.
Approach:	They propose to refine conventional self-training to progressive self-teaching to reduce noise . they use a discriminator to filter the noisy pseudo-labels.
Outcome:	The proposed model outperforms baseline models and achieves state-of-the-art performance on four SemEval datasets.

Copied to clipboard

Sheng Liang, Hang Lv, Zhihao Wen, Yaxiong Wu, Yongyue Zhang, Hao Wang, Yong Liu

Rethinking the Evaluation for Conversational Recommendation in the Era of Large Language Models (2023.emnlp-main)

Challenge:	Event extraction is a task in natural language processing that involves identifying and extracting event information from unstructured text.
Approach:	They propose a paradigm that combines schema paraphrasing with schema retrieval-augmented generation.
Outcome:	The proposed paradigm retrieves paraphrased schemas and accurately generates targeted structures.

Copied to clipboard

Xiaolei Wang, Xinyu Tang, Xin Zhao, Jingyuan Wang, Ji-Rong Wen

MathAgent: Leveraging a Mixture-of-Math-Agent Framework for Real-World Multimodal Mathematical Error Detection (2025.acl-industry)

Challenge:	Existing evaluation protocols for large language models (LLMs) are inadequate for conversational recommender systems.
Approach:	They propose an evaluation approach based on LLMs that harnesses LLM-based user simulators to evaluate ChatGPT's performance.
Outcome:	The proposed evaluation approach can simulate various system-user interaction scenarios.

Copied to clipboard

Yibo Yan, Shen Wang, Jiahao Huo, Philip S. Yu, Xuming Hu, Qingsong Wen

Language-Specific Neurons: The Key to Multilingual Capabilities in Large Language Models (2024.acl-long)

Challenge:	Multimodal Large Language Models (MLLMs) struggle with identifying and categorizing student errors in multimodal mathematical contexts.
Approach:	They propose a new framework that decomposes error detection into three phases with specialized agents.
Outcome:	The proposed framework shows higher accuracy in error step identification and 3% improvement in error categorization on real-world educational data.

Copied to clipboard

Tianyi Tang, Wenyang Luo, Haoyang Huang, Dongdong Zhang, Xiaolei Wang, Xin Zhao, Furu Wei, Ji-Rong Wen

BalanceSFT: Improving LLM Function Calling with Balanced Training Signals and Data Hardness (2026.findings-acl)

Challenge:	Despite the impressive multilingual capabilities demonstrated by LLMs, the understanding of how these abilities develop and function remains nascent.
Approach:	They propose a novel detection method to pinpoint language-specific neurons within LLMs by selectively activating or deactivating these neurons.
Outcome:	The proposed method can “steer” the output language of LLMs by selectively activating or deactivating language-specific neurons.

Copied to clipboard

Bingguang Hao, Zengzhuang Xu, Maolin Wang, Yuntao Wen, Yicheng Chen, Cunyin Peng, Long Chen, Xiangyu Zhao, Jinjie Gu, Chenyi Zhuang, Ji Zhang

Exploring Better Text Image Translation with Multimodal Codebook (2023.acl-long)

Challenge:	Currently, Supervised Fine-Tuning (SFT) is the prevailing method for equipping Large Language Models (LLMs) with function calling capabilities, but its effectiveness is often compromised by two challenges: 1) lengthy Chain-of-Thought (CoT) reasoning tokens dominate training signals over concise function calls in the learning objective; 2) scarcity of hard training examples.
Approach:	They propose a framework that uses a self-adjusted signal balancing loss and a hard data re-sampling strategy to selectively generate new, high-quality complex data guided by model errors.
Outcome:	The proposed framework surpasses state-of-the-art models like GPT-5 in function calling performance.

Copied to clipboard

Zhibin Lan, Jiawei Yu, Xiang Li, Wen Zhang, Jian Luan, Bin Wang, Degen Huang, Jinsong Su

Token-Level Policy Optimization: Linking Group-Level Rewards to Token-Level Aggregation via sequence-level likelihood (2026.acl-long)

Challenge:	Current studies on text image translation face bottlenecks due to lack of a publicly available dataset and poor optical character recognition.
Approach:	They propose a text image translation model with a multimodal codebook and an OCR dataset for Chinese-English translation.
Outcome:	The proposed model can associate the image with relevant texts, providing useful supplementary information for translation.

Copied to clipboard

Xingyu Lin, Yilin Wen, Du Su, En Wang, Wenbin Liu, Zhonghou Lv, Jinchang Hou, Chenfu Bao

SafeConf: A Confidence-Calibrated Safety Self-Evaluation Method for Large Language Models (2025.findings-emnlp)

Challenge:	Group Relative Policy Optimization (GRPO) has significantly advanced the reasoning ability of large language models (LLMs).
Approach:	They propose a token-level framework that leverages sequence-level likelihood to link group-level rewards with individual tokens via token- level aggregation and introduces a KL-Divergence mask constraint that targets tokens with positive advantages and decreasing entropy to mitigate abrupt policy updates.
Outcome:	Experiments show that TEPO achieves state-of-the-art performance on mathematical reasoning benchmarks and reduces convergence time by 50% compared with GRPO/DAPO.

Copied to clipboard

Bo Zhang, Cong Gao, Linkang Yang, Bingxu Han, Minghao Hu, Zhunchen Luo, Guotong Geng, Xiaoying Bai, Jun Zhang, Wen Yao, Zhong Wang

A Thorough Examination on Zero-shot Dense Retrieval (2023.findings-emnlp)

Challenge:	Large language models (LLMs) have many advantages but they also pose significant safety risks.
Approach:	They propose a method to enhance the safety self-evaluation capability of LLMs . they perform semantic mutations on the original safety evaluation questions .
Outcome:	The proposed method improves safety self-evaluation accuracy by 5.86% and 7.79% over baseline methods on Chinese and English datasets.

Copied to clipboard

Ruiyang Ren, Yingqi Qu, Jing Liu, Xin Zhao, Qifei Wu, Yuchen Ding, Hua Wu, Haifeng Wang, Ji-Rong Wen

GLiM: Integrating Graph Transformer and LLM for Document-Level Biomedical Relation Extraction with Incomplete Labeling (2025.findings-acl)

Challenge:	Recent advances in dense retrieval (DR) models have been shown to be not as competitive as traditional sparse retrieval models in a zero-shot retrieval setting.
Approach:	They propose to examine the zero-shot capability of DR models by analyzing key factors related to source training set and potential bias from target dataset.
Outcome:	The proposed model is not as competitive as sparse retrieval models in a zero-shot retrieval setting.

Copied to clipboard

Hao Fang, Yuejie Zhang, Rui Feng, Yingwen Wang, Qing Wang, Wen He, Xiaobo Zhang, Tao Zhang, Shang Gao

DopplerBAS: Binaural Audio Synthesis Addressing Doppler Effect (2023.findings-acl)

Challenge:	Document-level relation extraction (DocRE) solves problems of document quality . number of entities and entity-pair relations increases, causing incomplete annotations .
Approach:	a framework that reduces the problem space using a graph-enhanced Transformer-based model is proposed . GLiM leverages large language models for reasoning to reduce the problem-space .
Outcome:	GLiM boosts average recall and F1 scores on biomedical datasets . compared with existing models, GLim outperforms existing models on biomedicine benchmarks compared to existing models .

Copied to clipboard

Jinglin Liu, Zhenhui Ye, Qian Chen, Siqi Zheng, Wen Wang, Zhang Qinglin, Zhou Zhao

Evaluating Robustness of Generative Search Engine on Adversarial Factoid Questions (2024.findings-acl)

Challenge:	Existing methods for binaural audio synthesis are limited in phase estimation, which is crucial for spatial hearing.
Approach:	They propose a method to explicitly address the Doppler effect of the moving speaker . it calculates the radial relative velocity of the speaker in spherical coordinates .
Outcome:	The proposed method improves the representative WarpNet and BinauralGrad backbones in phase error metric and reaches a new state of the art (SOTA) it is compared with the current method which is limited in phase estimation .

Copied to clipboard

Xuming Hu, Xiaochuan Li, Junzhe Chen, Yinghui Li, Yangning Li, Xiaoguang Li, Yasheng Wang, Qun Liu, Lijie Wen, Philip Yu, Zhijiang Guo

Position: LLMs Can be Good Tutors in English Education (2025.emnlp-main)

Challenge:	Existing large language models (LLMs)-backed generative search engines may not always be accurate.
Approach:	They propose to evaluate the robustness of retrieval-augmented generation in a realistic and high-risk setting where adversaries have only black-box system access.
Outcome:	The proposed model exhibits higher susceptibility to factual errors compared to LLMs without retrieval.

Copied to clipboard

Jingheng Ye, Shen Wang, Deqing Zou, Yibo Yan, Kun Wang, Hai-Tao Zheng, Ruitong Liu, Zenglin Xu, Irwin King, Philip S. Yu, Qingsong Wen

HPSS: Heuristic Prompting Strategy Search for LLM Evaluators (2025.findings-acl)

Challenge:	Recent efforts to integrate large language models into English education lack adaptability to language learning.
Approach:	They argue that large language models can be effective tutors in English education . they encourage interdisciplinary research to explore these roles, fostering innovation and risks .
Outcome:	The proposed models can play three critical roles: 1) as data enhancers, 2) as task predictors, 3) as agents, enabling personalized and inclusive education.

Copied to clipboard

Bosi Wen, Pei Ke, Yufei Sun, Cunxiang Wang, Xiaotao Gu, Jinfeng Zhou, Jie Tang, Hongning Wang, Minlie Huang

CritiqueLLM: Towards an Informative Critique Generation Model for Evaluation of Large Language Model Generation (2024.acl-long)

Challenge:	Existing efforts to optimize text evaluation prompts neglect the combinatorial impact of multiple factors, leading to insufficient optimization of the evaluation pipeline.
Approach:	They propose to integrate 8 key factors for evaluation prompts and integrate them into an algorithm that searches for well-behaved prompting strategies for LLM evaluators.
Outcome:	The proposed method outperforms existing methods and human-designed evaluation prompts on four evaluation tasks.

Copied to clipboard

Pei Ke, Bosi Wen, Andrew Feng, Xiao Liu, Xuanyu Lei, Jiale Cheng, Shengyuan Wang, Aohan Zeng, Yuxiao Dong, Hongning Wang, Jie Tang, Minlie Huang

Towards Better Entity Linking with Multi-View Enhanced Distillation (2023.acl-long)

Challenge:	Existing models for NLP evaluations lack the ability to generate informative critiques in pointwise grading and pairwise comparison especially without references.
Approach:	They propose a method which can acquire pointwise grading critiques with pseudo references and revise these critiques via multi-path prompting to obtain informative evaluation data in different tasks and settings.
Outcome:	The proposed method outperforms all open-source models and even GPT-4 in system-level correlations of pointwise grading.

Copied to clipboard

Yi Liu, Yuan Tian, Jianxun Lian, Xinlong Wang, Yanan Cao, Fang Fang, Wen Zhang, Haizhen Huang, Weiwei Deng, Qi Zhang

CharacterGLM: Customizing Social Characters with Large Language Models (2024.emnlp-industry)

Challenge:	Entity linking is a fundamental task in Natural Language Processing (NLP), connecting mentions within unstructured contexts to their corresponding entities in a Knowledge Base (KB).
Approach:	They propose a dual-encoder framework that can efficiently match mentions to two-encoding frameworks by a global-view.
Outcome:	The proposed framework achieves state-of-the-art on several entity linking benchmarks.

Copied to clipboard

Jinfeng Zhou, Zhuang Chen, Dazhen Wan, Bosi Wen, Yi Song, Jifan Yu, Yongkang Huang, Pei Ke, Guanqun Bi, Libiao Peng, JiaMing Yang, Xiyao Xiao, Sahand Sabour, Xiaohan Zhang, Wenjing Hou, Yijia Zhang, Yuxiao Dong, Hongning Wang, Jie Tang, Minlie Huang

Cross-Utterance Conditioned VAE for Non-Autoregressive Text-to-Speech (2022.acl-long)

Challenge:	Character-based dialogue systems (CharacterDial) allow users to customize social characters for social interactions.
Approach:	They will collect a large-scale Chinese corpus of characters with diverse categories and behaviors and develop CharacterGLM models to address these challenges.
Outcome:	Experiments show that CharacterGLM outperforms most popular open- and closed-source LLMs and performs comparable to GPT-4.

Copied to clipboard

Yang Li, Cheng Yu, Guangzhi Sun, Hua Jiang, Fanglei Sun, Weiqin Zu, Ying Wen, Yang Yang, Jun Wang

NEAT: Neuron-Based Early Exit for Large Reasoning Models (2026.findings-acl)

Challenge:	Experimental results show that the proposed model improves naturalness and prosody diversity with clear margins.
Approach:	They propose a cross-utterance conditional VAE to estimate posterior probability distribution of latent prosody features for each phoneme by conditioning on acoustic features, speaker information, and text features from past and future sentences.
Outcome:	The proposed model improves naturalness and prosody diversity with clear margins.

Copied to clipboard

Kang Liu, YongKang Liu, Xiaocui Yang, Peidong Wang, Wen Zhang, Shi Feng, Yifei Zhang, Daling Wang

LLMBox: A Comprehensive Library for Large Language Models (2024.acl-demos)

Challenge:	Existing approaches to reduce overthinking require additional rollout computation or externally labeled datasets.
Approach:	They propose a Neuron-based Early reAsoning exiT framework that monitors neuron-level activation dynamics to enable training-free early exits.
Outcome:	The proposed framework reduces the amount of reasoning steps generated by LRMs while maintaining accuracy.

Copied to clipboard

Tianyi Tang, Hu Yiwen, Bingqian Li, Wenyang Luo, ZiJing Qin, Haoxiang Sun, Jiapeng Wang, Shiyi Xu, Xiaoxue Cheng, Geyang Guo, Han Peng, Bowen Zheng, Yiru Tang, Yingqian Min, Yushuo Chen, Jie Chen, Ranchi Zhao, Luran Ding, Yuhao Wang, Zican Dong, Xia Chunxuan, Junyi Li, Kun Zhou, Xin Zhao, Ji-Rong Wen

BASES: Large-scale Web Search User Simulation with Large Language Model based Agents (2024.findings-emnlp)

Challenge:	a library to facilitate the development, use, and evaluation of large language models (LLMs) is presented.
Approach:	They propose a unified library to facilitate the development, use and evaluation of large language models (LLMs).
Outcome:	The proposed library is based on extensive experiments in a variety of evaluation settings.

Copied to clipboard

Ruiyang Ren, Peng Qiu, Yingqi Qu, Jing Liu, Xin Zhao, Hua Wu, Ji-Rong Wen, Haifeng Wang

Retrieval-Augmented Process Reward Model for Generalizable Mathematical Reasoning (2025.findings-acl)

Challenge:	Existing research on web search rely on real-user experiments, which can be costly to scale up.
Approach:	They propose a user simulation framework with LLM-based agents that can generate unique user profiles at scale.
Outcome:	The proposed framework can generate unique user profiles at scale, leading to diverse search behaviors.

Copied to clipboard

Jiachen Zhu, Congmin Zheng, Jianghao Lin, Kounianhua Du, Ying Wen, Yong Yu, Jun Wang, Weinan Zhang

Do Language Models Mirror Human Confidence? Exploring Psychological Insights to Address Overconfidence in LLMs (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

Chenjun Xu, Bingbing Wen, Bin Han, Robert Wolfe, Lucy Lu Wang, Bill Howe

The Web Can Be Your Oyster for Improving Language Models (2023.findings-acl)

Challenge:	Psychology research has shown that humans are poor at estimating their performance on tasks, tending towards underconfidence on easy tasks and overconfidence on difficult tasks.
Approach:	They propose to use a self-assessment method to assess confidence in large language models (LLMs) they propose to ask for the answer separately and then use them to improve their accuracy.
Outcome:	The proposed method improves confidence calibration and interpretability in QA tasks with different personas.

Copied to clipboard

Junyi Li, Tianyi Tang, Wayne Xin Zhao, Jingyuan Wang, Jian-Yun Nie, Ji-Rong Wen

CodeTransOcean: A Comprehensive Multilingual Benchmark for Code Translation (2023.findings-emnlp)

Challenge:	Pretrained language models encode a large amount of knowledge, but knowledge is frozen at the time of training, and the models become static and limited by training data.
Approach:	They propose an adaptive search engine assisted learning method that can self-evaluate the confidence level of PLM’s predictions and adaptively determine when to refer to the web for more data.
Outcome:	The proposed model outperforms retrieval-augmented methods on 16 knowledge-intensive tasks on a wide range of knowledge-related tasks.

Copied to clipboard

Weixiang Yan, Yuchen Tian, Yunzhe Li, Qian Chen, Wen Wang

WavAlign: Enhancing Intelligence and Expressiveness in Spoken Dialogue Models via Adaptive Hybrid Post-Training (2026.findings-acl)

Challenge:	Existing code translation datasets focus on a single pair of programming languages . early software systems are developed using programming languages such as Fortran and COBOL .
Approach:	They propose a large-scale comprehensive benchmark that supports the largest variety of programming languages for code translation.
Outcome:	The proposed framework supports translations between multiple programming languages and a cross-framework dataset for deep learning code across different frameworks.

Copied to clipboard

Yifu Chen, Shengpeng Ji, Qian Chen, Tianle Liang, Yangzhuo Li, Ziqing Wang, Wen Wang, Jingyu Lu, Haoxiao Wang, Xueyi Pu, Fan Zhuo, Zhou Zhao

What Makes for Good Visual Instructions? Synthesizing Complex Visual Reasoning Instructions for Visual Instruction Tuning (2025.coling-main)

Challenge:	End-to-end spoken dialogue models have higher potential ceiling in expressiveness and perceptual ability than cascaded systems.
Approach:	They propose a modality-aware adaptive post-training recipe that constrains preference updates to the semantic channel and improves acoustic behavior via explicit anchoring.
Outcome:	The proposed model improves speech quality and expressiveness across spoken dialogue benchmarks and architectures.

Copied to clipboard

Yifan Du, Hangyu Guo, Kun Zhou, Wayne Xin Zhao, Jinpeng Wang, Chuyuan Wang, Mingchen Cai, Ruihua Song, Ji-Rong Wen

Characterizing LLM Abstention Behavior in Science QA with Context Perturbations (2024.findings-emnlp)

Challenge:	Experimental results show that visual instruction tuning improves performance of Multi-modal Large Language Models (MLLMs) to extend the application scope of Large Language Modells, a surge of work augments LLMs with vision encoders to endow the ability of multi-modal cognition and reasoning.
Approach:	They propose a systematic approach to create high-quality visual reasoning instructions using a synthesize-complicate-reformulate paradigm.
Outcome:	The proposed method improves performance of MLLMs by 27.86% and 27.60% on MME-Perception and MME Cognition.

Copied to clipboard

Bingbing Wen, Bill Howe, Lucy Wang

Question Answering

Challenge:	Prior work has investigated the ability of LLMs to abstain from answering context-dependent questions when provided insufficient or inconsistent context is provided.
Approach:	They propose to improve abstention when provided insufficient or incorrect context . they probed the ability of LLMs to abstain from answering context-dependent science questions .
Outcome:	The proposed models abstain from answering science questions when provided insufficient or incorrect context.

An Empirical Study of LLM Reasoning Ability Under Strict Output Length Constraint (2025.emnlp-main)

Copied to clipboard

Yi Sun, Han Wang, Jiaqiang Li, Jiacheng Liu, Xiangyu Li, Hao Wen, Yizhen Yuan, Huiwen Zheng, Yan Liang, Yuanchun Li, Yunxin Liu

Low-Resource NLP

Challenge:	Large Language Models (LLMs) are a powerful tool for test-time scaling, but they are often used under time constraints.
Approach:	They propose to use LLMs to make models think before answering questions . they also use self-correction and best-of-N decoding to encourage deeper thinking .
Outcome:	The proposed models are able to achieve higher inference accuracy with extra inference computation under time constraints.

Lock on Target! Precision Unlearning via Directional Control (2025.findings-emnlp)

Copied to clipboard

Yuntao Wen, Ruixiang Feng, Feng Guo, Yifan Wang, Ran Le, Yang Song, Shen Gao, Shuo Shang

Challenge:	Existing methods for unlearning harmful, sensitive, or outdated knowledge suffer from two critical limitations: (1) collateral forgetting, where erasing target data inadvertently removes related but desirable knowledge, and (2) generality forgetting degrades the model’s general capabilities.
Approach:	They propose a method that identifies and leverages a targeted "unlearning direction" in the model's parameter space and selectively updates along this direction.
Outcome:	Experiments show that the proposed method achieves state-of-the-art unlearning precision while preserving both related knowledge and general capabilities.

SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesis (2025.findings-emnlp)

Copied to clipboard

Shuang Sun, Huatong Song, Yuhao Wang, Ruiyang Ren, Jinhao Jiang, Junjie Zhang, Fei Bai, Jia Deng, Xin Zhao, Zheng Liu, Lei Fang, Zhongyuan Wang, Ji-Rong Wen

Locate and Label: A Two-stage Identifier for Nested Named Entity Recognition (2021.acl-long)

Challenge:	Existing approaches to deep search training lack high-quality training trajectories, prohibitive computational costs and lack of high-fidelity training data.
Approach:	They propose a framework that synthesizes high-quality training data by simulating real user interactions in live web search environments.
Outcome:	The proposed framework synthesizes high-quality training data by simulating user interactions in live web search environments.

Copied to clipboard

Yongliang Shen, Xinyin Ma, Zeqi Tan, Shuai Zhang, Wen Wang, Weiming Lu

Safety-Utility Conflicts Are Not Global: Surgical Alignment via Head-Level Diagnosis (2026.acl-long)

Challenge:	Named entity recognition (NER) is a well-studied task in natural language processing.
Approach:	They propose a method that generates span proposals and labels them with categories . they use boundary information of entities and partially matched spans to locate them .
Outcome:	The proposed method outperforms state-of-the-art models on nested NER datasets.

Copied to clipboard

Wang Cai, Yilin Wen, Jinchang Hou, Du Su, Guoqiu Wang, Zhonghou Lv, Chenfu Bao, Yunfang Wu

MATCH: Modulating Attention via In-Context Retrieval for Long-Context Transformers (2026.acl-long)

Challenge:	Existing mitigation strategies rely on global gradient geometry to resolve alignment conflicts . however, they overlook Modular Heterogeneity within Transformers, resulting in suboptimal trade-offs . Conflict-Aware Sparse Tuning (CAST) combines head-level diagnosis with sparse fine-tuning .
Approach:	They propose a framework that integrates head-level diagnosis with sparse fine-tuning to address this limitation.
Outcome:	The proposed framework integrates head-level diagnosis with sparse fine-tuning to reduce alignment conflicts in LLMs.

Copied to clipboard

Linrui Ma, Chun Hei Lo, Xinyu Wang, Peng Lu, Xihao Yuan, Hanting Chen, Kai Han, Xinghao Chen, Chengjun Zhan, Hanlin xu, Yichun Yin, Lifeng Shang, Feng Wen, Boxing Chen, Yufei Cui

CoTJudger: A Graph-Driven Framework for Automatic Evaluation of Chain-of-Thought Efficiency and Redundancy in LRMs (2026.findings-acl)

Challenge:	Existing approaches to improve efficiency often enforce rigid structural constraints such as local attention windows.
Approach:	They propose a framework that augments sparse-attention mechanisms with dynamically integrated in-context information through an efficient retrieval system.
Outcome:	Empirical results show that MATCH significantly improves the performance of sparse-attention models on synthetic and real-world natural-language tasks.

Copied to clipboard

Siyi Li, Jiajun Shi, Shiwen Ni, Ge Zhang, Shuaimin Li, Shijian Wang, Zhoufutu Wen, Yizhi LI, Hamid Alinejad-Rokny, Jiaheng Liu, Min Yang, Wenhao Huang

Green & Sustainable NLP

Challenge:	Existing evaluations emphasize final accuracy or coarse token counts, and lack automated tools to separate essential logic from structural redundancy.
Approach:	They propose a graph-driven framework that quantifies reasoning efficiency by converting free-form CoTs into directed dependency graphs and extracting the Shortest Effective Path needed to reach a correct solution.
Outcome:	Evaluating 21 LRMs, the proposed framework quantifies reasoning efficiency by converting free-form CoTs into directed dependency graphs and extracting the Shortest Effective Path (SEP) needed to reach a correct solution.

Cat-MoD: Accelerating Multimodal Alignment via Caption Token Guided Asymmetric Mixture-of-Depths (2026.acl-long)

Copied to clipboard

YiJie Huang, Xiaocui Yang, Shi Feng, Wen Zhang, Kaisong Song, Yifei Zhang, Daling Wang

Interactive Question Clarification in Dialogue via Reinforcement Learning (2020.coling-industry)

Challenge:	Existing query-based alignment modules enforce uniform cross-attention across all layers, leading to computational redundancy.
Approach:	They propose a framework that allows for asynchronous query-based alignment with large-scale visual features.
Outcome:	The proposed framework matches or surpasses baseline performance while reducing alignment FLOPs by approximately 37% during training and inference.

Copied to clipboard

Xiang Hu, Zujie Wen, Yafang Wang, Xiaolong Li, Gerard de Melo

Not Everything is All You Need: Toward Low-Redundant Optimization for Large Language Model Alignment (2024.emnlp-main)

Challenge:	ambiguous questions are a perennial problem in real-world dialogue systems.
Approach:	They propose a reinforcement model to clarify ambiguous questions by suggesting refinements of the original query.
Outcome:	The proposed model improves on real-world user clicks and shows significant improvements . it suggests that the original query is refined to clarify ambiguous questions .

Copied to clipboard

Zhipeng Chen, Kun Zhou, Xin Zhao, Jingyuan Wang, Ji-Rong Wen

Large Language Models are Complex Table Parsers (2023.emnlp-main)

Challenge:	Experimental results show that large language models are struggling to align with human preference in complex tasks and scenarios.
Approach:	They propose a low-redundant alignment method that selects the top-10% most updated parameters in LLMs for alignment training.
Outcome:	The proposed method improves on 10 datasets and shows that it is redundant . it can be used to train LLMs on QA and ECQA datasets, but it is not feasible to test it on a large dataset.

Copied to clipboard

Bowen Zhao, Changkai Ji, Yuejie Zhang, Wen He, Yingwen Wang, Qing Wang, Rui Feng, Xiaobo Zhang

Bridging Kernel Drivers and Virtual Device Models with LLM-Powered Automation (2026.acl-demo)

Challenge:	Extensive experiments and results on Complex Table QA datasets, i.e., the open-domain dataset HiTAB and the aviation domain dataset AIT-QA show that our approach significantly outperforms previous work on both datasets.
Approach:	They propose to incorporate Generative Pre-trained Transformer 3.5 to address the specific challenges posed by Complex Table QA by reconstructing tables into tuples and using prompt templates to create dialogues.
Outcome:	The proposed approach outperforms previous work on complex table parsing datasets and leads to state-of-the-art (SOTA) performance.

Copied to clipboard

Mingyu Wang, Bin Yu, Wenjian Lu, Zhi Wang, Gao Kefeng, Cheng Wen, Xu Lu, Cong Tian

Do LLMs Understand Wine Descriptors Across Cultures? A Benchmark for Cultural Adaptations of Wine Reviews (2025.findings-emnlp)

Challenge:	Linux kernel device drivers are tightly coupled with hardware, making them difficult to execute and test without physical devices.
Approach:	They present a tool that generates QEMU-based virtual devices directly from Linux driver source code.
Outcome:	The proposed tool generates QEMU-based virtual devices directly from Linux driver source code.

Copied to clipboard

Chenye Zou, Xingyue Wen, Tianyi Hu, Qian Janice Wang, Daniel Hershcovich

Machine Translation

Challenge:	Recent advances in large language models have opened the door to culture-aware language tasks.
Approach:	They propose to integrate regional taste preferences and culture-specific flavor descriptors into wine reviews across Chinese and English.
Outcome:	The proposed model incorporates regional taste preferences and culture-specific flavor descriptors into the translation process.

Every Document Owns Its Structure: Inductive Text Classification via Graph Neural Networks (2020.acl-main)

Copied to clipboard

Yufeng Zhang, Xueli Yu, Zeyu Cui, Shu Wu, Zhongzhen Wen, Liang Wang

Improving Adversarial Text Generation by Modeling the Distant Future (2020.acl-main)

Challenge:	Existing graph-based methods for text classification cannot capture contextual word relationships within each document nor can they produce inductive learning of new words.
Approach:	They propose to use Graph Neural Networks to learn the local word representations and then aggregate the word nodes as the document embeddings.
Outcome:	The proposed method outperforms state-of-the-art methods on four benchmark datasets.

Copied to clipboard

Ruiyi Zhang, Changyou Chen, Zhe Gan, Wenlin Wang, Dinghan Shen, Guoyin Wang, Zheng Wen, Lawrence Carin

SOLAR-RL: Semi-Online Long-horizon Assignment Reinforcement Learning (2026.findings-acl)

Challenge:	Recent work has shown excellent performance on text generation tasks by combining reinforcement learning (RL) and generative models.
Approach:	They propose a model-based imitation-learning approach to improve text generation performance by focusing on a long horizon.
Outcome:	The proposed model improves on a number of text-generation tasks and provides intermediate rewards for generator optimization.

Copied to clipboard

Jichao Wang, Liuyang Bian, Yufeng Zhou, Han Xiao, Yue Pan, Guozhi Wang, Hao Wang, Zhaoxiong Wang, Yafei Wen, Xiaoxin Chen, Shuai Ren, Lingfang Zeng

MolMem: Memory-Augmented Agentic Reinforcement Learning for Sample-Efficient Molecular Optimization (2026.acl-long)

Challenge:	Existing approaches to training GUI agents on dynamic tasks are based on SFT or Behavior Cloning.
Approach:	They propose a framework that integrates global trajectory insights directly into offline learning . they reconstruct diverse rollout candidates from static data and detect first failure point .
Outcome:	The proposed framework improves long-horizon task completion rates and robustness compared to baselines.

Copied to clipboard

Ziqing Wang, Yibo Wen, Abhishek Pandey, Han Liu, Kaize Ding

Green & Sustainable NLP

Challenge:	Existing methods for molecular optimization use expensive oracle evaluations to achieve sample efficiency under limited oracular budget.
Approach:	They propose a framework that iteratively refines a lead compound to improve molecular properties while preserving structural similarity to the original molecule.
Outcome:	The proposed framework achieves 90% success on single-property tasks and 52% on multi-propety task using only 500 oracle calls.

SpeechFake: A Large-Scale Multilingual Speech Deepfake Dataset Incorporating Cutting-Edge Generation Methods (2025.acl-long)

Copied to clipboard

Wen Huang, Yanmei Gu, Zhiming Wang, Huijia Zhu, Yanmin Qian

Scaling Law for Multimodal Large Language Model Supervised Fine-Tuning (2026.acl-long)

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

YiFan Zhang, Tao Yu, Feng Li, Chaoyou Fu, Yibo Hu, Kun Wang, Qingsong Wen, Zhang Zhang, Liang Wang, Rong Jin

ElitePLM: An Empirical Study on General Language Ability Evaluation of Pretrained Language Models (2022.naacl-main)

Challenge:	supervised fine-tuning (SFT) is crucial for multimodal large language models, yet a comprehensive scaling law is lacking . et al.: scaling laws focus on model size, pre-training tokens, and MLLM SFT data volumes .
Approach:	They propose two scaling laws to guide optimal model-data configuration . they propose one applicable when training data volumes are well defined by researchers .
Outcome:	The proposed scaling laws provide valuable recommendations for optimal resource allocation . they show that the proposed laws are more accurate than existing models .

Copied to clipboard

Junyi Li, Tianyi Tang, Zheng Gong, Lixin Yang, Zhuohao Yu, Zhipeng Chen, Jingyuan Wang, Xin Zhao, Ji-Rong Wen

Knowledge Injection Exists in MoE? Exploring Expert-Aware Contrast Decoding in MoE for Mitigating LLMs’ Hallucinations (2026.acl-long)

Challenge:	Recent years have featured a trend towards Transformer based pretrained language models (PLMs) in natural language processing systems.
Approach:	They propose to use four evaluation dimensions to evaluate ten widely-used PLMs . they find that pretrained language models are good at different ability tests .
Outcome:	The results show that pretrained language models are good at different ability tests and have excellent transferability between tasks.

Copied to clipboard

Xinyue Fang, Zhiliang Tian, Zhen Huang, Ziyi Pan, Zhihua Wen, Xi Wang, Quntian Fang, Dongsheng Li

ES4R: Speech Encoding Based on Prepositive Affective Modeling for Empathetic Response Generation (2026.acl-long)

Challenge:	Existing methods to mitigate hallucinations include prompt engineering and model optimization, but lack domain generalization and potential errors in fine-tuning data may exacerbate the hallucism.
Approach:	They propose an expert-aware adaptive contrast decoding that uses expert differences in MoE’s higher layers to mitigate hallucinations on QA tasks.
Outcome:	The proposed method outperforms baseline models on four datasets Large language models (LLMs) show strong performance but suffer from hallucinations, limiting their application.

Copied to clipboard

Zhuoyue Gao, Xiaohui Wang, Xiaocui Yang, Wen Zhang, Daling Wang, Shi Feng, Yifei Zhang