Papers by Yi Wu

Rethinking Data Selection at Scale: Random Selection is Almost All You Need (2025.findings-emnlp)

Challenge:	Existing methods to extract webpage snippets ignore contextual information of webpages, which may be sub-optimal.
Approach:	They propose a query-aware webpage snippet extraction method called DeepQSE that captures contextual information of webpages.
Outcome:	The proposed method can significantly improve the performance of DeepQSE without affecting its performance.

Copied to clipboard

Tingyu Xia, Bowen Yu, Kai Dang, An Yang, Yuan Wu, Yuan Tian, Yi Chang, Junyang Lin

Updating Large Language Models’ Memories with Time Constraints (2024.findings-emnlp)

Challenge:	Existing data selection techniques are designed for small data pools, a study finds . filtering data by token length is an efficient method for improving results .
Approach:	They use self-scoring methods that do not rely on external help to perform fine-tuning . they also find that filtering data by token length offers a stable and efficient method .
Outcome:	The proposed methods outperform random selection on large datasets on large data pools.

Copied to clipboard

Xin Wu, Yuqi Bu, Yi Cai, Tao Wang

BRIGHTER: BRIdging the Gap in Human-Annotated Textual Emotion Recognition Datasets for 28 Languages (2025.acl-long)

Challenge:	Large language models (LLMs) can modify their internal memory by incorporating the latest external knowledge, but in practical applications, outdated information may be inputted into LLMs.
Approach:	They propose a two-stage decoupling framework that separates the identification and computation of time constraints into a symbolic system and propose 'selective update' of internal memory based on time constraints.
Outcome:	The proposed framework improves ChatGPT performance by 60% and improves state-of-the-art LLM GPT-4.

Copied to clipboard

Shamsuddeen Hassan Muhammad, Nedjma Ousidhoum, Idris Abdulmumin, Jan Philip Wahle, Terry Ruas, Meriem Beloucif, Christine de Kock, Nirmal Surange, Daniela Teodorescu, Ibrahim Said Ahmad, David Ifeoluwa Adelani, Alham Fikri Aji, Felermino D. M. A. Ali, Ilseyar Alimova, Vladimir Araujo, Nikolay Babakov, Naomi Baes, Ana-Maria Bucur, Andiswa Bukula, Guanqun Cao, Rodrigo Tufiño, Rendi Chevi, Chiamaka Ijeoma Chukwuneke, Alexandra Ciobotaru, Daryna Dementieva, Murja Sani Gadanya, Robert Geislinger, Bela Gipp, Oumaima Hourrane, Oana Ignat, Falalu Ibrahim Lawan, Rooweither Mabuya, Rahmad Mahendra, Vukosi Marivate, Alexander Panchenko, Andrew Piper, Charles Henrique Porto Ferreira, Vitaly Protasov, Samuel Rutunda, Manish Shrivastava, Aura Cristina Udrea, Lilian Diana Awuor Wanzare, Sophie Wu, Florian Valentin Wunderlich, Hanif Muhammad Zhafran, Tianhui Zhang, Yi Zhou, Saif M. Mohammad

Sentiment Analysis

Challenge:	Emotion recognition is an umbrella term for several NLP tasks, but most work on high-resource languages has focused on low-resourced languages.
Approach:	They propose to use emotion recognition to describe perceived emotions in 28 different languages and across several domains to identify and annotate the datasets.
Outcome:	The proposed datasets cover low-resource languages from Africa, Asia, Eastern Europe, and Latin America, with instances labeled by fluent speakers.

A Learnable Skill Combination Strategy for Multi-task Learning in Natural Language Understanding (2026.findings-acl)

Copied to clipboard

Zhe Yang, Yi Huang, Yaqin Chen, Mengfei Guo, Xiaoting Wu, Junlan Feng

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

Challenge:	a novel multi-task learning framework for domain-specific natural language understanding tasks addresses these limitations by combing multiple tasks into a single framework.
Approach:	They propose a multi-task learning framework that decomposes the language model into modular skill components and employs a dynamic, learnable skill-combination mechanism to adaptively handle diverse tasks.
Outcome:	The proposed framework surpasses conventional multi-task learning approaches in performance.

Copied to clipboard

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

Green & Sustainable NLP

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

ESGenius: Benchmarking LLMs on Environmental, Social, and Governance (ESG) and Sustainability Knowledge (2025.emnlp-main)

Copied to clipboard

Chaoyue He, Xin Zhou, Yi Wu, Xinjia Yu, Yan Zhang, Lei Zhang, Di Wang, Shengfei Lyu, Hong Xu, Wang Xiaoqiao, Wei Liu, Chunyan Miao

AGGC: Adaptive Group Gradient Clipping for Stabilizing Large Language Model Training (2026.findings-acl)

Challenge:	ESGenius is a comprehensive benchmark for evaluating Large Language Models on ESG and sustainability knowledge.
Approach:	They introduce ESGenius, a benchmark for evaluating and enhancing ESG proficiency . they use a rigorous two-stage evaluation protocol and a repository of foundational frameworks .
Outcome:	ESGenius is a benchmark for evaluating and enhancing the proficiency of Large Language Models (LLMs) in ESG and sustainability-focused question answering.

Copied to clipboard

Zhiyuan Li, Yuan Wu, Yi Chang

FLAIR: Steering LLM Mathematical Problem Solving based on A Fuzzy-Logic-AssIsted Reasoner (2026.acl-long)

Challenge:	Adaptive group-wise gradient clipping (AGGC) is a new approach to stabilize training of Large Language Models.
Approach:	They propose a method to stabilize gradient clipping by partitioning parameters into groups based on functional types and a time-dependent scheduling mechanism to balance exploration and convergence.
Outcome:	The proposed algorithm outperforms standard LoRA and achieves 72.93% accuracy . it can be integrated into existing pipelines with negligible overhead.

Copied to clipboard

Hao Wu, Hongru Sun, Wanqing Li, Xinguo Yu, Hao Ming, Xiao Luo, Wenbin Zhang, Jiahong Zhao, Yi Guo, Jie Yang

Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents (2026.acl-long)

Challenge:	Existing approaches to mathematical reasoning rely on static heuristics or pre-determined reasoning strategies.
Approach:	They propose an adaptive framework that integrates fuzzy theory into LLM-based mathematical reasoning.
Outcome:	The proposed framework outperforms state-of-the-art models while offering effective and interpretable diagnostics of intermediate problem-solving states.

Copied to clipboard

Yi Yu, Liuyi Yao, Yuexiang Xie, Qingquan Tan, Jiaqi Feng, Yaliang Li, Libing Wu

Automated Progressive Red Teaming (2025.coling-main)

Challenge:	Existing methods handle long-term memory (LTM) and short-term (STM) as separate components, relying on heuristics or auxiliary controllers, which limits adaptability and end-to-end optimization.
Approach:	They propose a framework that integrates LTM and STM management directly into the agent's policy and propose 'agentic memory' to train such unified behaviors.
Outcome:	The proposed framework outperforms strong memory-augmented baselines on five long-horizon benchmarks and achieves higher-quality long-term memory and more efficient context usage.

Copied to clipboard

Bojian Jiang, Yi Jing, Tong Wu, Tianhao Shen, Deyi Xiong, Qing Yang

CONQRR: Conversational Query Rewriting for Retrieval with Reinforcement Learning (2022.emnlp-main)

Challenge:	Automated red teaming (ART) is effective but time-consuming, costly and lacks scalability.
Approach:	They propose an automated red teaming framework that generates adversarial prompts to expose LLM vulnerabilities.
Outcome:	The proposed framework explores and exploits LLM vulnerabilities through multi-round interactions.

Copied to clipboard

Zeqiu Wu, Yi Luan, Hannah Rashkin, David Reitter, Hannaneh Hajishirzi, Mari Ostendorf, Gaurav Singh Tomar

Natural Language Interfaces

Challenge:	Existing models for conversational question answering require specific retrievers to understand user questions.
Approach:	They develop a query rewriting model CONQRR that rewrites a conversational question into a standalone question.
Outcome:	The proposed model achieves state-of-the-art on an open-domain conversational question answering dataset and is effective for two different off-the shelf retrievers.

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

Copied to clipboard

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

Information Extraction & Text Mining

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

Dropping Experts, Recombining Neurons: Retraining-Free Pruning for Sparse Mixture-of-Experts LLMs (2025.findings-emnlp)

Copied to clipboard

Yixiao Zhou, Ziyu Zhao, Dongzhou Cheng, Zhiliang Wu, Jie Gui, Yi Yang, Fei Wu, Yu Cheng, Hehe Fan

On the Vulnerability of Safety Alignment in Open-Access LLMs (2024.findings-acl)

Challenge:	Sparse Mixture-of-Experts (SMoE) architectures require loading all expert parameters . previous work focused on expert pruning and merging but focused on neuron-level structure .
Approach:	They propose a task-agnostic framework for expert pruning and reconstruction . it prunes redundant experts using router statistics, then decomposes them into neuron-level expert segments .
Outcome:	The proposed framework reduces the number of experts and memory usage, making it easier to deploy.

Copied to clipboard

Jingwei Yi, Rui Ye, Qisi Chen, Bin Zhu, Siheng Chen, Defu Lian, Guangzhong Sun, Xing Xie, Fangzhao Wu

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

Challenge:	Large language models (LLMs) are susceptible to malicious exploitation, but are often rejected and limited harmfulness is limited.
Approach:	They propose two types of reverse alignment techniques: reverse supervised fine-tuning (RSFT) and reverse preference optimization (RPO).
Outcome:	The proposed methods can significantly enhance the success rate and harmfulness of jailbreak attacks, but they face high rejection rates and limited harmfulness.

Copied to clipboard

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

Unlocking Human-Like Visible Logic: How Logic Diagrams Boost Logic Reasoning in Large Language Models? (2026.findings-acl)

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

Copied to clipboard

Xin Wu, Yuqi Bu, Mengchen Zhao, Qingbao Huang, Yi Cai

Generalized Intent Discovery: Learning from Open World Dialogue System (2022.coling-1)

Challenge:	Recent advances in large language models (LLMs) have demonstrated their remarkable capabilities in natural language understanding and generation, but they struggle with formal logical reasoning.
Approach:	They propose to incorporate visual logic diagrams into LLMs’ reasoning workflows to enhance their performance on formal logic tasks.
Outcome:	The proposed model improves on syllogistic and conditional reasoning with programmatically generated Venn, Euler, and Linear diagrams.

Copied to clipboard

Yutao Mou, Keqing He, Yanan Wu, Pei Wang, Jingang Wang, Wei Wu, Yi Huang, Junlan Feng, Weiran Xu

DocMMIR: A Framework for Document Multi-modal Information Retrieval (2025.findings-emnlp)

Challenge:	Existing intent classification models rely on a pre-defined intent set and supervised labels, which is limited in some practical scenarios.
Approach:	They propose to extend an IND intent classifier to an open-world intent set including IND and OOD intents.
Outcome:	The proposed task can classify IND and OOD intents while discovering new unlabeled OOD types incrementally.

Copied to clipboard

Zirui Li, Siwei Wu, Yizhi Li, Xingyu Wang, Yi Zhou, Chenghua Lin

SpecEdit: A Spectral Approach for Multi-Round Knowledge Editing (2026.findings-acl)

Challenge:	Existing multi-modal information retrieval models lack a comprehensive exploration of document-level retrieval . existing models suffer from the absence of cross-domain datasets at this granularity.
Approach:	They propose a multi-modal document retrieval framework to unify diverse document formats and domains with a comprehensive retrieval scenario.
Outcome:	The proposed framework improves document retrieval performance on a large multimodal dataset.

Copied to clipboard

Junxian Liu, Zikun Deng, Xin Wu, Dazhen Deng, Yi Cai

Explainability & Interpretability in NLP

Challenge:	Multi-round knowledge editing suffers from performance degradation as edits accumulate . intrinsic knowledge of model and historical edit memories are naively coupled during editing . SpecEdit improves model editing performance by reducing destructive coupling .
Approach:	They propose a spectral-based model editing module that integrates into existing editing methods without altering their original optimization procedures.
Outcome:	The proposed model improves performance on multiple LLMs and editing methods.

Evaluating Fairness in Large Vision-Language Models Across Diverse Demographic Attributes and Prompts (2025.findings-emnlp)

Copied to clipboard

Xuyang Wu, Yuan Wang, Hsin-Tai Wu, Zhiqiang Tao, Yi Fang

Tiny-NewsRec: Effective and Efficient PLM-based News Recommendation (2022.emnlp-main)

Challenge:	Large vision-language models have demonstrated strong capabilities in open-world visual understanding, but it is not clear how they address demographic biases in real life.
Approach:	They propose a method to assess visual fairness in LVLMs by question-answering/classification tasks.
Outcome:	The proposed approach improves transparency and offers a scalable solution for fairness mitigation.

Copied to clipboard

Yang Yu, Fangzhao Wu, Chuhan Wu, Jingwei Yi, Qi Liu

Unveiling Environmental Impacts of Large Language Model Serving: A Functional Unit View (2025.acl-long)

Challenge:	Existing work fine tunes the PLM with the news recommendation task, which can cause a domain shift problem.
Approach:	They propose a self-supervised method to adapt general PLM to news domain with a contrastive matching task between news titles and news bodies.
Outcome:	The proposed method can improve both the effectiveness and efficiency of the large PLM-based news recommendation model while maintaining its performance.

Copied to clipboard

Yanran Wu, Inez Hua, Yi Ding

Towards a Mechanistic Understanding of Large Reasoning Models: A Survey of Training, Inference, and Failures (2026.acl-long)

Challenge:	Existing studies benchmark carbon emissions but lack a standardized basis for comparison across different model configurations.
Approach:	They propose a functional unit (FU) as a standardized basis for comparison across different model configurations and introduce FUEL, the first FU-based framework for evaluating LLM serving’s environmental impact.
Outcome:	The proposed framework uncovers key insights and trade-offs in reducing carbon emissions by optimizing model size, quantization strategy, and hardware choice, paving the way for more sustainable LLM serving.

Copied to clipboard

Yi Hu, Jiaqi Gu, Ruxin Wang, Zijun Yao, Hao Peng, Xiaobao Wu, Jianhui Chen, Muhan Zhang, Liangming Pan

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

Challenge:	Recent research has shown that reinforcement learning can elicit intriguing emergent reasoning behaviors.
Approach:	They propose a comprehensive survey of the mechanistic understanding of large reasoning models . they organize findings into three core dimensions: 1) training dynamics, 2) reasoning mechanisms, and 3) unintended behaviors.
Outcome:	This paper synthesizes the mechanistic understanding of large reasoning models into three dimensions . authors outline a roadmap for future studies including improved interpretability and methodologies .

Copied to clipboard

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

Multi-Turn Response Selection for Chatbots with Deep Attention Matching Network (P18-1)

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

Copied to clipboard

Xiangyang Zhou, Lu Li, Daxiang Dong, Yi Liu, Ying Chen, Wayne Xin Zhao, Dianhai Yu, Hua Wu

Natural Language Interfaces

Challenge:	Existing models for matching dialogue responses rely on semantic and functional dependencies . a recent study only uses the last utterance in context for matching a reply .
Approach:	They propose a model that matches a response with its multi-turn context using attention.
Outcome:	The proposed model outperforms the state-of-the-art models on two large-scale multi-turn response selection tasks.

Does Reasoning Introduce Bias? A Study of Social Bias Evaluation and Mitigation in LLM Reasoning (2025.findings-emnlp)

Copied to clipboard

Xuyang Wu, Jinming Nian, Ting-Ruen Wei, Zhiqiang Tao, Hsin-Tai Wu, Yi Fang

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

Challenge:	Recent advances in large language models have enabled automatic generation of chain-of-thought reasoning . however, when reasoning steps reflect social stereotypes, they can reinforce harmful associations and lead to misleading conclusions.
Approach:	They propose a method that detects how model predictions change across incremental reasoning steps.
Outcome:	The proposed method outperforms a stereotype-free baseline and improves accuracy.

Copied to clipboard

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

NovBench: Evaluating Large Language Models on Academic Paper Novelty Assessment (2026.findings-acl)

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

Copied to clipboard

Wenqing Wu, Yi Zhao, Yuzhuo Wang, Siyou Li, Juexi Shao, Yunfei Long, Chengzhi Zhang

SRF: Enhancing Document-Level Relation Extraction with a Novel Secondary Reasoning Framework (2024.emnlp-main)

Challenge:	Existing methods for evaluating novelty have been proposed, but there is no systematic evaluation of their ability to generate novelty evaluations.
Approach:	They propose a benchmark to evaluate large language models’ ability to generate novelty evaluations in support of human peer review.
Outcome:	The proposed framework evaluates the quality of LLM-generated novelty evaluations under different prompting strategies.

Copied to clipboard

Fu Zhang, Qi Miao, Jingwei Cheng, Hongsen Yu, Yi Yan, Xin Li, Yongxue Wu

Information Extraction & Text Mining

Challenge:	Existing methods for document-level relation extraction ignore bidirectional mention interaction when generating relational features for entity pairs.
Approach:	They propose a document-level relation extraction model that incorporates bidirectional mention fusion and a simple yet effective evidence extraction module for relation prediction.
Outcome:	The proposed model achieves SOTA performance and the proposed method is effective and general when integrated into existing models.

Classic4Children: Adapting Chinese Literary Classics for Children with Large Language Model (2025.findings-naacl)

Copied to clipboard

Jiali Chen, Xusen Hei, Yuqi Xue, Zihan Wu, Jiayuan Xie, Yi Cai

Video-Language Understanding: A Survey from Model Architecture, Model Training, and Data Perspectives (2024.findings-acl)

Challenge:	Recent large language models (LLMs) overlook children’s reading preferences, which poses challenges in CLA.
Approach:	They propose a method that augments large language models with children's reading preferences for adaptation by obtaining characters' personalities and narrative structure as additional information for fine-grained instruction tuning.
Outcome:	The proposed method significantly improves performance in automatic and human evaluation.

Copied to clipboard

Thong Nguyen, Yi Bin, Junbin Xiao, Leigang Qu, Yicong Li, Jay Zhangjie Wu, Cong-Duy Nguyen, See-Kiong Ng, Anh Tuan Luu

Visual Data in NLP

Challenge:	Existing video-language understanding systems with human-like senses can mimic both our linguistic medium and visual environment with temporal dynamics.
Approach:	They propose to develop video-language understanding systems with human-like senses . they summarize their methods and highlight challenges associated with them .
Outcome:	The proposed models perform well in a variety of tasks and domains.

ThinkLinker: From Low-Rank Interaction to Knowledge-Aware Verification for Multimodal Entity Linking (2026.findings-acl)

Copied to clipboard

Yingyao Ma, Yuanyuan Zhou, Congyu Zhang, Yi Yuan, Jiasong Wu, Lotfi Senhadji, Huazhong Shu

M-ABSA: A Multilingual Dataset for Aspect-Based Sentiment Analysis (2025.emnlp-main)

Challenge:	Existing methods for multimodal entity linking rely on textual context for disambiguation . textual contextual information alone fails to resolve ambiguity, leading to unreliable disambiguations in weak contexts.
Approach:	They propose a two-stage multimodal entity linking framework called ThinkLinker . they propose fusion mechanism to model joint dependencies among features .
Outcome:	The proposed framework outperforms state-of-the-art models on public benchmark datasets.

Copied to clipboard

ChengYan Wu, Bolei Ma, Yihong Liu, Zheyu Zhang, Ningyuan Deng, Yanshu Li, Baolan Chen, Yi Zhang, Yun Xue, Barbara Plank

Multilinguality

Challenge:	Existing studies focus on English-centric aspects of sentiment analysis, limiting scope for multilingual evaluation and research.
Approach:	They propose to use a multilingual dataset to analyze aspects with associated sentiment elements in text.
Outcome:	The proposed dataset is the most extensive multilingual parallel dataset for ABSA to date.

HetGCoT: Heterogeneous Graph-Enhanced Chain-of-Thought LLM Reasoning for Academic Question Answering (2025.findings-emnlp)

Copied to clipboard

Runsong Jia, Mengjia Wu, Ying Ding, Jie Lu, Yi Zhang

Question Answering

Challenge:	graph neural networks capture structured graph information, but lack integration at the reasoning level.
Approach:	They propose a framework that leverages graph structural information to reason interpretable academic QA results.
Outcome:	The proposed framework outperforms sota baselines on OpenAlex and DBLP datasets.

IPR: Intelligent Prompt Routing with User-Controlled Quality-Cost Trade-offs (2025.emnlp-industry)

Copied to clipboard

Aosong Feng, Balasubramaniam Srinivasan, Yun Zhou, Zhichao Xu, Kang Zhou, Sheng Guan, Yueyan Chen, Xian Wu, Ninad Kulkarni, Yi Zhang, Zhengyuan Shen, Dmitriy Bespalov, Soumya Smruti Mishra, Yifei Teng, Darren Yow-Bang Wang, Haibo Ding, Lin Lee Cheong

Low-Resource NLP

Challenge:	Existing systems require users to manually select models or employ rigid routing rules that fail to capture the continuous spectrum of query complexity.
Approach:	They propose a quality-constrained intelligent prompt routing framework that automatically selects optimal models based on predicted response quality and user-specified tolerance levels.
Outcome:	The proposed framework achieves 43.9% cost reduction while maintaining quality parity with strongest model in the Claude family and processes requests with sub-150ms latency.

PLAWBENCH: A Rubric-Based Benchmark for Evaluating LLMs in Real-World Legal Practice (2026.acl-long)

Copied to clipboard

Yuzhen Shi, Huanghai Liu, Yiran HU, Song Gaojie, Xu Xinran, Yubo Ma, Tianyi Tang, Li Zhang, Qingjing Chen, Feng Di, Wenbo Lv, Weiheng Wu, Kexin Yang, Sen Yang, Wei Wang, Rongyao Shi, Qiu Yuanyang, Yuemeng Qi, Zhang Jingwen, Sui Xiaoyu, Yifan Chen, Zhang Yi, An Yang, Bowen Yu, Dayiheng Liu, Junyang Lin, Weixing Shen, Bing Zhao, Charles L. A. Clarke, HU Wei

Are You Copying My Model? Protecting the Copyright of Large Language Models for EaaS via Backdoor Watermark (2023.acl-long)

Challenge:	Existing benchmarks for large language models (LLMs) are coarse, single-dimensional metrics and do not explicitly assess fine-grained legal reasoning.
Approach:	They propose a Practical Law Benchmark to evaluate large language models in real-world legal practice scenarios.
Outcome:	The proposed model is based on 850 questions and 13 scenarios with expert-designed evaluation rubrics.

Copied to clipboard

Wenjun Peng, Jingwei Yi, Fangzhao Wu, Shangxi Wu, Bin Bin Zhu, Lingjuan Lyu, Binxing Jiao, Tong Xu, Guangzhong Sun, Xing Xie

Segment-Level and Category-Oriented Network for Knowledge-Based Referring Expression Comprehension (2023.findings-acl)

Challenge:	Large language models (LLMs) have demonstrated exceptional abilities in both text understanding and generation.
Approach:	They propose an Embedding Watermark method that implants backdoors on embeddings to protect copyright of large language models.
Outcome:	The proposed method protects the copyright of large language models without compromising service quality while minimizing the adverse impact on the original embeddings’ utility.

Copied to clipboard

Yuqi Bu, Xin Wu, Liuwu Li, Yi Cai, Qiong Liu, Qingbao Huang

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

Challenge:	Existing methods employ sentence-level retrieval and fusion methods, which may lead to similarity bias and interference from irrelevant information in unstructured knowledge sentences.
Approach:	They propose a segment-level and category-oriented network to solve similarity bias problem by segmenting and prompting knowledge retrieval methods and a category-based grounding method.
Outcome:	The proposed model eliminates similarity bias and improves the overall performance of the KB-REC task.

Copied to clipboard

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

Can LLMs Hear the Dogwhistle? (2026.findings-acl)

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

Copied to clipboard

Yifan Liu, Yi Lin, Xinwei Guo, Ziwei Wang, Jiaxin Zhang, Guanhua Chen, Haiyan Wu, Xiangyu Zhao, Xin Yao, Xuetao Wei

Graph-Reward-SQL: Execution-Free Reinforcement Learning for Text-to-SQL via Graph Matching and Stepwise Reward (2025.findings-emnlp)

Challenge:	Existing safety benchmarks focus on explicitly harmful content, but ignore context-dependent expressions such as dogwhistles.
Approach:	They propose a benchmark for evaluating LLM safety under dogwhistle-driven prompts . their findings expose a blind spot in current safety evaluation practices .
Outcome:	The proposed benchmark compared safety performance with toxic terms using dogwhistle-driven prompts.

Copied to clipboard

Han Weng, Puzhen Wu, Cui Longjie, Yi Zhan, Boyi Liu, Yuanfeng Song, Dun Zeng, Yingxiang Yang, Qianru Zhang, Dong Huang, Xiaoming Yin, Yang Sun, Xing Chen

StructFlowBench: A Structured Flow Benchmark for Multi-turn Instruction Following (2025.findings-acl)

Challenge:	Existing methods to enhance performance of large language models (LLMs) on Text-to-SQL tasks rely on execution-based or LLM-based reward models.
Approach:	They propose a reward model framework for RL-based Text-to-SQL that employs the GMNScore outcome reward model.
Outcome:	The proposed reward model outperforms existing reward models on standard benchmarks including Spider and BIRD.

Copied to clipboard

Jinnan Li, Jinzhe Li, Yue Wang, Yi Chang, Yuan Wu

Does RAG Introduce Unfairness in LLMs? Evaluating Fairness in Retrieval-Augmented Generation Systems (2025.coling-main)

Challenge:	Existing evaluation benchmarks focus on fine-grained constraint satisfaction and domain-specific capability assessment, yet overlook the crucial structural dependencies between dialogue turns that distinguish multi-turn from single-turn interactions.
Approach:	They propose a multi-turn instruction following benchmark with structural flow modeling that defines an innovative structural flow framework with six fundamental inter-turn relationships.
Outcome:	The proposed model is based on a framework with six fundamental inter-turn relationships and is able to analyze and generate specific dialogue flows tailored to specific scenarios.

Copied to clipboard

Xuyang Wu, Shuowei Li, Hsin-Tai Wu, Zhiqiang Tao, Yi Fang

Cross-document Misinformation Detection based on Event Graph Reasoning (2022.naacl-main)

Challenge:	Retrieval-Augmented Generation (RAG) models address fairness concerns with respect to sensitive attributes such as gender, geographic location, and other demographic factors.
Approach:	They propose a framework to evaluate fairness in RAG using scenario-based questions and analyzing disparities across demographic attributes.
Outcome:	The proposed framework analyzes disparities across demographic attributes and identifies fairness issues in retrieval and generation stages.

Copied to clipboard

Xueqing Wu, Kung-Hsiang Huang, Yi Fung, Heng Ji

RSVP: Reasoning Segmentation via Visual Prompting and Multi-modal Chain-of-Thought (2025.acl-long)

Challenge:	Existing methods for misinformation detection are limited to judging each document in isolation.
Approach:	They propose a task of cross-document misinformation detection that detects fake news from a cluster of topically related news documents.
Outcome:	The proposed method outperforms existing methods by up to 7 F1 points on this task.

Copied to clipboard

Yi Lu, Jiawang Cao, Yongliang Wu, Bozheng Li, Licheng Tang, Yangguang Ji, Chong Wu, Jay Wu, Wenbo Zhu

Meta-Reinforced Multi-Domain State Generator for Dialogue Systems (2020.acl-main)

Challenge:	Recent advances in multi-modal learning have enhanced MLLMs' ability to reason about visual content.
Approach:	They propose a framework that unifies multi-step multimodal reasoning with grounded visual understanding.
Outcome:	The proposed framework surpasses state-of-the-art methods by +6.5 gIoU and +9.2 cIou on ReasonSeg and achieves 49.7 mAP on SegInW under zero-shot settings.

Copied to clipboard

Yi Huang, Junlan Feng, Min Hu, Xiaoting Wu, Xiaoyu Du, Shuo Ma

MACAROON: Training Vision-Language Models To Be Your Engaged Partners (2024.findings-emnlp)

Challenge:	Existing methods to train a multi-domain dialogue state tracker are lacking in accuracy.
Approach:	They propose a Meta-Reinforced Multi-Domain State Generator to train a DST meta-learning model with a few domains as source domains and a new domain as target domain.
Outcome:	The proposed system outperforms the traditional training approach with extremely little training data in target domain.

Copied to clipboard

Shujin Wu, Yi Fung, Sha Li, Yixin Wan, Kai-Wei Chang, Heng Ji

OMIBench: Benchmarking Olympiad-Level Multi-Image Reasoning in Large Vision-Language Models (2026.acl-long)

Challenge:	Large vision-language models (LVLMs) generate detailed responses even when questions are ambiguous or unanswerable, leading to hallucinations and bias issues.
Approach:	They propose a three-tiered hierarchy for questions of invalid, ambiguous, and personalizable nature to measure the proactive engagement capabilities of LVLMs.
Outcome:	The proposed model generates contrastive response pairs for unlabeled questions, achieving 0.84 AAR, while maintaining comparable performance on general tasks.

Copied to clipboard

Qiguang Chen, Chengyu Luan, Jiajun Wu, Qiming Yu, Yi Yang, Yizhuo Li, Jingqi Tong, Xiachong Feng, Libo Qin, Wanxiang Che

Large Language Model Evaluation via Matrix Nuclear-Norm (2025.findings-emnlp)

Challenge:	Existing multimodal reasoning benchmarks for large vision-language models emphasize single-image analysis and fail to exploit contextual information across multiple images.
Approach:	They propose a benchmark to evaluate Olympiad-level reasoning when evidence is distributed over multiple images.
Outcome:	The proposed model outperforms existing models on bi-image Olympiads and Gemini-3-Pro on multimodal Olympiad-level reasoning tasks.

Copied to clipboard

Yahan Li, Tingyu Xia, Yuan Wu, Yi Chang

INDOORWORLD : Integrating Physical Task Solving and Social Simulation in A Heterogeneous Multi-Agent Environment (2025.findings-emnlp)

Challenge:	Large language models (LLMs) are computationally intensive due to their O(n3) time complexity with Singular Value Decomposition (SVD).
Approach:	They propose a metric to quantify the data compression proficiency of large language models and a convex approximation of matrix rank to capture both predictive discriminability and diversity.
Outcome:	The proposed model achieves speeds 8 to 24 times faster than Matrix Entropy for the CEREBRAS-GPT model as models increase from 111M to 6.7B .

Copied to clipboard

Dekun Wu, Frederik Brudy, Bang Liu, Yi Wang

Challenge:	Existing virtual environments for LLM agent research focus on task solving or social simulation . existing environments for virtual environments lack physical grounding of social behaviors .
Approach:	They propose a virtual environment that tightly integrates physical and social dynamics . IndoorWorld is a heterogeneous multi-agent environment that integrates social and physical dynamics based on a simulation of physical environments .
Outcome:	The proposed environment integrates physical and social dynamics into a heterogeneous multi-agent environment.

Query-Driven Multimodal GraphRAG: Dynamic Local Knowledge Graph Construction for Online Reasoning (2025.findings-acl)

Copied to clipboard

Chenyang Bu, Guojie Chang, Zihao Chen, CunYuan Dang, Zhize Wu, Yi He, Xindong Wu

R3: End-to-End Reasoning-based Planning for Multi-step Retrosynthesis via Reinforcement Learning (2026.acl-long)

Challenge:	Existing approaches to build knowledge graphs with LLMs are constrained by static knowledge bases and ineffective multimodal data integration.
Approach:	They propose a Query-Driven Multimodal GraphRAG framework that dynamically constructs local knowledge graphs tailored to query semantics.
Outcome:	The proposed framework outperforms unsupervised competitors in cross-modal understanding of complex queries.

Copied to clipboard

YiFei Wang, Qizhi Pei, Jiangtao Feng, Yuntian Shi, Yi Duan, Lihao Wang, Lei Bai, Lijun Wu, Wei-Ying Ma, Hao Zhou

Training-free LLM Merging for Multi-task Learning (2025.acl-long)

Challenge:	Experimental results show that R3 is a superior alternative to traditional search algorithms for multistep retrosynthesis planning.
Approach:	They propose a framework that reformulates multistep retrosynthetic planning as a generative reasoning task.
Outcome:	The proposed framework achieves state-of-the-art Top-1 accuracy of 43.7% on retrobench . it leverages Large Language Models to reformulate multistep retrosynthesis as a generative reasoning task.

Copied to clipboard

Zichuan Fu, Xian Wu, Yejing Wang, Wanyu Wang, Shanshan Ye, Hongzhi Yin, Yi Chang, Yefeng Zheng, Xiangyu Zhao

Evidence-Aligned Entity Verification for Hallucination Detection in Retrieval-Augmented Generation (2026.findings-acl)

Challenge:	Large Language Models (LLMs) have demonstrated exceptional capabilities across diverse natural language processing tasks.
Approach:	They propose a training-free method for unifying different specialized LLMs into a single model using model-wise and layer-wise pruning and scaling.
Outcome:	The proposed method outperforms existing merging techniques and surpasses models fine-tuned on combined datasets in most scenarios.

Copied to clipboard

Runsong Jia, Zhen Fang, Mengjia Wu, Jie Lu, Yi Zhang

MARCH: Multi-Agent Radiology Clinical Hierarchy for CT Report Generation (2026.acl-short)

Challenge:	Existing methods for hallucination detection depend on internal signals like uncertainty and self-consistency checks to identify unreliable outputs.
Approach:	They propose a retrieval-augmented generation method to enhance hallucination detection by addressing information updating challenges.
Outcome:	The proposed method improves on existing methods with strong generalization capabilities.

Copied to clipboard

Yi Lin, Yihao Ding, Yonghui Wu, Yifan Peng

Three Minds, One Legend: Jailbreak Large Reasoning Model with Adaptive Stacked Ciphers (2026.findings-acl)

Challenge:	Automated 3D radiology report generation suffers from clinical hallucinations and lacks the iterative verification characteristic of clinical workflows.
Approach:	They propose a multi-agent framework that emulates the professional hierarchy of radiology departments and assigns specialized roles to distinct agents.
Outcome:	The proposed framework outperforms state-of-the-art models in clinical fidelity and linguistic accuracy on the RadGenome-ChestCT dataset.

Copied to clipboard

Nguyen Viet Anh, Shiqian Zhao, Gia Dao, Runyi Hu, Yi Xie, Xiaobao Wu, Anh Tuan Luu

ChatMusician: Understanding and Generating Music Intrinsically with LLM (2024.findings-acl)

Challenge:	Existing jailbreak methods struggle to balance effectiveness with robustness against adaptive safety mechanisms.
Approach:	They propose a novel approach that targets Large Reasoning Models through an adaptive encryption pipeline designed to overwhelm their reasoning capabilities.
Outcome:	The proposed approach achieves an attack success rate of 85.6% on OpenAI GPT-o4-mini, outperforming state-of-the-art baselines by a significant margin of 17.2%.

Copied to clipboard

Ruibin Yuan, Hanfeng Lin, Yi Wang, Zeyue Tian, Shangda Wu, Tianhao Shen, Ge Zhang, Yuhang Wu, Cong Liu, Ziya Zhou, Liumeng Xue, Ziyang Ma, Qin Liu, Tianyu Zheng, Yizhi Li, Yinghao Ma, Yiming Liang, Xiaowei Chi, Ruibo Liu, Zili Wang, Chenghua Lin, Qifeng Liu, Tao Jiang, Wenhao Huang, Wenhu Chen, Jie Fu, Emmanouil Benetos, Gus Xia, Roger Dannenberg, Wei Xue, Shiyin Kang, Yike Guo

Towards Low-Resource Semi-Supervised Dialogue Generation with Meta-Learning (2020.findings-emnlp)

Challenge:	Despite LLMs' impressive capabilities in musical knowledge, music reasoning remains an unsolved task.
Approach:	They propose an open-source large language model (LLM) that integrates intrinsic musical abilities into LLaMA2 and GPT-3.5.
Outcome:	The proposed model can understand and generate music with a pure text tokenizer without external multi-modal neural structures or tokenizers.

Copied to clipboard

Yi Huang, Junlan Feng, Shuo Ma, Xiaoyu Du, Xiaoting Wu

AutoSchemaKG: Autonomous Knowledge Graph Construction through Dynamic Schema Induction from Web-Scale Corpora (2026.acl-long)

Challenge:	Existing systems that use labelled data to generate dialogues are lacking in high accuracy.
Approach:	They propose a meta-learning based semi-supervised explicit dialogue state tracker for neural dialogue generation, denoted as MEDST.
Outcome:	The proposed system outperforms existing systems by 18.7% goal accuracy and 14.3% entity match rate on the KVRET corpus with 2% labelled data in semi-supervision.

Copied to clipboard

Jiaxin Bai, Wei Fan, Qi Hu, Qing Zong, Chunyang Li, Hong Ting Tsang, Hongyu Luo, Yauwai Yim, Haoyu Huang, Xiao Zhou, Feng Qin, Tianshi Zheng, Xi Peng, Xin Yao, Huiwen Yang, Leijie Wu, JI Yi, Gong Zhang, Renhai Chen, Yangqiu Song

BV-Blend: Uncertainty-Weighted Historical Baselines for Stable Critic-Free RL with Verifiable Rewards (2026.findings-acl)

Challenge:	Existing knowledge graph construction frameworks require predefined schemas, limiting their scalability and domain coverage.
Approach:	They propose a framework for fully autonomous knowledge graph construction that eliminates the need for predefined schemas.
Outcome:	The proposed framework outperforms state-of-the-art models on multi-hop QA tasks and enhances LLM factuality.

Copied to clipboard

Yupeng Chang, Yuan Wu, Yi Chang

Scene Graph Enhanced Pseudo-Labeling for Referring Expression Comprehension (2023.findings-emnlp)

Challenge:	Critic-free reinforcement learning with verifiable rewards (RLVR) is a practical paradigm for aligning Large Language Models.
Approach:	They propose a framework that stabilizes advantage estimation by combining prompt-local on-policy statistics with semantic-cluster-conditioned historical moments.
Outcome:	Experiments show that RLVR improves training stability and performance compared to critic-based methods . compared with other approaches, RL VR improves in cold-start regimes with binary verifiers .

Copied to clipboard

Cantao Wu, Yi Cai, Liuwu Li, Jiexin Wang

Chinese Idiom Paraphrasing (2023.tacl-1)

Challenge:	Referring expression comprehension is a visual-linguistic task that involves localizing objects in images based on textual referring expressions.
Approach:	They propose a scene graph-based framework that generates high-quality pseudo region-query pairs . their method captures relationships between objects in images and generates expressions enriched with relation information.
Outcome:	The proposed framework outperforms existing methods by 10%, 12%, and 11% on RefCOCO, RefCoCO+, and Ref COCOg datasets.

Copied to clipboard

Jipeng Qiang, Yang Li, Chaowei Zhang, Yun Li, Yi Zhu, Yunhao Yuan, Xindong Wu

Do Large Language Models Rank Fairly? An Empirical Study on the Fairness of LLMs as Rankers (2024.naacl-long)

Challenge:	Chinese idioms are hard to understand by children and non-native speakers due to their non-compositionality and metaphorical meaning.
Approach:	They propose a task to rephrase idiom-containing sentences to non-idiomatic ones under the premise of preserving the original sentence’s meaning.
Outcome:	The proposed method has better performance than baselines based on the established dataset.

Copied to clipboard

Yuan Wang, Xuyang Wu, Hsin-Tai Wu, Zhiqiang Tao, Yi Fang

From Query to Counsel: Structured Reasoning with a Multi-Agent Framework and Dataset for Legal Consultation (2026.acl-long)

Challenge:	Recent studies have shown that Large Language Models (LLMs) are more efficient in natural language understanding tasks.
Approach:	They evaluate large language models (LLMs) using a TREC Fair Ranking dataset . they assess fairness from both user and content perspectives .
Outcome:	The proposed model outperforms the existing models in the fair ranking task.

Copied to clipboard

Mingfei Lu, Yi Zhang, Mengjia Wu, Yue Feng

Unsupervised Extractive Summarization by Pre-training Hierarchical Transformers (2020.findings-emnlp)

Challenge:	Legal consultation question answering presents unique challenges compared to traditional legal QA tasks .
Approach:	They propose a framework that converts queries into a legal element graph . jurisMA supports dynamic routing, statutory grounding, and stylistic optimization .
Outcome:	The proposed framework outperforms general-purpose and legal-domain LLMs across multiple lexical and semantic metrics.

Copied to clipboard

Shusheng Xu, Xingxing Zhang, Yi Wu, Furu Wei, Ming Zhou

Information Extraction & Text Mining

Challenge:	Existing methods for document summarization use graphs and unlabeled documents . Existing models require labeled data, and it is expensive to create summarized documents.
Approach:	They propose to rank sentences using transformer attentions and pre-training objectives by unlabeled documents.
Outcome:	The proposed model achieves state-of-the-art on unsupervised summarization and is less dependent on sentence positions.

Efficient-FedRec: Efficient Federated Learning Framework for Privacy-Preserving News Recommendation (2021.emnlp-main)

Copied to clipboard

Jingwei Yi, Fangzhao Wu, Chuhan Wu, Ruixuan Liu, Guangzhong Sun, Xing Xie

Improve Decoding Factuality by Token-wise Cross Layer Entropy of Large Language Models (2025.findings-naacl)

Challenge:	Existing news recommendation methods rely on centralized storage of user click behavior data, which may lead to privacy concerns and hazards.
Approach:	They propose a federated learning framework for privacy-preserving news recommendation . they propose aggregation of news representations and user model by a client .
Outcome:	The proposed framework reduces computation and communication cost on clients while keeping promising model performance.

Copied to clipboard

Jialiang Wu, Yi Shen, Sijia Liu, Yi Tang, Sen Song, Xiaoyi Wang, Longjun Cai

LoRA-MGPO: Mitigating Double Descent in Low-Rank Adaptation via Momentum-Guided Perturbation Optimization (2025.findings-emnlp)

Challenge:	Large language models (LLMs) often struggle with the issue of generating inaccurate or fabricated content even when they possess correct knowledge.
Approach:	They propose a decoding method that mitigates hallucinations without extra training . they propose entropy eNhanced decoding that leverages inner probability changes .
Outcome:	The proposed method improves the truthfulness and informativeness of generation while maintaining robust QA accuracy.

Copied to clipboard

Yupeng Chang, Chenlu Guo, Yi Chang, Yuan Wu

Step Feasibility-Aware and Error-Correctable Entailment Tree Generation (2024.lrec-main)

Challenge:	Low-Rank Adaptation (LoRA) adapts large language models by training only a small fraction of parameters, but as the rank of the low-rank matrices increases, LoRA exhibits an unstable “double descent” phenomenon, which delays convergence and impairs generalization by causing instability due to the attraction to sharp local minima.
Approach:	They propose a framework that incorporates Momentum-Guided Perturbation Optimization (MGPO) MGPO stabilizes training dynamics by mitigating double descent phenomenon and guiding weight perturbations using momentum vectors from the optimizer’s state.
Outcome:	The proposed framework improves performance on natural language understanding benchmarks and shows that it improves convergence and generalization.

Copied to clipboard

Junyue Song, Xin Wu, Yi Cai

Truth or Sophistry? LoFa: A Benchmark for LLM Robustness Against Logical Fallacies (2026.acl-long)

Challenge:	Existing methods for generating entailment trees suffer from false feasible steps, resulting in error propagation.
Approach:	They propose an iterative entailment tree generation framework with step feasibility perception and state error handling mechanisms to enhance the interpretability of QA systems.
Outcome:	The proposed framework improves the interpretation of QA systems by demonstrating that it is feasible to choose steps that are false feasible and error propagating.

Copied to clipboard

Xudong Shen, li Yuan, Ye Chen, Xin Wu, Yi Cai, Zhiyong Wu

Robustness in NLP

Challenge:	Prior work has focused on the ability of Large Language Models to identify or classify fallacies, but their robustness against these fallacias in persuasive contexts remains largely unexplored.
Approach:	They propose a new metric to assess LLM robustness against fallacies by pairing factual questions with fallacious arguments and developing a multi-round debate framework to assess model resilience.
Outcome:	The proposed metric disentangles robustness from a model’s knowledge limitations and demonstrates unique vulnerability profiles across models.

CoTKR: Chain-of-Thought Enhanced Knowledge Rewriting for Complex Knowledge Graph Question Answering (2024.emnlp-main)

Copied to clipboard

Yike Wu, Yi Huang, Nan Hu, Yuncheng Hua, Guilin Qi, Jiaoyan Chen, Jeff Pan

Natural Language Interfaces

Challenge:	Existing knowledge rewriting methods may include irrelevant information, omit crucial details, or fail to align with the question’s semantics.
Approach:	They propose a new rewriting method CoTKR for generating reasoning traces and corresponding knowledge in an interleaved manner, thereby mitigating the limitations of single-step knowledge rewrite.
Outcome:	The proposed method mitigates the limitations of single-step knowledge rewriting and bridges the preference gap between the knowledge reactor and the question answering (QA) model.

UniMSE: Towards Unified Multimodal Sentiment Analysis and Emotion Recognition (2022.emnlp-main)

Copied to clipboard

Guimin Hu, Ting-En Lin, Yi Zhao, Guangming Lu, Yuchuan Wu, Yongbin Li

Sentiment Analysis

Challenge:	Existing studies study sentiment and emotion separately and do not fully exploit the complementary knowledge behind the two.
Approach:	They propose a multimodal sentiment knowledge-sharing framework that unifies MSA and ERC tasks from features, labels, and models.
Outcome:	The proposed framework achieves consistent improvements on four public benchmark datasets on MOSI, MOSEI, MELD, and IEMOCAP.

A Survey of Retentive Network (2026.findings-acl)

Copied to clipboard

Haiqi Yang, Zhiyuan Li, Yi Chang, Yuan Wu

Challenge:	Existing studies on the effectiveness of the Retentive Networks have not yet been conducted.
Approach:	They propose a retention mechanism that integrates the inductive bias of recurrent neural networks with the parallelizable training advantages of attention-based models.
Outcome:	The proposed retention mechanism combines the inductive bias of recurrent neural networks with the parallelizable training advantages of attention-based models.

Language Models can Evaluate Themselves via Probability Discrepancy (2024.findings-acl)

Copied to clipboard

Tingyu Xia, Bowen Yu, Yuan Wu, Yi Chang, Chang Zhou

AlphaEdit+: Model Editing in the Presence of Conflicting and Inconsistent Knowledge (2026.findings-acl)

Challenge:	Existing evaluation frameworks focus on superficial text differences and fail to align with human judgment.
Approach:	They propose a new method to evaluate the performance of Large Language Models (LLMs) by calculating probability discrepancies between original response generation and revised versions of LLMs.
Outcome:	The proposed method eliminates the need for training an additional evaluation model or relying on external proprietary models such as GPT-4 as a judger.

Copied to clipboard

Qing Liu, Jianhao Zhang, Ou Wu, Michael Ng, Yi Du

Challenge:	Existing methods for knowledge editing struggle with knowledge conflicts and inconsistencies.
Approach:	They propose a new method for knowledge editing that relaxes null-space constraints and introduces a weighting scheme to mitigate conflicts between new and historical knowledge.
Outcome:	The proposed method outperforms existing methods on challenging datasets and outperformed existing methods.

SOS-LoRA: Static Orthogonal-Subspace Low-Rank Adaptation with Fixed Multi-Scale Scaling (2026.acl-long)

Copied to clipboard

Yupeng Chang, Yuan Wu, Yi Chang

Triggerless Backdoor Attack for NLP Tasks with Clean Labels (2022.naacl-main)

Challenge:	Low-Rank Adaptation (LoRA) is a parameter-efficient fine-tuning method for large language models.
Approach:	They propose a drop-in extension that reparameterizes a rank-rtot update as a sum of K static low-rank experts.
Outcome:	Experiments on reasoning and knowledge-intensive benchmarks show consistent gains over matched-budget LoRA.

Copied to clipboard

Leilei Gan, Jiwei Li, Tianwei Zhang, Xiaoya Li, Yuxian Meng, Fei Wu, Yi Yang, Shangwei Guo, Chun Fan

Robustness in NLP

Challenge:	Backdoor attacks are a new threat to neural natural language processing models due to the fragility and lack of interpretability of NLP models.
Approach:	They propose a method to perform backdoor attacks without an external trigger . they propose to use clean-labeled examples to generate poisoned clean-labelled examples .
Outcome:	The proposed strategy is effective and hard to defend due to its triggerless nature.

TSDG: Content-aware Neural Response Generation with Two-stage Decoding Process (2020.findings-emnlp)

Copied to clipboard

Junsheng Kong, Zhicheng Zhong, Yi Cai, Xin Wu, Da Ren

AIGT: AI Generative Table Based on Prompt (2025.coling-main)

Challenge:	Empirical results show that generative models often use a single decoder to generate a complete response at a stroke.
Approach:	They propose a content-aware model with two-stage decoding process to separate content words from function words.
Outcome:	The proposed model outperforms competing models in automatic and human evaluation on two datasets.

Copied to clipboard

Mingming Zhang, Zhiqing Xiao, Guoshan Lu, Sai Wu, Weiqiang Wang, Xing Fu, Can Yi, Junbo Zhao

Exploiting Contrastive Learning and Numerical Evidence for Confusing Legal Judgment Prediction (2023.findings-emnlp)

Challenge:	Tabular data is an essential resource for many fields, but current methods do not fully utilize the rich information available in tables.
Approach:	They propose a method that utilizes metadata information to generate tabular data . they propose long-token partitioning algorithms that enable AIGT to model tables of any scale .
Outcome:	The proposed approach achieves state-of-the-art on 14 out of 20 public datasets and two real industry datasets within the Alipay risk control system.

Copied to clipboard

Leilei Gan, Baokui Li, Kun Kuang, Yating Zhang, Lei Wang, Anh Luu, Yi Yang, Fei Wu

PILE: Pairwise Iterative Logits Ensemble for Multi-Teacher Labeled Distillation (2022.emnlp-industry)

Challenge:	Existing studies fail to distinguish different classification errors with a standard cross-entropy classification loss and ignore the numbers in the fact description for predicting the term of penalty.
Approach:	They propose to extract crime amounts from fact description and use them to learn distinguishable representations to exploit the numbers in the fact description for predicting the term of penalty.
Outcome:	The proposed method achieves state-of-the-art results on real-world datasets and ablation studies demonstrate the effectiveness of each component.

Copied to clipboard

Lianshang Cai, Linhao Zhang, Dehong Ma, Jun Fan, Daiting Shi, Yi Wu, Zhicong Cheng, Simiu Gu, Dawei Yin

Walk in Others’ Shoes with a Single Glance: Human-Centric Visual Grounding with Top-View Perspective Transformation (2025.acl-long)

Challenge:	Pre-trained language models have been a key part of ranking systems . knowledge distillation is widely used to maintain high performance while keeping efficient computations.
Approach:	They propose an algorithm to combine knowledge from multi-teachers and label information to achieve competitive performance in offline and online experiments.
Outcome:	The proposed method has been deployed in a real-world commercial search system.

Copied to clipboard

Yuqi Bu, Xin Wu, Zirui Zhao, Yi Cai, David Hsu, Qiong Liu

LLM as a metric critic for low resource relation identification (2024.findings-emnlp)

Challenge:	Existing VLMs are insensitive to information differences induced by slight perspective changes.
Approach:	They propose a visual perspective-taking task that requires robots to interpret human-centric instructions and identify corresponding objects from robot perspectives.
Outcome:	The proposed method improves performance by up to 18% and generalizes effectively to robotic and dynamic scenarios.

Copied to clipboard

Zhe Yang, Yi Huang, Yaqin Chen, Xiaoting Wu, Junlan Feng, Chao Deng

Don’t Take the Premise for Granted: Evaluating the Premise Critique Ability of Large Language Models (2025.findings-emnlp)

Challenge:	Existing studies show that small language models (SLMs) overfit in low resource situations . however, the gap between pre-training and fine-tuning leads to performance decay .
Approach:	They propose to combine large language models and LLM for relation identification by co-evolution . they propose to use a masked language model prompt to generate a relation identification task .
Outcome:	The proposed model can handle low resource relation identification tasks with minimal overfitting . the proposed model provides essential background knowledge to assist training process .

Copied to clipboard

Jinzhe Li, Gengxu Li, Yi Chang, Yuan Wu

Abstract-level Deductive Reasoning for Pre-trained Language Models (2024.lrec-main)

Challenge:	Existing studies assess LLMs’ reasoning ability in ideal settings, ignoring their vulnerabilities when faced with flawed premises.
Approach:	They propose to evaluate LLMs' ability to proactively identify and articulate errors in input premises.
Outcome:	The proposed model enables LLMs to proactively identify and articulate errors in input premises.

Copied to clipboard

Xin Wu, Yi Cai, Ho-fung Leung

Measuring Human Contribution in AI-Assisted Content Generation (2026.acl-long)

Challenge:	Existing methods fine-tune PLMs using the validity label and instance-level reasoning proofs as supervision signals.
Approach:	They propose to train PLMs to learn general reasoning patterns rather than instance-level knowledge by predicting the abstract reasoning proof of each sample.
Outcome:	The proposed model significantly reduces the impact of learning instance-level knowledge (over 70%)

Copied to clipboard

Yueqi Xie, Tao Qi, Jingwei Yi, Xiyuan Yang, Ryan Whalen, Junming Huang, Qian Ding, Yu Xie, Xing Xie, Fangzhao Wu

CMDL: A Large-Scale Chinese Multi-Defendant Legal Judgment Prediction Dataset (2024.findings-acl)

Challenge:	generative AI has created a new way to generate content with humans . varying degrees of human contribution in content generation poses significant challenges for the delineation of originality .
Approach:	They propose a framework to measure human contribution in AI-assisted content generation by calculating mutual information between human input and AI-aided output relative to self-information of AI-assist output.
Outcome:	The proposed measure discriminates between varying degrees of human contribution across multiple creative domains and is validated in real-world applications.

Copied to clipboard

Wanhong Huang, Yi Feng, Chuanyi Li, Honghan Wu, Jidong Ge, Vincent Ng

Challenge:	Legal Judgment Prediction (LJP) has attracted significant attention in recent years.
Approach:	They propose a large-scale Chinese Multi-Defendant LJP dataset . they propose case-level evaluation metrics dedicated for the multi-defendant scenario .
Outcome:	The proposed methods show weaknesses when applied to cases involving multiple defendants.

Beyond Static Profiles: Capturing the Fluidity of User Preferences in Diverse Scenarios (2026.findings-acl)

Copied to clipboard

Chunyang Gao, Yi Huang, Jingyu Yao, Xiaoting Wu, Junlan Feng

Challenge:	Existing approaches to personalize Large Language Models often default to homogeneous behaviors . preferences can shift, and conflict, depending on context, authors argue .
Approach:	They propose a hierarchical taxonomy to differentiate between stable and situational preferences . they use a dataset of 10k meticulously curated preferences to test their taxonomies .
Outcome:	The proposed model differentiates between stable and situational preferences based on curated user preferences . it provides a practical testbed for advancing dynamic, context-aware personalization in conversational agents.

OS Agents: A Survey on MLLM-based Agents for Computer, Phone and Browser Use (2025.acl-long)

Copied to clipboard

Xueyu Hu, Tao Xiong, Biao Yi, Zishu Wei, Ruixuan Xiao, Yurun Chen, Jiasheng Ye, Meiling Tao, Xiangxin Zhou, Ziyu Zhao, Yuhuai Li, Shengze Xu, Shenzhi Wang, Xinchen Xu, Shuofei Qiao, Zhaokai Wang, Kun Kuang, Tieyong Zeng, Liang Wang, Jiwei Li, Yuchen Eleanor Jiang, Wangchunshu Zhou, Guoyin Wang, Keting Yin, Zhou Zhao, Hongxia Yang, Fan Wu, Shengyu Zhang, Fei Wu

AdvPicker: Effectively Leveraging Unlabeled Data via Adversarial Discriminator for Cross-Lingual NER (2021.acl-long)

Challenge:	a new generation of (M)LLMs is enabling the creation of superintelligent AI assistants . OS Agents can complete tasks autonomously and have the potential to significantly enhance the lives of billions of users worldwide.
Approach:	They propose to build OS Agents that operate within operating systems' GUIs and GUIs . they examine evaluation metrics and benchmarks to identify promising directions .
Outcome:	The proposed agents are based on operating systems (OS) and operating systems frameworks.

Copied to clipboard

Weile Chen, Huiqiang Jiang, Qianhui Wu, Börje Karlsson, Yi Guan

Equal Truth: Rumor Detection with Invariant Group Fairness (2025.findings-emnlp)

Challenge:	Named entity recognition models rely on expensive labeled data for training, which is not always available across languages.
Approach:	They propose an adversarial approach where an encoder learns entity domain knowledge from labeled source-language data and better shared features are captured via adversarially trained discriminators.
Outcome:	The proposed approach outperforms existing state-of-the-art methods on standard benchmark datasets and outperformed existing methods on the target language.

Copied to clipboard

Junyi Chen, Mengjia Wu, Qian Liu, Jing Sun, Ying Ding, Yi Zhang

OneRec-Think: In-Text Reasoning for Generative Recommendation (2026.acl-long)

Challenge:	Existing rumor detection methods rarely consider fairness issues inherent in the model . this can lead to biased predictions across stakeholder groups, undermining their detection effectiveness .
Approach:	They propose a framework to address fairness issues inherent in rumor detection models . they perform unsupervised partitioning to dynamically identify potential unfair data patterns . then, they apply invariant learning to these partitions to extract fair and informative feature representations .
Outcome:	The proposed method outperforms strong baselines regarding detection and fairness performance . it also shows robust performance on out-of-distribution samples .

Copied to clipboard

Zhanyu Liu, Shiyao Wang, Xingmei Wang, Rongzhou Zhang, Jiaxin Deng, Honghui Bao, Jinghao Zhang, Wuchao Li, PengFei Zheng, Xiangyu Wu, Yifei Hu, Qigen Hu, Xinchen Luo, Lejian Ren, Zhang Zixing, Qianqian Wang, Kuo Cai, Yunfan Wu, Hongtao Cheng, Zexuan Cheng, Lu Ren, Huanjie Wang, Yi Su, Ruiming Tang, Kun Gai, Guorui Zhou

UMPIRE: Unveiling LLM-generated Posts via Redundant Expressions (2026.acl-long)

Challenge:	Existing generative models lack the capacity for explicit and controllable reasoning, a key advantage of LLMs.
Approach:	They propose a framework that integrates dialogue, reasoning, and personalized recommendation.
Outcome:	Experiments across public benchmarks show state-of-the-art performance.

Copied to clipboard

Xiaoquan Yi, Haixing Wu, Haozhao Wang, Yichen Li, Yuhua Li, Rui Zhang, Ruixuan Li

SteerLM: Attribute Conditioned SFT as an (User-Steerable) Alternative to RLHF (2023.findings-emnlp)

Challenge:	Existing methods to verify the provenance of multimodal content fall into two categories: traditional methods rely on low-level artifacts or unimodal statistics.
Approach:	They propose a semantic decomposition mechanism that disentangles textual embeddings into redundant and complementary components and a latent redundancy regularization loss to encourage LLM-generated content to exhibit high semantic redundancies.
Outcome:	The proposed method outperforms state-of-the-art detection methods across multiple datasets and achieves 5.38% improvement in accuracy.

Copied to clipboard

Yi Dong, Zhilin Wang, Makesh Sreedhar, Xianchao Wu, Oleksii Kuchaiev

R-LoRA: Randomized Multi-Head LoRA for Efficient Multi-task Learning (2025.findings-emnlp)

Challenge:	supervised fine-tuning and reinforcement learning from human feedback (RLHF) are not effective in generating useful and high-quality responses.
Approach:	They propose a supervised fine-tuning method that empowers end-users to control responses during inference.
Outcome:	Experiments show that supervised fine-tuning and reinforcement learning from human feedback (RLHF) can generate helpful and high-quality responses while maintaining customizability.

Copied to clipboard

Jinda Liu, Yi Chang, Yuan Wu

NLoRA: Nyström-Initiated Low-Rank Adaptation for Large Language Models (2025.findings-emnlp)

Challenge:	Low-Rank Adaptation (LoRA) improves performance in multi-task learning by diversifying the head matrices through Multi-Head Dropout and Multi-head Random Initialization.
Approach:	They propose a low-rank adaptive approach to fine-tune large language models by approximating weight updates through low-ranked matrices.
Outcome:	The proposed approach improves performance in multi-task learning while reducing memory usage and training time.

Copied to clipboard

Chenlu Guo, Yi Chang, Yuan Wu

Thinking Alignment of Scenario-Oriented User Simulation (2026.acl-long)

Challenge:	Parameter-efficient fine-tuning is essential for adapting large language models (LLMs). However, LoRA suffers from slow convergence and some recent LoRA variants, such as PiSSA, rely on Singular Value Decomposition (SVD) for initialization.
Approach:	They propose to introduce a small intermediate matrix between the low-rank matrices (A) and (B) and propose NyströmLoRA (NLoRA) which leverages Nyström-based initialization for SLoRA to improve its effectiveness and efficiency.
Outcome:	The proposed approach improves on 5 natural language generation tasks and 8 natural language understanding tasks with minimal parameter overhead.

Copied to clipboard

Xiaoting Wu, Yi Huang, Chunyang Gao, Mengfei Guo, Jingyu Yao, Junlan Feng

AraMUS: Pushing the Limits of Data and Model Scale for Arabic Natural Language Processing (2023.findings-acl)

Challenge:	Existing user simulators based on prompting to role-play or SFT focus on imitating textual utterances without considering multi-faceted cognitive processes that underlie human decision-making during interactions.
Approach:	They construct a user-simulator dataset that augments 51k human–LLM conversations by reconstructing the user’s inner reasoning during and at the end of each dialogue.
Outcome:	The proposed user simulators augment 51k human–LLM conversations by reconstructing the user’s inner reasoning both during and at the end of each dialogue.

Copied to clipboard

Asaad Alghamdi, Xinyu Duan, Wei Jiang, Zhenhai Wang, Yimeng Wu, Qingrong Xia, Zhefeng Wang, Yi Zheng, Mehdi Rezagholizadeh, Baoxing Huai, Peilun Cheng, Abbas Ghaddar

TOREE: Evaluating Topic Relevance of Student Essays for Chinese Primary and Middle School Education (2024.findings-acl)

Challenge:	Developing monolingual large Pre-trained Language Models (PLMs) is shown to be very successful in handling different tasks in Natural Language Processing (NLP).
Approach:	They present AraMUS, the largest Arabic PLM with 11B parameters trained on 529GB of high-quality Arabic textual data.
Outcome:	The proposed model achieves state-of-the-art performance on a diverse set of Arabic classification and generative tasks.

Copied to clipboard

Xinlin Zhuang, Hongyi Wu, Xinshu Shen, Peimin Yu, Gaowei Yi, Xinhao Chen, Tu Hu, Yang Chen, Yupei Ren, Yadong Zhang, Youqi Song, Binxuan Liu, Man Lan

Rhombus: Incentivizing Coordination in Parallel Thinking through Reinforcement Learning (2026.findings-acl)

Challenge:	Existing research on Automatic Essay Scoring (AES) for Chinese essays has overlooked topic relevance and lacks detailed feedback.
Approach:	They propose to use TOREE to assess topic relevance in Chinese primary and middle school students’ essays to improve automatic and human evaluations.
Outcome:	The proposed method significantly improves both automatic and human evaluations across four diverse LLMs.

Copied to clipboard

Ziyuan Nan, Qi Yi, Di Huang, Yutong Wu, Guanhua Huang, Xue Gong, Kejiao Li, Yuhao Jiang, Chenchen Zhang, Zenan Xu, Xing Hu, Bo Zhou

Conic10K: A Challenging Math Problem Understanding and Reasoning Dataset (2023.findings-emnlp)

Challenge:	Parallel thinking is a promising avenue for scaling test-time compute in Large Language Models . however, coordinating the exploration and aggregation stages remains challenging .
Approach:	They propose a parallel thinking framework that explicitly incentivizes coordination between components via end-to-end reinforcement learning.
Outcome:	The proposed framework improves accuracy by 6.0% over long chain-of-thought baselines while reducing wall-clock latency by 39.4% under matched token budgets.

Copied to clipboard

Haoyi Wu, Wenyang Hui, Yezeng Chen, Weiqi Wu, Kewei Tu, Yi Zhou