Papers by Chen Lyu

Collaborative Performance Prediction for Large Language Models (2024.emnlp-main)

Challenge:	a comprehensive and fine-grained measurement of the hallucination is crucial for LLMs' wide applications.
Approach:	They propose a dataset that offers ANalytical Annotation of Hallucinations in Large Language Models.
Outcome:	The proposed dataset can be used to train and evaluate hallucination annotators.

Copied to clipboard

Qiyuan Zhang, Fuyuan Lyu, Xue Liu, Chen Ma

LLM-Rec: Personalized Recommendation via Prompting Large Language Models (2024.findings-naacl)

Challenge:	Large language models (LLMs) are one of the most important AI research powered by largescale parameters, high computational resources, and massive training data.
Approach:	They propose a framework that leverages historical performance of large language models and other design factors to improve prediction accuracy.
Outcome:	The proposed framework surpasses scaling laws in predicting performance of large language models . it also facilitates a detailed analysis of factor importance, an area previously overlooked .

Copied to clipboard

Hanjia Lyu, Song Jiang, Hanqing Zeng, Yinglong Xia, Qifan Wang, Si Zhang, Ren Chen, Chris Leung, Jiajie Tang, Jiebo Luo

Generation-Augmented and Embedding Fusion in Document-Level Event Argument Extraction (2025.coling-main)

Challenge:	Recent advances in large language models (LLMs) have showcased their remarkable ability to harness commonsense knowledge and reasoning.
Approach:	They propose a novel approach which incorporates four distinct prompting strategies of text enrichment for improving personalized text-based recommendations.
Outcome:	The proposed approach improves recommendation quality and even basic MLP models achieve comparable or even better results than complex content-based methods.

Copied to clipboard

Xingjian Lin, Shengfei Lyu, Xin Wang, Qiuju Chen, Huanhuan Chen

PDTrim: Targeted Pruning for Prefill-Decode Disaggregation in Inference (2026.acl-long)

Challenge:	Document-level event argument extraction is a crucial task that aims to extract arguments from the entire document, beyond sentence-level analysis.
Approach:	They propose a novel approach to document-level event argument extraction that integrates predefined templates and generative language models into a foundational embedding derived from a classification model.
Outcome:	The proposed approach is more effective than baseline models and data-efficient in low-resource scenarios.

Copied to clipboard

Hao Zhang, Lyu Mengsi, Zhuo Chen, Yulong Ao, Yonghua Lin

Green & Sustainable NLP

Challenge:	Existing pruning methods ignore prefill-decode (PD) disaggregation in practice.
Approach:	They propose a pruning method that is highly integrated with prefill-decode (PD) disaggregation, enabling more precise pruning of blocks.
Outcome:	The proposed method achieves strong performance in both PD disaggregation and PD unified settings, and can be extended to other non-block pruning methods.

Think Wider, Detect Sharper: Reinforced Reference Coverage for Document-Level Self-Contradiction Detection (2025.emnlp-main)

Copied to clipboard

Yuhao Chen, Yuanjie Lyu, Shuochen Liu, Chao Zhang, Junhui Lv, Tong Xu

RubricBench: Aligning Model-Generated Rubrics with Human Standards (2026.acl-long)

Challenge:	Recent approaches to document-level contradiction detection (DSCD) only gain marginal improvement and often introduce inconsistencies across repeated responses.
Approach:	They propose a method that combines supervised fine-tuning and reinforcement learning to enhance document-level contradiction detection (DSCD) they propose to use a task-specific reward function to expand the model’s reasoning scope, boosting both accuracy and consistency.
Outcome:	The proposed method significantly boosts Llama 3.1-8B-Instruct’s accuracy from 38.5% to 51.1%, and consistency from 59.6% to76.2%.

Copied to clipboard

Junyi Zhou, Qiyuan Zhang, Yufei Wang, Fuyuan Lyu, Yidong Ming, Can Xu, Qingfeng Sun, Kai Zheng, Peng Kang, Xue Liu, Chen Ma

Challenge:	Existing benchmarks lack discriminative complexity and ground-truth rubric annotations required for rigorous evaluation.
Approach:	They propose a curated benchmark with 1,147 pairwise comparisons to assess the reliability of rubric-based evaluation.
Outcome:	The proposed benchmarks show that they support diverse domains, exhibit discriminative ability, provide high-quality annotations, and include human-authored rubrics.

CoQuIR: A Comprehensive Benchmark for Code Quality-Aware Information Retrieval (2026.acl-long)

Copied to clipboard

Jiahui Geng, Fengyu Cai, Shaobo Cui, Qing Li, Liangwei Chen, Chenyang Lyu, Haonan Li, Derui Zhu, Alexander Pretschner, Heinz Koeppl, Fakhri Karray

Optimizing User Profiles via Contextual Bandits for Retrieval-Augmented LLM Personalization (2026.acl-long)

Challenge:	Existing benchmarks focus on functional relevance while neglecting code quality.
Approach:	They propose a multilingual benchmark to evaluate quality-aware code retrieval . they include fine-grained quality annotations over 42,725 queries and 134,907 code snippets .
Outcome:	The proposed benchmarks show that state-of-the-art models fail to separate buggy or insecure code from robust counterparts.

Copied to clipboard

Linfeng Du, Ye Yuan, Zichen Zhao, Fuyuan Lyu, Emiliano Penaloza, Xiuying Chen, Zipeng Sun, Jikun Kang, Laurent Charlin, Xue Liu, Haolun Wu

Understanding Secret Leakage Risks in Code LLMs: A Tokenization Perspective (2026.findings-acl)

Challenge:	Existing approaches for personalizing large language models require modifying parameters.
Approach:	They propose a lightweight approach to personalizing large language models via retrieval augmentation . relevance serves as an unreliable proxy for utility, they argue .
Outcome:	The proposed framework outperforms strong heuristic and retrieval-augmented baselines on nine personalization tasks.

Copied to clipboard

Meifang Chen, Zhe Yang, Huang Nianchen, Yizhan Huang, Yichen LI, Zihan Li, Michael R. Lyu

Syntactic Text Processing

Challenge:	Code Large Language Models (CLLMs) are reshaping how software is built, maintained, and evolved.
Approach:	They propose to use BPE tokenization to inadvertently leak code secrets . they propose to mitigate the gibberish bias by using a newer tokenizer .
Outcome:	The proposed model is based on a novel method that can be used to detect and mitigate gibberish bias in CLLMs.

Attention-Enhancing Backdoor Attacks Against BERT-based Models (2023.findings-emnlp)

Copied to clipboard

Weimin Lyu, Songzhu Zheng, Lu Pang, Haibin Ling, Chao Chen

Robustness in NLP

Challenge:	Existing textual backdoor attacks focus on generating stealthy triggers or modifying model weights.
Approach:	They propose a Trojan Attention Loss (TAL) which enhances the Trojan behavior by directly manipulating attention patterns.
Outcome:	The proposed method improves the effectiveness of the backdoor attacks on different backbone models and tasks.

PersonalAlign: Hierarchical Implicit Intent Alignment for Personalized GUI Agent with Long-Term User-Centric Records (2026.acl-long)

Copied to clipboard

Yibo Lyu, Gongwei Chen, Rui Shao, Weili Guan, Liqiang Nie

Challenge:	GUI agents have shown strong performance under explicit and completion instructions, but real-world deployment requires aligning with users’ more complex implicit intents.
Approach:	They propose a task that requires agents to leverage long-term user records as persistent context to resolve omitted preferences in vague instructions and anticipate latent routines by user state for proactive assistance.
Outcome:	The proposed task improves execution and proactive performance by 15.7% and 7.3% under explicit and completion instructions.

Extracted BERT Model Leaks More Information than You Think! (2022.emnlp-main)

Copied to clipboard

Xuanli He, Lingjuan Lyu, Chen Chen, Qiongkai Xu

Responsible & Trustworthy NLP

Challenge:	Existing pre-trained language models are vulnerable to model extraction attacks . model extraction can cause severe privacy leakage even when victim models are facilitated with state-of-the-art defensive strategies.
Approach:	They propose to launch an attribute-inference attack against an extracted BERT model to prevent privacy leakage.
Outcome:	The proposed attack can cause severe privacy leakage even when victim models are facilitated with state-of-the-art defensive strategies.

From Selection to Generation: A Survey of LLM-based Active Learning (2025.acl-long)

Copied to clipboard

Yu Xia, Subhojyoti Mukherjee, Zhouhang Xie, Junda Wu, Xintong Li, Ryan Aponte, Hanjia Lyu, Joe Barrow, Hongjie Chen, Franck Dernoncourt, Branislav Kveton, Tong Yu, Ruiyi Zhang, Jiuxiang Gu, Nesreen K. Ahmed, Yu Wang, Xiang Chen, Hanieh Deilamsalehy, Sungchul Kim, Zhengmian Hu, Yue Zhao, Nedim Lipka, Seunghyun Yoon, Ting-Hao Kenneth Huang, Zichao Wang, Puneet Mathur, Soumyabrata Pal, Koyel Mukherjee, Zhehao Zhang, Namyong Park, Thien Huu Nguyen, Jiebo Luo, Ryan A. Rossi, Julian McAuley

Responsible & Trustworthy NLP

Challenge:	Large Language Models (LLMs) have been used for selection and training of data for active learning.
Approach:	They propose an intuitive taxonomy that categorizes LLM-based active learning techniques and discuss the transformative roles they can play in the active learning loop.
Outcome:	The proposed model can generate entirely new data instances and provide more cost-effective annotations with fewer labeled data instances.

Streamlining the Collaborative Chain of Models into A Single Forward Pass in Generation-Based Tasks (2025.findings-acl)

Copied to clipboard

Yuanjie Lyu, Chao Zhang, Yuhao Chen, Yong Chen, Tong Xu

CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward (2025.emnlp-main)

Challenge:	Recent advances in "Chain of Models" approach increase resource demands as each model must be deployed separately.
Approach:	They propose a prompt-tuning method that enables models to share hidden states . they modify input and attention masks during training to eliminate redundant forward passes .
Outcome:	Empirical results show that FTHSS matches the performance of traditional model chains while improving inference efficiency.

Copied to clipboard

Shudong Liu, Hongwei Liu, Junnan Liu, Linchen Xiao, Songyang Gao, Chengqi Lyu, Yuzhe Gu, Wenwei Zhang, Derek F. Wong, Songyang Zhang, Kai Chen

Robustness in NLP

Challenge:	Existing approaches lack robustness to handle complex edge cases and generalizability across different domains.
Approach:	They develop an accurate and lightweight verifier model for evaluation and outcome reward that matches unstructured outputs against standard answers.
Outcome:	The proposed model can process multiple answer types including multi-subproblems, formulas, and sequence answers while identifying abnormal/invalid responses.

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

Copied to clipboard

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

Repulsive Attention: Rethinking Multi-head Attention as Bayesian Inference (2020.emnlp-main)

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

Copied to clipboard

Bang An, Jie Lyu, Zhenyi Wang, Chunyuan Li, Changwei Hu, Fei Tan, Ruiyi Zhang, Yifan Hu, Changyou Chen

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

Challenge:	Existing studies show that multi-head attention is an effective module in deep neural networks, but there are no explicit mechanisms guaranteeing this property.
Approach:	They propose a non-parametric approach that explicitly improves the repulsiveness in multi-head attention and consequently strengthens model’s expressiveness.
Outcome:	The proposed approach improves the repulsiveness in multi-head attention and strengthens model’s expressiveness.

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

Mitigating Hallucinations in Multi-modal Large Language Models via Image Token Attention-Guided Decoding (2025.naacl-long)

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.

Copied to clipboard

Xinhao Xu, Hui Chen, Mengyao Lyu, Sicheng Zhao, Yizhe Xiong, Zijia Lin, Jungong Han, Guiguang Ding

Relation Classification with Entity Type Restriction (2021.findings-acl)

Challenge:	Multi-modal large language models (MLLMs) generate plausible but incorrect content, resulting in hallucinations . recent advances in MLLM technology have demonstrated their outstanding performance in a variety of visual tasks, such as object detection.
Approach:	They propose a plug-and-play method which leverages MLLMs’ internal representations to mitigate hallucinations by analyzing input and output tokens.
Outcome:	The proposed method exploits MLLMs’ internal representations to mitigate hallucinations.

Copied to clipboard

Shengfei Lyu, Huanhuan Chen

VideoScore: Building Automatic Metrics to Simulate Fine-grained Human Feedback for Video Generation (2024.emnlp-main)

Challenge:	Existing methods regard all relations as candidate relations for the two entities, which leads to inappropriate relations being candidate relations.
Approach:	They propose a paradigm which exploits entity types to restrict candidate relations by mutual restrictions.
Outcome:	The proposed paradigm improves GCN and SpanBERT on a standard dataset by 6.9 and 4.4 F1 points.

Copied to clipboard

Xuan He, Dongfu Jiang, Ge Zhang, Max Ku, Achint Soni, Sherman Siu, Haonan Chen, Abhranil Chandra, Ziyan Jiang, Aaran Arulraj, Kai Wang, Quy Do, Yuansheng Ni, Bohan Lyu, Yaswanth Narsupalli, Rongqi Fan, Zhiheng Lyu, Bill Yuchen Lin, Wenhu Chen

Explanation in the Era of Large Language Models (2024.naacl-tutorials)

Challenge:	Existing video metrics are lagging behind in providing reliable scores over generated videos due to lack of large-scale human-annotated dataset.
Approach:	They propose to use VideoFeedback to train a human-annotated multi-aspect score over 37.6K synthesized videos from 11 existing video generative models.
Outcome:	The proposed model outperforms the prior best metrics by 50 points in the test.

Copied to clipboard

Zining Zhu, Hanjie Chen, Xi Ye, Qing Lyu, Chenhao Tan, Ana Marasovic, Sarah Wiegreffe

Explainability & Interpretability in NLP

Challenge:	Explanation has long been a part of communication, where humans use language to elucidate each other and transmit information about mechanisms of events.
Approach:	They review the opportunities and challenges of explanations in the era of large language models and examine how they can be used to generate explanations.
Outcome:	The proposed methods are based on the models of large language models (LLMs) and their opaque nature.

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

Copied to clipboard

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

Capturing Argument Interaction in Semantic Role Labeling with Capsule Networks (D19-1)

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

Copied to clipboard

Xinchi Chen, Chunchuan Lyu, Ivan Titov

Neural Graph Matching Networks for Chinese Short Text Matching (2020.acl-main)

Challenge:	State-of-the-art SRL models do not model non-local interaction between arguments . e.g., LSTMs do not allow for efficient inference .
Approach:	They propose a new approach to model interactions between arguments using capsule networks . they analyze errors in the refinement procedure by capturing intuition in a flexible way .
Outcome:	The proposed model outperforms the baseline model on all 7 languages and achieves state-of-the-art results on 5 languages including English.

Copied to clipboard

Lu Chen, Yanbin Zhao, Boer Lyu, Lesheng Jin, Zhi Chen, Su Zhu, Kai Yu

Crowd Comparative Reasoning: Unlocking Comprehensive Evaluations for LLM-as-a-Judge (2025.acl-long)

Challenge:	Chinese word segmentation can be erroneous, ambiguous or inconsistent, causing performance problems.
Approach:	They propose a sentence matching framework that uses paired word lattices as input instead of a character sequence.
Outcome:	The proposed framework outperforms the state-of-the-art short text matching models on two Chinese datasets.

Copied to clipboard

Qiyuan Zhang, Yufei Wang, Yuxin Jiang, Liangyou Li, Chuhan Wu, Yasheng Wang, Xin Jiang, Lifeng Shang, Ruiming Tang, Fuyuan Lyu, Chen Ma

Training Language Models to Critique With Multi-agent Feedback (2025.findings-emnlp)

Challenge:	Existing methods rely on majority voting or criteria expansion to capture detailed and detailed details, often leading to incomplete outcomes.
Approach:	They propose a method which introduces additional crowd responses to compare with the candidate responses, thereby exposing deeper and more comprehensive details within the candidate answers.
Outcome:	Experiments show that the proposed method improves evaluation reliability and achieves an average gain of 6.7% across five benchmarks.

Copied to clipboard

Tian Lan, Wenwei Zhang, Chengqi Lyu, Shuaibin Li, Chen Xu, Heyan Huang, Dahua Lin, Xian-Ling Mao, Kai Chen

Stable Language Guidance for Vision–Language–Action Models (2026.acl-long)

Challenge:	utilizing human annotations can enhance critique ability, but model-generated critiques suffer from inherent flaws due to complexity of critique . a new framework that leverages multi-agent feedback improves critique ability .
Approach:	They propose a framework that leverages multi-agent feedback to improve critique ability . they propose to use supervised fine-tuning and reinforcement learning to improve this capability .
Outcome:	The proposed framework improves critique ability in both supervised fine-tuning and reinforcement learning stages.

Copied to clipboard

Zhihao Zhan, Yuhao Chen, Jiaying Zhou, Qinhan Lyu, Hao Liu, Keze Wang, Liang Lin, Guangrun Wang

SoMeLVLM: A Large Vision Language Model for Social Media Processing (2024.findings-acl)

Challenge:	Existing vision-Language-Action models are notoriously brittle to linguistic perturbations.
Approach:	They propose a probabilistic framework that disentangles physical affordance from semantic execution.
Outcome:	The proposed framework disentangles physical affordance from semantic execution.

Copied to clipboard

Xinnong Zhang, Haoyu Kuang, Xinyi Mou, Hanjia Lyu, Kun Wu, Siming Chen, Jiebo Luo, Xuanjing Huang, Zhongyu Wei

Task-Agnostic Detector for Insertion-Based Backdoor Attacks (2024.findings-naacl)

Challenge:	Genereal domain large models lack nuanced multimodal understanding of social media . general domain models focus more on text than other modalities, which is not consistent with real-world user habits.
Approach:	They propose a Large Vision Language Model for Social Media Processing that combines five key capabilities to understand and generate real social media behavior.
Outcome:	The proposed model achieves state-of-the-art performance in multiple social media tasks.

Copied to clipboard

Weimin Lyu, Xiao Lin, Songzhu Zheng, Lu Pang, Haibin Ling, Susmit Jha, Chao Chen

Robustness in NLP

Challenge:	Existing methods for textual backdoor detection are task-specific and less effective beyond sentence classification.
Approach:	They propose a task-agnostic method for backdoor detection that leverages final layer logits and an efficient pooling technique.
Outcome:	TABDet can jointly learn from diverse task-specific models, demonstrating superior detection efficacy over traditional methods.

Retrieve-Plan-Generation: An Iterative Planning and Answering Framework for Knowledge-Intensive LLM Generation (2024.emnlp-main)

Copied to clipboard

Yuanjie Lyu, Zihan Niu, Zheyong Xie, Chao Zhang, Tong Xu, Yang Wang, Enhong Chen

AwarenessBench: Assessing Cognitive Capabilities of Language Models (2026.acl-long)

Challenge:	Large language models (LLMs) often produce factual errors due to limited internal knowledge.
Approach:	They propose a retrieval-augmented generation framework that generates plan tokens to guide subsequent generation.
Outcome:	The proposed framework improves the accuracy of large language models with external knowledge sources.

Copied to clipboard

Xiaojian Li, Rongwu Xu, Tianyun Zhang, Yue Wang, Shuo Chen, Qiner Lyu, Briana Zhang, Peiran Yang, Kyle Xue Chen, Haoyuan Shi, Yu Wang, Wei Xu

Multi-Defendant Legal Judgment Prediction via Hierarchical Reasoning (2023.findings-emnlp)

Challenge:	Language models exhibit increasingly consciousness-like behaviors, requiring a baseline to evaluate their cognitive abilities.
Approach:	They propose a benchmark to assess the cognitive abilities of language models (LMs) they compare 18 state-of-the-art LMs to human models in metacognition, self-awareness, social awareness and situational awareness .
Outcome:	Evaluating 18 state-of-the-art LMs, they find they consistently surpass baselines . but most models fall short in metacognition and self-awareness, the study finds .

Copied to clipboard

Yougang Lyu, Jitai Hao, Zihan Wang, Kai Zhao, Shen Gao, Pengjie Ren, Zhumin Chen, Fang Wang, Zhaochun Ren

Enhancing Code Generation Performance of Smaller Models by Distilling the Reasoning Ability of LLMs (2024.lrec-main)

Challenge:	Existing methods for predicting judgment results for multiple defendants are ineffective.
Approach:	They propose a method to predict the judgment results for each defendant in multi-defendant cases . they formalize the multi-diffendant judgment process as hierarchical reasoning chains .
Outcome:	The proposed method can predict the judgment results for multiple defendants in multi-defendant cases.

Copied to clipboard

Zhihong Sun, Chen Lyu, Bolun Li, Yao Wan, Hongyu Zhang, Ge Li, Zhi Jin

Text Generation

Challenge:	Large Language Models (LLMs) have made significant advances in code generation through the ‘Chain-of-Thought’ prompting technique.
Approach:	They propose a framework which aims to transfer LLMs’ reasoning capabilities to smaller models through distillation.
Outcome:	The proposed framework improves the smaller model's code generation performance by over 130% on the APPS benchmark.

Few-Shot Text Classification with Edge-Labeling Graph Neural Network-Based Prototypical Network (2020.coling-main)

Copied to clipboard

Chen Lyu, Weijie Liu, Ping Wang

VSCBench: Bridging the Gap in Vision-Language Model Safety Calibration (2025.findings-acl)

Challenge:	a few-shot text classification method is proposed to solve the few-sshot text problem . supervised learning methods require large corpus of labeled data, making them hindered in practical application.
Approach:	They propose a few-shot text classification method that takes advantage of advanced pre-trained language models to extract the semantic features of each document.
Outcome:	The proposed method achieves state-of-the-art on sentiment analysis and relation datasets.

Copied to clipboard

Jiahui Geng, Qing Li, Zongxiong Chen, Yuxia Wang, Derui Zhu, Zhuohan Xie, Chenyang Lyu, Xiuying Chen, Preslav Nakov, Fakhri Karray

HD-NDEs: Neural Differential Equations for Hallucination Detection in LLMs (2025.acl-long)

Challenge:	Existing safety calibration methods focus on model undersafety, where the model responds to hazardous queries, while neglecting oversafetiness, where models refuse to answer safe queries.
Approach:	They propose safety calibration which addresses both undersafety and oversafetiness by comparing model responses to a novel dataset of 3,600 image-text pairs.
Outcome:	The proposed methods have been used to evaluate safety calibration across image-centric and text-centric scenarios.

Copied to clipboard

Qing Li, Jiahui Geng, Zongxiong Chen, Derui Zhu, Yuxia Wang, Congbo Ma, Chenyang Lyu, Fakhri Karray

A Study of the Attention Abnormality in Trojaned BERTs (2022.naacl-main)

Challenge:	Hallucination is a significant challenge for large language models, but current methods struggle when non-factual information arises in the early or mid-sequence of outputs, reducing their reliability.
Approach:	They propose a method that captures the full dynamics of large language models by using neural differential equations to assess the truthfulness of statements.
Outcome:	The proposed method achieves 14% improvement in AUC-ROC on the True-False dataset compared to state-of-the-art methods.

Copied to clipboard

Weimin Lyu, Songzhu Zheng, Tengfei Ma, Chao Chen

GUI Agents: A Survey (2025.findings-acl)

Challenge:	In computer vision, the trigger can be a fixed pattern overlaid on the images or videos.
Approach:	They propose an attention-based Trojan detector to distinguish Trojaned models from clean ones by observing the attention focus drifting behavior of Trojanes.
Outcome:	The proposed detector is based on transformer’s attention and can distinguish Trojan models from clean ones.

Copied to clipboard

Dang Nguyen, Jian Chen, Yu Wang, Gang Wu, Namyong Park, Zhengmian Hu, Hanjia Lyu, Junda Wu, Ryan Aponte, Yu Xia, Xintong Li, Jing Shi, Hongjie Chen, Viet Dac Lai, Zhouhang Xie, Sungchul Kim, Ruiyi Zhang, Tong Yu, Mehrab Tanjim, Nesreen K. Ahmed, Puneet Mathur, Seunghyun Yoon, Lina Yao, Branislav Kveton, Jihyung Kil, Thien Huu Nguyen, Trung Bui, Tianyi Zhou, Ryan A. Rossi, Franck Dernoncourt

Challenge:	Large Foundation Models (LFMs) have transformed the landscape of AI research and day-to-day life.
Approach:	They propose a framework that delineates GUI agents' perception, reasoning, planning, and acting capabilities.
Outcome:	The proposed framework delineates their perception, reasoning, planning, and acting capabilities.

Glyph Enhanced Chinese Character Pre-Training for Lexical Sememe Prediction (2021.findings-emnlp)

Copied to clipboard

Boer Lyu, Lu Chen, Kai Yu

Defining and Evaluating Visual Language Models’ Basic Spatial Abilities: A Perspective from Psychometrics (2025.acl-long)

Challenge:	Sememes are defined as the atomic units to describe the semantic meaning of concepts.
Approach:	They propose a method which incorporates internal Chinese character information to help sememe prediction.
Outcome:	The proposed method outperforms existing non-external information models on howNet, a famous sememe knowledge base.

Copied to clipboard

Wenrui Xu, Dalin Lyu, Weihang Wang, Jie Feng, Chen Gao, Yong Li

KnowTuning: Knowledge-aware Fine-tuning for Large Language Models (2024.emnlp-main)

Challenge:	Existing studies assessing the spatial abilities of VLMs lack a solid theoretical foundation and lack measurable data.
Approach:	They propose a psychometric framework defining five basic spatial abilities in Visual Language Models.
Outcome:	The proposed framework defines five basic spatial abilities in Visual Language Models (VLMs) it provides a comprehensive evaluation benchmark and methodological perspective for embodied AI development .

Copied to clipboard

Yougang Lyu, Lingyong Yan, Shuaiqiang Wang, Haibo Shi, Dawei Yin, Pengjie Ren, Zhumin Chen, Maarten Rijke, Zhaochun Ren

Multi-view Classification Model for Knowledge Graph Completion (2020.aacl-main)

Challenge:	Large language models (LLMs) are a default solution for many natural language processing tasks.
Approach:	They propose a knowledge-aware fine-tuning method to improve LLMs' knowledge awareness . they propose augmentation and comparison stages to improve accuracy and reliability .
Outcome:	The proposed method generates more facts with less factual error rate under fine-grained facts evaluation.

Copied to clipboard

Wenbin Jiang, Mengfei Guo, Yufeng Chen, Ying Li, Jinan Xu, Yajuan Lyu, Yong Zhu

Rethinking Expert Trajectory Utilization in LLM Post-training for Mathematical Reasoning (2026.acl-long)

Challenge:	Existing knowledge graph completion models only evaluated candidate triples from content information.
Approach:	They propose a multi-view classification model where multiple views are performed based on both content and context information for candidate triple evaluation.
Outcome:	The proposed model improves on two representative datasets and improves performance.

Copied to clipboard

Bowen Ding, Yuhan Chen, Jiayang Lyu, Jiyao Yuan, Qi Zhu, Shuangshuang Tian, Dantong Zhu, Futing Wang, Heyuan Deng, Fei Mi, Lifeng Shang, Tao Lin

MedCoach: Enhancing Medical Reasoning in LLMs via Knowledge Graph-Augmented Chain-of-Thought Distillation (2026.findings-acl)

Challenge:	evolving generic Large Language Models into specialized Large Reasoning Models requires effective post-training.
Approach:	They propose a plasticity-ceiling framework to harness expert trajectories . they establish the Sequential SFT-then-RL pipeline as the superior standard .
Outcome:	The proposed framework overcomes stability and premature convergence deficits in synchronized approaches.

Copied to clipboard

Chuan Li, Ye Lyu, Chengyu Wang, Mingyuan Fan, Cen Chen

Asclepius: A Spectrum Evaluation Benchmark for Medical Multi-Modal Large Language Models (2025.acl-long)

Challenge:	Existing methods for training specialized reasoning models for the medical domain are limited due to the scarcity of high-quality, large-scale Chain-of-Thought (CoT) data.
Approach:	They propose a framework that introduces a dedicated coach role to guide the student model through question decomposition.
Outcome:	The proposed framework smooths the learning curve in medical reasoning by facilitating domain adaptation before advancing to complex long-chain reasoning.

Copied to clipboard

Jie Liu, Wenxuan Wang, Su Yihang, Jingyuan Huang, Yudi Zhang, Cheng-Yi Li, Wenting Chen, Xiaohan Xing, Kao-Jung Chang, Linlin Shen, Michael R. Lyu

EAGLE: Expert-Guided Self-Enhancement for Preference Alignment in Pathology Large Vision-Language Model (2025.acl-long)

Challenge:	Medical Multi-Modal Large Language Models (Med-MLLMs) are a promising new form of artificial general intelligence due to their ability to tackle complex tasks.
Approach:	They propose a new benchmark that comprehensively assesses medical multi-modal large language models in terms of distinct medical specialties and different diagnostic capacities.
Outcome:	The proposed model covers 15 medical specialties and different diagnostic capacities, and excludes overlap with existing VQA dataset.

Copied to clipboard

Meidan Ding, Jipeng Zhang, Wenxuan Wang, Haiqin Zhong, Xiaoqin Wang, Xinheng Lyu, Wenting Chen, Linlin Shen

All Languages Matter: On the Multilingual Safety of LLMs (2024.findings-acl)

Challenge:	Recent advances in Large Vision Language Models (LVLMs) show promise for pathological diagnosis, yet their application in clinical settings faces critical challenges of multimodal hallucination and biased responses.
Approach:	They propose a framework that integrates medical expertise into preference alignment.
Outcome:	The proposed framework outperforms existing pathological LVLMs while maintaining pathological accuracy.

Copied to clipboard

Wenxuan Wang, Zhaopeng Tu, Chang Chen, Youliang Yuan, Jen-tse Huang, Wenxiang Jiao, Michael Lyu

KnowAgent: Knowledge-Augmented Planning for LLM-Based Agents (2025.findings-naacl)

Challenge:	Existing safety benchmarks only concern the safety in one language, e.g. the majority language in the pretraining data such as English.
Approach:	They propose a prompting method to improve multilingual safety of ChatGPT by enhancing cross-lingual generalization of safety alignment.
Outcome:	The proposed method can significantly reduce the ratio of unsafe responses by 42% for non-English queries.

Copied to clipboard

Yuqi Zhu, Shuofei Qiao, Yixin Ou, Shumin Deng, Shiwei Lyu, Yue Shen, Lei Liang, Jinjie Gu, Huajun Chen, Ningyu Zhang

Towards a Design Guideline for RPA Evaluation: A Survey of Large Language Model-Based Role-Playing Agents (2025.findings-acl)

Challenge:	Large Language Models (LLMs) fail to effectively guide the planning trajectories during task solving and result in planning hallucinations.
Approach:	They propose a novel approach to enhance the planning capabilities of large language models by incorporating explicit action knowledge.
Outcome:	The proposed approach can achieve comparable or superior performance to existing baselines on HotpotQA and ALFWorld.

Copied to clipboard

Chaoran Chen, Bingsheng Yao, Ruishi Zou, Wenyue Hua, Weimin Lyu, Toby Jia-Jun Li, Dakuo Wang

Enhancing Open-Domain Task-Solving Capability of LLMs via Autonomous Tool Integration from GitHub (2025.acl-long)

Challenge:	Role-Playing Agents (RPAs) are increasingly popular due to diverse task requirements and agent designs.
Approach:	They propose an evidence-based evaluation design guideline for LLM-based RPAs based on agent attributes, task attributes, and evaluation metrics.
Outcome:	The proposed evaluation design guideline is based on a systematic review of 1,676 papers published between Jan. 2021 and Dec. 2024.

Copied to clipboard

Bohan Lyu, Xin Cong, Heyang Yu, Pan Yang, Cheng Qian, Zihe Wang, Yujia Qin, Yining Ye, Yaxi Lu, Chen Qian, Zhong Zhang, Yukun Yan, Yankai Lin, Zhiyuan Liu, Maosong Sun

SecureVibeBench: Benchmarking Secure Vibe Coding of AI Agents via Reconstructing Vulnerability-Introducing Scenarios (2026.acl-long)

Challenge:	Existing approaches lack flexibility to address diverse and ever-evolving user queries in open domains.
Approach:	They propose to evaluate LLMs on open-domain knowledge that requires tools to solve diverse and ever-evolving user queries.
Outcome:	The proposed system outperforms baselines in the open domain task-solving benchmark.

Copied to clipboard

Junkai Chen, Huihui Huang, Yunbo Lyu, Junwen An, Jieke Shi, Chengran Yang, Ting Zhang, Haoye Tian, Yikun Li, Zhenhao Li, Xin Zhou, Xing Hu, David Lo

Challenge:	Existing benchmarks fail to capture scenarios in which vulnerabilities are introduced by humans . we evaluate 5 popular code agents supported by 5 LLMs on SecureVibeBench .
Approach:	They propose a benchmarking tool that compares 105 C/C++ secure coding tasks . they use real-world open-source vulnerabilities and a comprehensive evaluation tool .
Outcome:	The proposed benchmarks show that code agents struggle to produce correct and secure code . the best performing agent produces merely 23.8% correct and secured solutions .

CLEVA: Chinese Language Models EVAluation Platform (2023.emnlp-demo)

Copied to clipboard

Yanyang Li, Jianqiao Zhao, Duo Zheng, Zi-Yuan Hu, Zhi Chen, Xiaohui Su, Yongfeng Huang, Shijia Huang, Dahua Lin, Michael Lyu, Liwei Wang