Papers by Yue Shen

Red-Teaming LLM Multi-Agent Systems via Communication Attacks (2025.findings-acl)

Challenge:	Existing supervised defense methods rely on labeled malicious agents to train a supervised model of malicious behavior.
Approach:	They propose an unsupervised defense method that learns without requiring any attack-specific labels or prior knowledge of malicious behaviors.
Outcome:	The proposed method detects diverse attack types across MAS with various communication patterns while maintaining superior generalizability compared to baselines.

Copied to clipboard

Pengfei He, Yuping Lin, Shen Dong, Han Xu, Yue Xing, Hui Liu

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

Challenge:	Large Language Model-based Multi-Agent Systems (LLM-MAS) have revolutionized complex problem-solving capability by enabling agent collaboration through message-based communications.
Approach:	They propose an attack that exploits communication mechanisms in Large Language Model-based Multi-Agent Systems (LLM-MAS) by intercepting and manipulating inter-agent messages.
Outcome:	The proposed attack exploits communication mechanisms in large language model-based multi-agent systems by intercepting and manipulating inter-agencies.

Copied to clipboard

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

Dialogue Systems & Conversational Agents

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

Gentopia.AI: A Collaborative Platform for Tool-Augmented LLMs (2023.emnlp-demo)

Copied to clipboard

Binfeng Xu, Xukun Liu, Hua Shen, Zeyu Han, Yuhan Li, Murong Yue, Zhiyuan Peng, Yuchen Liu, Ziyu Yao, Dongkuan Xu

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

Challenge:	Existing frameworks for Augmented Language Models lack flexibility, democratization, and holistic evaluation.
Approach:	They propose a lightweight and extensible framework for Augmented Language Models called Gentopia.
Outcome:	The proposed framework integrates language models, task formats, prompting modules, and plugins into a unified paradigm.

Copied to clipboard

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

Structured Data in NLP

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

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

Copied to clipboard

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

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

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

Copied to clipboard

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

Learning to Use Tools via Cooperative and Interactive Agents (2024.findings-emnlp)

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

Copied to clipboard

Zhengliang Shi, Shen Gao, Xiuyi Chen, Yue Feng, Lingyong Yan, Haibo Shi, Dawei Yin, Pengjie Ren, Suzan Verberne, Zhaochun Ren

Green & Sustainable NLP

Challenge:	Existing methods for large language models (LLMs) use one agent to iterate and execute tools, but they suffer from performance degradation when addressing practical tasks.
Approach:	They propose a tool learning framework that coordinates three specialized agents for tool selection, tool execution, and action calibration separately.
Outcome:	The proposed framework outperforms baseline models on three datasets with 14% higher success rate.

HIRAG: Hierarchical-Thought Instruction-Tuning Retrieval-Augmented Generation (2025.findings-emnlp)

Copied to clipboard

Yihan Jiao, Zhehao Tan, Dan Yang, Duolin Sun, Jie Feng, Yue Shen, Jian Wang, Peng Wei

Cold-Start Data Selection for Better Few-shot Language Model Fine-tuning: A Prompt-based Uncertainty Propagation Approach (2023.acl-long)

Challenge:	In-depth research on the specific capabilities needed by the RAG generation model is lacking, leading to inconsistent document quality and retrieval system imperfections.
Approach:	They propose that RAG models should possess three progressively hierarchical abilities: (1) Filtering: the ability to select relevant information; (2) Combination: the capability to combine semantic information across paragraphs; (3) RAG-specific reasoning: the capacity to further process external knowledge using internal knowledge.
Outcome:	Experiments show that the proposed method significantly improves the model’s open-book examination capability on datasets such as RGB, PopQA, MuSiQue, HotpotQA, and PubmedQA.

Copied to clipboard

Yue Yu, Rongzhi Zhang, Ran Xu, Jieyu Zhang, Jiaming Shen, Chao Zhang

Predicting Text Preference Via Structured Comparative Reasoning (2024.acl-long)

Challenge:	Pre-trained language models (PLMs) have achieved competitive performance with limited labeled data for many NLP tasks.
Approach:	They propose a prompt-based data selection method for pre-trained language models fine-tuning under cold-start scenarios.
Outcome:	The proposed method outperforms the strongest cold-start data selection baselines on six text classification datasets with 128 labels.

Copied to clipboard

Jing Nathan Yan, Tianqi Liu, Justin Chiu, Jiaming Shen, Zhen Qin, Yue Yu, Charumathi Lakshmanan, Yair Kurzion, Alexander Rush, Jialu Liu, Michael Bendersky

Reasoning

Challenge:	Existing approaches to comparative reasoning rely on pretraining or fine-tuning models at the cost of massive human annotation and computation.
Approach:	They propose a model that prompts LLMs to generate structured intermediate comparisons by proposing aspects for comparison, followed by generating textual comparisons under each aspect.
Outcome:	The proposed model significantly reduces hallucination and improves consistency across various NLP tasks.

SalaMAnder: Shapley-based Mathematical Expression Attribution and Metric for Chain-of-Thought Reasoning (2025.findings-emnlp)

Copied to clipboard

Yue Xin, Chen Shen, Shaotian Yan, Xiaosong Yuan, Yaoming Wang, Xiaofeng Zhang, Chenxi Huang, Jieping Ye

LLMEval-Fair: A Large-Scale Longitudinal Study on Robust and Fair Evaluation of Large Language Models (2026.acl-long)

Challenge:	Chain-of-Thought prompting improves the math reasoning capability of large language models.
Approach:	They propose a method for attribution of component-level contributions in CoT reasoning using Shapley value and a stratified sampling algorithm that significantly reduces computational complexity.
Outcome:	The proposed method reduces computational complexity and provides robust correlations with model performance.

Copied to clipboard

Ming Zhang, Yujiong Shen, Jingyi Deng, Yuhui Wang, Huayu Sha, Kexin Tan, Qiyuan Peng, Yue Zhang, Junzhe Wang, Shichun Liu, Yueyuan Huang, Jingqi Tong, Changhao Jiang, Yilong Wu, Zhihao Zhang, Mingqi Wu, Mingxu Chai, Zhiheng Xi, Shihan Dou, Tao Gui, Qi Zhang, Xuanjing Huang

Editing Conceptual Knowledge for Large Language Models (2024.findings-emnlp)

Challenge:	Existing evaluation of Large Language Models on static benchmarks is vulnerable to data contamination and leaderboard overfitting.
Approach:	LLMEval-Fair framework provides a framework for dynamic evaluation of Large Language Models . evaluators use a proprietary bank of 220k graduate-level questions to analyze model data .
Outcome:	LLMEval-Fair provides robust and credible evaluation framework for Large Language Models . it provides a strong empirical validation for the dynamic evaluation paradigm .

Copied to clipboard

Xiaohan Wang, Shengyu Mao, Shumin Deng, Yunzhi Yao, Yue Shen, Lei Liang, Jinjie Gu, Huajun Chen, Ningyu Zhang

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

Challenge:	Existing knowledge editing methods can modify concept-level definitions, but they can distort instantial knowledge in LLMs, leading to poor performance.
Approach:	They construct a benchmark dataset ConceptEdit and establish new metrics for evaluation to investigate the editing capability of LLMs.
Outcome:	The proposed methods can modify concept definitions but can distort instantial knowledge in LLMs, leading to poor performance.

Copied to clipboard

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

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

DRAGON: Domain-specific Robust Automatic Data Generation for RAG Optimization (2026.findings-eacl)

Copied to clipboard

Haiyang Shen, Hang Yan, Zhongshi Xing, Mugeng Liu, Yue Li, Zhiyang Chen, Yuxiang Wang, Jiuzheng Wang, Yun Ma

Multimodal Language Models See Better When They Look Shallower (2025.emnlp-main)

Challenge:	Existing retrieval-augmented generation paradigms rely heavily on public knowledge . Existing RAGs reliant on public information and often falter when faced with domain-specific queries.
Approach:	They propose a framework that combines a data-construction modeling approach with a scalable synthetic data-generation pipeline to optimize domain-specific retrieval performance.
Outcome:	The proposed framework optimizes domain-specific retrieval performance and bolsters retriever robustness.

Copied to clipboard

Haoran Chen, Junyan Lin, Xinghao Chen, Yue Fan, Jianfeng Dong, Xin Jin, Hui Su, Jinlan Fu, Xiaoyu Shen

Multimodality

Challenge:	Existing studies show that multimodal large language models extract visual features from the final layers of a pretrained Vision Transformer.
Approach:	They propose a feature fusion method that strategically incorporates shallower layers . they propose MLLMs that extract visual features from the final layers of a pretrained Vision Transformer .
Outcome:	The proposed method outperforms deep layers on fine-grained visual tasks . it is the first comprehensive study of visual layer selection for MLLMs .

GUI-Bee: Align GUI Action Grounding to Novel Environments via Autonomous Exploration (2025.emnlp-main)

Copied to clipboard

Yue Fan, Handong Zhao, Ruiyi Zhang, Yu Shen, Xin Eric Wang, Gang Wu

Green & Sustainable NLP

Challenge:	Recent work of GUI action grounding fine-tunes data from pre-trained MLLMs, but data is limited to specific GUI environments.
Approach:	They propose to use a GUI-based agent to collect environment-specific data and fine-tune GUI grounding models with the collected data.
Outcome:	The proposed model can be extended to other GUI environments to improve performance.

Unveiling the Deficiencies of Pre-trained Text-and-Layout Models in Real-world Visually-rich Document Information Extraction (2026.findings-eacl)

Copied to clipboard

Chong Zhang, Yixi Zhao, Yulu Xie, Chenshu Yuan, Yi Tu, Ya Guo, Mingxu Chai, Ziyu Shen, Yue Zhang, Qi Zhang

Multimodality

Challenge:	PTLMs have shown remarkable success in multiple information extraction tasks . however, their performance in real-world scenarios falls short of expectations .
Approach:	They propose to use an entity-centric dataset to evaluate PTLMs' performance . they find that inadequate annotations in benchmark datasets lead to spurious correlations .
Outcome:	The proposed dataset disentangles the falsely-coupled segment and entity annotations that arises from the block-level annotation of FUNSD.

PEAR: Planner-Executor Agent Robustness Benchmark (2026.findings-eacl)

Copied to clipboard

Shen Dong, Mingxuan Zhang, Pengfei He, Li Ma, Bhavani Thuraisingham, Hui Liu, Yue Xing

GroupRank: A Groupwise Paradigm for Effective and Efficient Passage Reranking with LLMs (2026.findings-acl)

Challenge:	Existing studies examine isolated attack surfaces or specific scenarios, leaving a lack of holistic understanding of MAS vulnerabilities.
Approach:	They propose a benchmark to evaluate the utility and vulnerability of planner–executor MAS.
Outcome:	The proposed benchmark evaluates planner–executor MAS on a widely adopted design.

Copied to clipboard

Meixiu Long, Duolin Sun, Dan Yang, Yihan Jiao, Lei Liu, Jiahai Wang, Binbin Hu, Yue Shen, Jie Feng, Zhehao Tan, Junjie Wang, Lianzhen Zhong, Jian Wang, Peng Wei, Jinjie Gu

RSDA: Restoring Stale Data Affinity via Dynamic Renovation Strategy for Mitigating Data Scarcity (2026.acl-long)

Challenge:	Existing rankers excel in lexical-matching scenarios, while they struggle with complex queries requiring deep reasoning.
Approach:	They propose a new paradigm that balances flexibility and context awareness to unlock the full potential of groupwise reranking.
Outcome:	The proposed approach achieves a state-of-the-art 65.2 NDCG@10 on BRIGHT and surpasses baselines by 2.1 points on R2MED while delivering a 6.4 inference speedup.

Copied to clipboard

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

ReGen: Zero-Shot Text Classification via Training Data Generation with Progressive Dense Retrieval (2023.findings-acl)

Challenge:	High-quality data is the cornerstone of advancing large language models, but the supply of premium data is nearing depletion, while vast stale corpora remain underutilized.
Approach:	They propose a framework to restore stale data affinity by quantifying the latent value of samples and employing a dynamic renovation strategy selection mechanism to determine the optimal component-level strategy.
Outcome:	The proposed framework achieves performance improvements using less than 10% of the data volume, underscoring that the latent potential of stale corpora remains largely untapped.

Copied to clipboard

Yue Yu, Yuchen Zhuang, Rongzhi Zhang, Yu Meng, Jiaming Shen, Chao Zhang

Exploiting Syntactic Structure for Better Language Modeling: A Syntactic Distance Approach (2020.acl-main)

Challenge:	Recent studies show that large pretrained language models can generate training data with no task-specific or cross-task data.
Approach:	They propose a retrieval-enhanced framework to create training data from a general-domain unlabeled corpus.
Outcome:	The proposed framework achieves 4.3% gain over baselines and saves 70% of time compared with baselines using large language models.

Copied to clipboard

Wenyu Du, Zhouhan Lin, Yikang Shen, Timothy J. O’Donnell, Yoshua Bengio, Yue Zhang

Syntactic Text Processing

Challenge:	incorporating syntactic structure into language models has been a challenge since the 1990s.
Approach:	They propose to use syntactic information to integrate syntastic structure into neural language models by providing ground truth parse trees as additional training signals.
Outcome:	The proposed model achieves lower perplexity and better quality when ground truth parse trees are provided as training signals.

KCVR: Knowledge-Centric Video Reconstruction for Structured Pedagogical Summarization via Dynamic Graph Planning (2026.acl-long)

Copied to clipboard

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

Multimodality

Challenge:	Existing summarization methods compress content for gist browsing, but they break prerequisite logic in instructional videos.
Approach:	They propose a framework that decouples epistemic planning from content generation.
Outcome:	The proposed framework outperforms strong end-to-end baselines on Knowledge Progression Consistency and Learning Objective Coverage.

Enhancing Chain-of-Thought Reasoning with Critical Representation Fine-tuning (2025.acl-long)

Copied to clipboard

Chenxi Huang, Shaotian Yan, Liang Xie, Binbin Lin, Sinan Fan, Yue Xin, Deng Cai, Chen Shen, Jieping Ye

SeaLLMs - Large Language Models for Southeast Asia (2024.acl-demos)

Challenge:	Representation Fine-tuning (ReFT) is a proposed method for improving parameter efficiency . however, it yields suboptimal performance, as fixed-position representations have uncertain impact on outputs .
Approach:	They propose a method that fine-tunes critical representations in a low-rank linear subspace while freezing the base model.
Outcome:	The proposed method improves accuracy of LLaMA-2-7B and ReFT by 18.2 and 3.8 on GSM8K.

Copied to clipboard

Xuan-Phi Nguyen, Wenxuan Zhang, Xin Li, Mahani Aljunied, Zhiqiang Hu, Chenhui Shen, Yew Ken Chia, Xingxuan Li, Jianyu Wang, Qingyu Tan, Liying Cheng, Guanzheng Chen, Yue Deng, Sen Yang, Chaoqun Liu, Hang Zhang, Lidong Bing

ConU: Conformal Uncertainty in Large Language Models with Correctness Coverage Guarantees (2024.findings-emnlp)

Challenge:	Existing large language models favor high-resource languages, such as English, at the expense of low-resourced and regional languages.
Approach:	They propose a series of language models that specifically focuses on Southeast Asian languages.
Outcome:	SeaLLM models outperform ChatGPT-3.5 in non-Latin languages by large margins . linguistic disparity impedes access to state-of-the-art AI technologies for non-English-speaking populations .

Copied to clipboard

Zhiyuan Wang, Jinhao Duan, Lu Cheng, Yue Zhang, Qingni Wang, Xiaoshuang Shi, Kaidi Xu, Heng Tao Shen, Xiaofeng Zhu

Phun-Bench: Evaluating LLMs on Phonological Understanding in Chinese (2026.acl-long)

Challenge:	Uncertainty quantification (UQ) in natural language generation tasks remains an open challenge . however, black-box uncertainty measures require investigating with the proliferation of LLMs served via APIs.
Approach:	They propose a conformal uncertainty measure and a method to transform heuristic uncertainty notions into rigorous prediction sets.
Outcome:	Empirical results show that the proposed method outperforms state-of-the-art methods and can provide reliable guarantees for open-ended NLG tasks.

Copied to clipboard

Xing Yue, Yongliang Shen, Weiming Lu

Syntactic Text Processing

Challenge:	Existing benchmarks on LLMs’ phonological abilities are either solvable through rote memorization or intertwined with other abilities, making them inadequate to measure LLM’s genuine ability in phonological understanding.
Approach:	They propose to use a Chinese benchmark to evaluate LLMs' phonological understanding to test their ability to recall correct pronunciations.
Outcome:	The proposed benchmarks show that LLMs excel at recalling correct pronunciations, but struggle to leverage phonological knowledge in the flexible and intuitive way that human speakers do.

A Survey on Natural Language Counterfactual Generation (2024.findings-emnlp)

Copied to clipboard

Yongjie Wang, Xiaoqi Qiu, Yu Yue, Xu Guo, Zhiwei Zeng, Yuhong Feng, Zhiqi Shen

Challenge:	Recent advances in NLP are driven by a variety of Large Language Models (LLMs), such as GPT-3 (175B) and PaLM (540B).
Approach:	They propose a taxonomy that categorizes the methods into four groups and summarizes the metrics for evaluating the generation quality.
Outcome:	The proposed taxonomy categorizes the generation methods into four groups and summarizes the metrics for evaluating the quality.

DocFusion: A Unified Framework for Document Parsing Tasks (2025.findings-acl)

Copied to clipboard

Mingxu Chai, Ziyu Shen, Chong Zhang, Yue Zhang, Xiao Wang, Shihan Dou, Jihua Kang, Jiazheng Zhang, Qi Zhang

Challenge:	Existing methods for document parsing often employ multiple models, limiting performance . Existing models often employ discrete tokens, whereas recognition relies on continuous coordinates .
Approach:	They propose a Gaussian-Kernel Cross-Entropy Loss (GK-CEL) that unifies detection and recognition by enabling generative frameworks to handle both tasks simultaneously.
Outcome:	The proposed model performs competitively across four core document parsing tasks.

Explanation-aware Soft Ensemble Empowers Large Language Model In-context Learning (2024.acl-long)

Copied to clipboard

Yue Yu, Jiaming Shen, Tianqi Liu, Zhen Qin, Jing Nathan Yan, Jialu Liu, Chao Zhang, Michael Bendersky

Seq2Path: Generating Sentiment Tuples as Paths of a Tree (2022.findings-acl)

Challenge:	Recent advances in natural language processing (NLP) have witnessed the remarkable capabilities of Large Language Models (LLMs).
Approach:	They propose an Explanation-Aware Soft Ensemble framework to empower in-context learning with Large language models.
Outcome:	The proposed framework can be used to enhance in-context learning on seven natural language understanding tasks and four varying-size LLMs.

Copied to clipboard

Yue Mao, Yi Shen, Jingchao Yang, Xiaoying Zhu, Longjun Cai

Sentiment Analysis

Challenge:	Existing generative methods for extracting sentiment tuples do not have orders between the t-uples . a novel parallel generative framework for ABSA is proposed .
Approach:	They propose a parallel generative framework to generate sentiment tuples as paths of a tree . they train the model with an independent target and introduce a discriminative token .
Outcome:	The proposed method achieves state-of-the-art on AOPE, ASTE, TASD, UABSA, ACOS . it trains with the loss of ordinary Seq2Seq averaged over paths, and inferences automatically select valid paths.

Whether LLMs Know If They Know: Identifying Knowledge Boundaries via Debiased Historical In-Context Learning (2025.findings-acl)

Copied to clipboard

Bo Lv, Nayu Liu, Yang Shen, Xin Liu, Ping Luo, Yue Yu