Acquiescence Bias in Large Language Models
机构 * Marburg University（马尔堡大学）
Comments Accepted to EMNLP 2025 Findings
期刊&会议
EMNLP
Conference on Empirical Methods in Natural Language Processing · 会议 · Natural Language Processing
Adversarial Attacks Against Automated Fact-Checking: A Survey
机构 * School of Computing, Macquarie University, Australia（麦考瑞大学计算机学院） ； CSIRO’s Data61, Australia（澳大利亚CSIRO数据61） ； UNSW Sydney, Australia（新南威尔士大学悉尼分校）
Comments Accepted to the Main Conference of EMNLP 2025. Resources are available at https://github.com/FanzhenLiu/Awesome-Automated-Fact-Checking-Attacks
CURE: Controlled Unlearning for Robust Embeddings -- Mitigating Conceptual Shortcuts in Pre-Trained Language Models
机构 * Technical University of Munich（慕尼黑技术大学）
Comments Accepted at the Conference on Empirical Methods in Natural Language Processing (EMNLP 2025)
Measuring Bias or Measuring the Task: Understanding the Brittle Nature of LLM Gender Biases
机构 * The University of Chicago（芝加哥大学） ； University of California, Los Angeles（加州大学洛杉矶分校）
Comments To be published at EMNLP 2025 (main conference)
A Survey on Training-free Alignment of Large Language Models
机构 * School of Computer Science, Wuhan University, Wuhan, China（武汉大学计算机学院） ； Faculty of Computer Science and Technology, Qilu University of Technology, Shandong, China（青岛科技大学计算机科学与技术学院） ； Zhongguancun Academy, Beijing, China（中关村学院）
Comments Accepted to EMNLP 2025 (findings), camera-ready version
Your Language Model Can Secretly Write Like Humans: Contrastive Paraphrase Attacks on LLM-Generated Text Detectors
机构 * Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院，清华大学） ； Harbin Institute of Technology（哈尔滨工业大学） ； Pengcheng Laboratory（鹏城实验室）
Comments Accepted by EMNLP-2025
Prior Prompt Engineering for Reinforcement Fine-Tuning
Comments Accepted at EMNLP 2025, Main; 26 pages, 42 figures
To See a World in a Spark of Neuron: Disentangling Multi-task Interference for Training-free Model Merging
机构 * Xiamen University Malaysia（马来西亚厦门大学） ； The Hong Kong Polytechnic University（香港理工大学） ； Columbia University（哥伦比亚大学） ； Duke University（杜克大学） ； Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））
Comments Accepted to EMNLP 2025 Main Conference. This is the camera-ready version. Code: https://ZzzitaoFang.github.io/projects/NeuroMerging/
MPO: Boosting LLM Agents with Meta Plan Optimization
Comments EMNLP 2025 Findings
REGen: A Reliable Evaluation Framework for Generative Event Argument Extraction
机构 * Department of Computer Science, Dartmouth College（计算机科学系，达特茅斯学院）
Comments Accepted at EMNLP-2025
Beyond Seen Data: Improving KBQA Generalization Through Schema-Guided Logical Form Generation
机构 * The University of Melbourne（墨尔本大学）
Comments Accepted by EMNLP 2025
GENUINE: Graph Enhanced Multi-level Uncertainty Estimation for Large Language Models
机构 * Virginia Polytechnic Institute and State University（弗吉尼亚理工学院和州立大学） ； Ball State University（巴尔的摩州立大学） ； Dartmouth College（达特茅斯学院）
Comments Accepted by EMNLP 2025
Uncovering Scaling Laws for Large Language Models via Inverse Problems
机构 * Singapore-MIT Alliance for Research and Technology（新加坡-麻省理工联盟研究技术中心） ； Dept. of Computer Science, National University of Singapore（新加坡国立大学计算机科学系） ； Agency for Science, Technology and Research（科技研究局） ； Institute of Data Science, National University of Singapore（新加坡国立大学数据科学研究院） ； SAP（SAP公司） ； AI Singapore（AI新加坡）
Comments Accepted at EMNLP Findings 2025
MoLoRAG: Bootstrapping Document Understanding via Multi-modal Logic-aware Retrieval
机构 * The Chinese University of Hong Kong（香港中文大学） ； Fuzhou University（福州大学） ； University of Macau（澳门大学）
Comments EMNLP Main 2025
Transferable Direct Prompt Injection via Activation-Guided MCMC Sampling
机构 * School of Software Engineering, Huazhong University of Science and Technology（华中科技大学软件学院） ； School of Cyber Science and Engineering, Huazhong University of Science and Technology（华中科技大学网络安全学院） ； College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算与数据科学学院） ； Faculty of Data Science, City University of Macau（澳门城市大学数据科学学院）
Comments Accepted to EMNLP 2025
Avoiding Knowledge Edit Skipping in Multi-hop Question Answering with Guided Decomposition
机构 * State Key Laboratory for Novel Software Technology, Nanjing University, China（新型软件技术国家重点实验室，南京大学，中国） ； National Institute of Healthcare Data Science, Nanjing University, China（医疗数据科学国家研究院，南京大学，中国）
Comments Accepted in EMNLP Findings 2025
SheetDesigner: MLLM-Powered Spreadsheet Layout Generation with Rule-Based and Vision-Based Reflection
机构 * Peking University（北京大学） ； Microsoft（微软）
Comments Accepted to EMNLP 2025 Main Conference
Mitigating Attention Localization in Small Scale: Self-Attention Refinement via One-step Belief Propagation
机构 * Seoul National University（首尔国立大学）
Comments Accepted at EMNLP 2025
Adaptive LLM Routing under Budget Constraints
机构 * Fujitsu Research（富士通研究所） ； Microsoft Research（微软研究院）
Comments Accepted at EMNLP 2025 (findings)
Persuasion Dynamics in LLMs: Investigating Robustness and Adaptability in Knowledge and Safety with DuET-PD
机构 * Singapore University of Technology and Design (SUTD)（新加坡科技设计大学） ； Institute for Infocomm Research (I2R), A*STAR, Singapore（信息通信研究院）
Comments To appear at EMNLP 2025
Step-level Verifier-guided Hybrid Test-Time Scaling for Large Language Models
机构 * School of Computer Science and Engineering, Northeastern University（东北大学计算机科学与工程学院） ； NiuTrans Research（NiuTrans研究院） ； ByteDance（字节跳动）
Comments Accepted by EMNLP 2025. Code: https://github.com/Lucky-259/Hybrid_TTS
Addition in Four Movements: Mapping Layer-wise Information Trajectories in LLMs
机构 * Chongqing Normal University（重庆师范大学） ； College of Computer and Information Science（计算机与信息科学学院） ； Chongqing Key Lab of Cognitive Intelligence and Intelligent Finance（重庆认知智能与智能金融重点实验室）
Comments 12 pages, including appendix, 7 figures. EMNLP 2025 submission (ARR May 2025 cycle, reviews pending)
Debatable Intelligence: Benchmarking LLM Judges via Debate Speech Evaluation
机构 * School of Computer Science and Engineering, The Hebrew University of Jerusalem（计算机科学与工程学院，特拉维夫大学） ； IBM Research（IBM研究院） ； The Allen Institute for AI (AI2)（人工智能研究所）
Comments EMNLP 2025. Code: https://github.com/noy-sternlicht/Debatable-Intelligence
Are Economists Always More Introverted? Analyzing Consistency in Persona-Assigned LLMs
机构 * Research Centre for Information Systems Engineering (LIRIS), KU Leuven（信息系统工程研究中心（LIRIS），鲁汶大学） ； Department of Engineering Management, University of Antwerp（工程管理系，安特卫普大学） ； Department of Decision Analytics and Risk, University of Southampton（决策分析与风险系，南安普顿大学） ； School of Information, University of Michigan（信息学院，密歇根大学）
Comments Accepted to EMNLP 2025 findings
Multimodal Emotion Recognition in Conversations: A Survey of Methods, Trends, Challenges and Prospects
机构 * Guangdong Provincial Key Laboratory of Quantum Engineering and Quantum Materials（广东省量子工程与量子材料重点实验室） ； School of Electronic Science and Engineering (School of Microelectronics), South China Normal University（华南师范大学电子科学学院（微电子学院）） ； North Carolina Central University（北卡罗来纳中央大学） ； Georgia Institute of Technology（佐治亚理工学院） ； Columbia University（哥伦比亚大学） ； LMU Munich & Munich Center for Machine Learning（慕尼黑大学及慕尼黑机器学习中心）
Comments EMNLP 2025 Findings
Pierce the Mists, Greet the Sky: Decipher Knowledge Overshadowing via Knowledge Circuit Analysis
机构 * The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）） ； The Hong Kong University of Science and Technology（香港科技大学） ； Shanghai Jiao Tong University（上海交通大学） ； Nanyang Technological University（南洋理工大学）
Comments Accepted by 2025 EMNLP Main
OBLIVIATE: Robust and Practical Machine Unlearning for Large Language Models
机构 * The Hong Kong Polytechnic University（香港理工大学） ； The State Key Laboratory of Blockchain and Data Security, Zhejiang University（浙江大学区块链与数据安全国家重点实验室）
Comments To appear at EMNLP 25 main conference
Unlearning vs. Obfuscation: Are We Truly Removing Knowledge?
机构 * Department of Engineering, University of Cambridge（剑桥大学工程系） ； Department of Informatics, King’s College London（伦敦大学国王学院信息学院） ； SCB 10X, SCBX Group（SCB 10X，SCBX集团）
Comments To Appear in EMNLP 2025 main conference
M-ABSA: A Multilingual Dataset for Aspect-Based Sentiment Analysis
Comments EMNLP 2025
Cardiverse: Harnessing LLMs for Novel Card Game Prototyping
Comments 37 pages, 13 figures, 8 tables. Accepted by EMNLP 2025
