AIP: Subverting Retrieval-Augmented Generation via Adversarial Instructional Prompt
机构 * Clemson University（克莱姆森大学）
Comments Accepted at EMNLP 2025 Conference
期刊&会议
EMNLP
Conference on Empirical Methods in Natural Language Processing · 会议 · Natural Language Processing
CLEAR: A Comprehensive Linguistic Evaluation of Argument Rewriting by Large Language Models
机构 * University of St. Gallen（圣加尔登大学）
Comments Accepted at EMNLP 2025 Findings
Mind the Gap: A Closer Look at Tokenization for Multiple-Choice Question Answering with LLMs
机构 * Johannes Gutenberg University Mainz（法兰克福-马因茨大学） ； University of Colorado Boulder（科罗拉多大学博尔德分校）
Comments Accepted to EMNLP 2025 Main
A Knowledge-driven Adaptive Collaboration of LLMs for Enhancing Medical Decision-making
机构 * Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)（莫扎德·本·扎耶德人工智能大学） ； University of Electronic Science and Technology of China（电子科学与技术大学） ； Swiss Federal Institute of Technology Lausanne (EPFL)（苏黎世联邦理工学院）
Comments The paper has been accepted to the EMNLP 2025 Main Conference
Evaluating Large Language Models for Cross-Lingual Retrieval
Comments Accepted at EMNLP 2025 (Findings)
From Ground Trust to Truth: Disparities in Offensive Language Judgments on Contemporary Korean Political Discourse
Comments EMNLP 2025 findings
MUSE: MCTS-Driven Red Teaming Framework for Enhanced Multi-Turn Dialogue Safety in Large Language Models
机构 * East China Normal University（东华大学） ； Xi’an Jiaotong University（西安交通大学） ； Meituan（美团） ； Zhejiang University（浙江大学）
Comments EMNLP 2025 main conference
Reveal and Release: Iterative LLM Unlearning with Self-generated Data
机构 * New York University Shanghai（纽约大学上海）
Comments Accepted to EMNLP 2025 Findings
Catch Me If You Can? Not Yet: LLMs Still Struggle to Imitate the Implicit Writing Styles of Everyday Authors
机构 * Stony Brook University（石英溪大学） ； The Pennsylvania State University（宾夕法尼亚州立大学） ； Bosch Center for AI（博世人工智能中心）
Comments EMNLP 2025 (Findings)
Not What the Doctor Ordered: Surveying LLM-based De-identification and Quantifying Clinical Information Loss
机构 * Department of Computing Science, University of Alberta（计算科学系，阿尔伯塔大学） ； Department of Medicine, University of Alberta（医学系，阿尔伯塔大学） ； Alberta Machine Intelligence Institute (Amii)（阿尔伯塔机器智能研究所） ； Arthritis Research Canada（关节炎研究加拿大）
Comments Accepted to EMNLP 2025
Annotating Training Data for Conditional Semantic Textual Similarity Measurement using Large Language Models
机构 * University of Liverpool（利弗池大学） ； Cardiff University（卡迪夫大学）
Comments Accepted to EMNLP 2025
AssoCiAm: A Benchmark for Evaluating Association Thinking while Circumventing Ambiguity
机构 * Sun Yat-sen University（中山大学） ； Guangdong University of Technology（广东工业大学） ； Northwestern University（西北大学）
Comments Accepted by EMNLP 2025 main track
Pluralistic Alignment for Healthcare: A Role-Driven Framework
机构 * Cheriton School of Computer Science, University of Waterloo（滑铁卢大学计算机科学学院） ； School of Computing, FSE, Macquarie University（麦觉大学计算机学院） ； School of Computing and Information System, the University of Melbourne（墨尔本大学计算机与信息系统学院） ； Rajax Network Technology (ele.me), China（中国Rajax网络技术（饿了么）） ； Alibaba Cloud Computing, Alibaba Group, China（中国阿里云 computing，阿里集团）
Comments Accepted to EMNLP 2025 (Main Proceedings)
MovieCORE: COgnitive REasoning in Movies
机构 * National Taiwan University（国立台湾大学） ； NVIDIA ； National Tsing Hua University（国立清华大学）
Comments Accepted for EMNLP'2025 Main Conference (Oral Presentation). Project Page: https://joslefaure.github.io/assets/html/moviecore.html
SMART: Simulated Students Aligned with Item Response Theory for Question Difficulty Prediction
机构 * University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校） ； Cambium Assessment（Cambium评估）
Comments Published in EMNLP 2025: The 2025 Conference on Empirical Methods in Natural Language Processing
DiCoRe: Enhancing Zero-shot Event Detection via Divergent-Convergent LLM Reasoning
机构 * Computer Science Department, University of California, Los Angeles（加州大学洛杉矶分校计算机科学系）
Comments Accepted at EMNLP 2025 Main
ImpRAG: Retrieval-Augmented Generation with Implicit Queries
机构 * Rutgers University（新泽西罗格斯大学） ； FAIR, Meta（FAIR，Meta）
Comments Findings of EMNLP 2025
Enhancing Logical Reasoning in Language Models via Symbolically-Guided Monte Carlo Process Supervision
机构 * School of Computer Science, University of Sheffield（谢菲尔德大学计算机科学学院） ； School of Electronic Engineering and Computer Science, Queen Mary University of London（伦敦大学玛丽女王学院电子工程与计算机科学学院） ； The Alan Turing Institute（艾伦·图灵研究所）
Comments EMNLP 2025 (Main), 9+6 pages
Mechanistic Understanding and Mitigation of Language Confusion in English-Centric Large Language Models
机构 * Center for Information and Language Processing (CIS)（信息与语言处理中心） ； Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心）
Comments Accepted to EMNLP 2025 Findings
An Empirical Study of Position Bias in Modern Information Retrieval
Comments EMNLP 2025 Findings (camera-ready)
CARE: Multilingual Human Preference Learning for Cultural Awareness
机构 * Georgia Institute of Technology（佐治亚理工学院） ； Sony Group Corporation（索尼集团） ； Sony AI（索尼人工智能）
Comments Accepted at EMNLP 2025
Unsupervised Concept Vector Extraction for Bias Control in LLMs
机构 * Department of Computer Science University of Virginia（计算机科学系 首都维吉尼亚大学）
Comments Accepted to EMNLP 2025
SNaRe: Domain-aware Data Generation for Low-Resource Event Detection
机构 * Computer Science Department, University of California, Los Angeles（加州大学洛杉矶分校计算机科学系）
Comments Accepted at EMNLP 2025 Main
Superpose Task-specific Features for Model Merging
机构 * Tsinghua University（清华大学） ； Huawei（华为） ； State Key laboratory of Space Network and Communications（空间网络与通信国家重点实验室）
Comments EMNLP 2025
RAcQUEt: Unveiling the Dangers of Overlooked Referential Ambiguity in Visual LLMs
机构 * Amsterdam UMC, Department of Medical Informatics（阿姆斯特丹大学医学中心，医学信息学系） ； Center for Information and Language Processing, LMU Munich（信息与语言处理中心，慕尼黑大学） ； Munich Center for Machine Learning (MCML), Munich（慕尼黑机器学习中心（MCML）） ； Institute for Logic, Language and Computation (ILLC), University of Amsterdam（逻辑、语言与计算研究所（ILLC），阿姆斯特丹大学）
Comments Accepted to EMNLP 2025 (Main Conference)
Unlocking Legal Knowledge: A Multilingual Dataset for Judicial Summarization in Switzerland
机构 * University of Bern（伯尔尼大学） ； Bern University of Applied Sciences（伯尔尼应用科学大学） ； Stanford University（斯坦福大学） ； University of Fribourg（弗里堡大学）
Comments Accepted to EMNLP 2025 Findings
3DS: Medical Domain Adaptation of LLMs via Decomposed Difficulty-based Data Selection
机构 * School of Computer Science, Peking University, Beijing, China（北京大学计算机学院） ； Key Laboratory of High Confidence Software Technologies, Ministry of Education（教育部高可信软件技术重点实验室） ； National Engineering Research Center for Software Engineering, Peking University, China（软件工程国家级工程研究中心） ； Big Data Technology Research Center, Nanhu Laboratory, Jiaxing, China（南湖实验室大数据技术研究中心） ； Peking University Information Technology Institute, Tianjin Binhai, China（北京大学信息科学技术研究院）
Comments Accepted to EMNLP 2025 (Main Conference)
FG-PRM: Fine-grained Hallucination Detection and Mitigation in Language Model Mathematical Reasoning
机构 * Department of Computer Science, University of Texas at Dallas（德克萨斯大学达拉斯分校计算机科学系） ； Department of Electrical Engineering Computer Science, University of Michigen（密歇根大学电子工程与计算机科学系）
Comments Findings of EMNLP 2025
