Convergence and Divergence of Language Models under Different Random Seeds
机构 * ETH Zürich（苏黎世联邦理工学院） ； University of Texas at Austin（德克萨斯大学奥斯汀分校）
Comments Published at EMNLP 2025
期刊&会议
EMNLP
Conference on Empirical Methods in Natural Language Processing · 会议 · Natural Language Processing
The Impact of Language Mixing on Bilingual LLM Reasoning
机构 * University of Pennsylvania（宾夕法尼亚大学）
Comments Accepted at EMNLP 2025 (Main Conference)
Causal Interventions Reveal Shared Structure Across English Filler-Gap Constructions
机构 * The University of Texas at Austin（德克萨斯大学奥斯汀分校） ； Stanford University（斯坦福大学）
Comments 22 pages, 21 figures, 10 tables; EMNLP (Main) 2025
QUARTZ : QA-based Unsupervised Abstractive Refinement for Task-oriented Dialogue Summarization
机构 * Université de Lorraine, CNRS, Inria, LORIA（法国洛林大学、法国国家科学研究中心、法国国家信息与自动化研究所、LORIA研究所） ； Université Sorbonne Paris Nord, CNRS, Laboratoire d’Informatique de Paris Nord, LIPN（法国巴黎北大学、法国国家科学研究中心、巴黎北信息学实验室、LIPN研究所） ； Inserm, Centre de Recherche des Cordeliers, Université Paris Cité, Sorbonne Université（法国国家医学研究院、cordeliers研究中心、巴黎城市大学、索邦大学） ； HeKA, Inria Paris（HeKA、法国国家信息与自动化研究所巴黎分所） ； Department of Medical Informatics, Assistance Publique Hôpitaux de Paris, Georges Pompidou European Hospital（医学信息学系、巴黎公共医院、乔治·蓬皮杜欧洲医院）
Comments Accepted to Empirical Methods in Natural Language Processing (EMNLP 2025)
Type-Less yet Type-Aware Inductive Link Prediction with Pretrained Language Models
Comments Accepted and to appear in Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP 2025)
End-to-End Aspect-Guided Review Summarization at Scale
机构 * Wayfair
Comments Camera-ready preprint for EMNLP 2025 Industry Track
Scaling Up Temporal Domain Generalization via Temporal Experts Averaging
机构 * Boston University（波士顿大学） ； University of Central Florida（中央佛罗里达大学）
Comments Accepted by EMNLP 2025 main
RAGferee: Building Contextual Reward Models for Retrieval-Augmented Generation
Comments Accepted to EMNLP 2025 Main
Reliability Crisis of Reference-free Metrics for Grammatical Error Correction
机构 * Nara Institute of Science and Technology（奈良科学技術研究所）
Comments EMNLP 2025 Findings
VELA: An LLM-Hybrid-as-a-Judge Approach for Evaluating Long Image Captions
机构 * Keio University（庆应大学）
Comments EMNLP 2025 Main Conference
ReTAG: Retrieval-Enhanced, Topic-Augmented Graph-Based Global Sensemaking
机构 * Dept. of CSE, Korea University（计算机科学与工程系，韩国大学）
Comments 9 pages, 5 figures, EMNLP 2025 Findings
CATCH: A Novel Data Synthesis Framework for High Therapy Fidelity and Memory-Driven Planning Chain of Thought in AI Counseling
机构 * School of EE South China University of Technology Guangzhou China（华南理工大学电子工程学院） ； Foshan University Foshan China（佛山大学）
Comments To be published in EMNLP 2025 Findings
Controlled Generation for Private Synthetic Text
机构 * Johns Hopkins University（约翰霍普金斯大学）
Comments EMNLP 2025
Mitigating Biases in Language Models via Bias Unlearning
机构 * University of Science and Technology of China（中国科学技术大学） ； State Key Laboratory of Communication Content Cognition, People’s Daily Online（通信内容认知国家重点实验室）
Comments EMNLP 2025 MainConference
Chat-Driven Text Generation and Interaction for Person Retrieval
机构 * Zhejiang University（浙江大学） ； Northwest A&F University（西北农林科技大学）
Comments Accepted to EMNLP 2025 Main Conference. 13 pages, 3 figures
Linguistic and Embedding-Based Profiling of Texts generated by Humans and Large Language Models
机构 * Department of Politics and Public Administration University of Konstanz（政治与公共管理系 康斯坦茨大学）
Comments arXiv admin note: text overlap with arXiv:2412.03025
Journal ref Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP 2025)
TableRAG: A Retrieval Augmented Generation Framework for Heterogeneous Document Reasoning
机构 * Huawei Cloud BU（华为云业务部）
Comments Accepted by EMNLP 2025. Codes are available at https://github.com/yxh-y/TableRAG/tree/main
Efficient Context Selection for Long-Context QA: No Tuning, No Iteration, Just Adaptive-$k$
机构 * University of Notre Dame（内布拉斯加大学达灵顿分校） ； Megagon Labs（梅加贡实验室）
Comments 26 pages, 16 tables, 5 figures. Accepted at EMNLP 2025 (Main)
Static Word Embeddings for Sentence Semantic Representation
机构 * ZOZO Research（ZOZO研究院）
Comments 17 pages; accepted to the Main Conference of EMNLP 2025
How Do Large Vision-Language Models See Text in Image? Unveiling the Distinctive Role of OCR Heads
Comments EMNLP 2025 Oral
DEBATE, TRAIN, EVOLVE: Self Evolution of Language Model Reasoning
机构 * Department of Computer Science, Virginia Tech, USA（弗吉尼亚理工大学计算机科学系）
Comments Accepted to EMNLP 2025 Main Conference
ThinkEdit: Interpretable Weight Editing to Mitigate Overly Short Thinking in Reasoning Models
机构 * UCSD CSE（加州大学圣地亚哥分校计算机科学系） ； UCSD HDSI（加州大学圣地亚哥分校人类发展与应用科学学院）
Comments Accepted to EMNLP 2025
Value Profiles for Encoding Human Variation
机构 * Department of Computer Science, University of Washington（华盛顿大学计算机科学系） ； Google DeepMind（谷歌DeepMind）
Comments EMNLP 2025
Towards Reasoning Ability of Small Language Models
机构 * Department of Computer Science, Virginia Tech, USA（弗吉尼亚理工大学计算机科学系） ； Department of Physics, Clarendon Laboratory, University of Oxford, UK（牛津大学物理系，克伦德尔实验室） ； NVIDIA Corporation（英伟达公司）
Comments Accepted to EMNLP 2025 Main Conference
SAFE-SQL: Self-Augmented In-Context Learning with Fine-grained Example Selection for Text-to-SQL
机构 * Department of Artificial Intelligence, Chung-Ang University（人工智能系， Chung-Ang 大学） ； New York University（纽约大学）
Comments EMNLP 2025 (Main Conference)
Where Fact Ends and Fairness Begins: Redefining AI Bias Evaluation through Cognitive Biases
机构 * The Chinese University of Hong Kong（香港中文大学） ； University of California, Los Angeles（加州大学洛杉矶分校）
Comments Accepted to EMNLP 2025 (Findings)
Mind the Value-Action Gap: Do LLMs Act in Alignment with Their Values?
机构 * University of Washington（华盛顿大学） ； NYU Shanghai（纽约大学上海校区） ； New York University（纽约大学）
Comments EMNLP 2025 Main Paper
Dagger Behind Smile: Fool LLMs with a Happy Ending Story
机构 * S-Lab, Nanyang Technological University, Singapore（南洋理工大学新加坡分校S实验室） ； College of Computing and Data Science, Nanyang Technological University, Singapore（南洋理工大学计算机与数据科学学院）
Comments EMNLP 2025 Findings
Turning Logic Against Itself : Probing Model Defenses Through Contrastive Questions
机构 * Ubiquitous Knowledge Processing Lab (UKP Lab), Department of Computer Science and Hessian Center for AI (hessian.AI), Technical University of Darmstadt（德累斯顿技术大学计算机科学系、海斯堡人工智能中心（hessian.AI）、通用知识处理实验室（UKP Lab））
Comments Accepted at EMNLP 2025 (Main)
Cut the Deadwood Out: Backdoor Purification via Guided Module Substitution
机构 * National University of Singapore（新加坡国立大学） ； Macquarie University（麦考瑞大学） ； University College London（伦敦大学学院） ； Monash University（墨尔本大学）
Comments Accepted to Findings of the Association for Computational Linguistics: EMNLP 2025
