Spectral Scaling Laws in Language Models: How Effectively Do Feed-Forward Networks Use Their Latent Space?
机构 * New York University（纽约大学）
Comments EMNLP 2025 Main Conference (Long paper)
期刊&会议
EMNLP
Conference on Empirical Methods in Natural Language Processing · 会议 · Natural Language Processing
Enhancing Rating Prediction with Off-the-Shelf LLMs Using In-Context User Reviews
机构 * The University of Tokyo（东京大学） ； Riken（理化学研究所）
Comments Accepted to EMNLP 2025 PALS Workshop
Efficient Layer-wise LLM Fine-tuning for Revision Intention Prediction
机构 * Department of Computer Science, Learning Research & Development Center University of Pittsburgh（计算机科学系、学习研究与开发中心匹兹堡大学）
Comments In The Conference on Empirical Methods in Natural Language Processing (EMNLP), November 2025
PrimeX: A Dataset of Worldview, Opinion, and Explanation
机构 * Apple（苹果公司） ； University of Southern California（南加州大学）
Comments EMNLP 2025 Main
Explaining novel senses using definition generation with open language models
机构 * University of Oslo（奥斯陆大学） ； KU Leuven - Flanders Make（库尔勒文大学-佛兰德斯制造）
Comments EMNLP 2025 Findings
Taxonomy of Comprehensive Safety for Clinical Agents
Comments EMNLP 2025 Industry
Out of the Box, into the Clinic? Evaluating State-of-the-Art ASR for Clinical Applications for Older Adults
机构 * Department of Public Health and Primary Care, Leiden University Medical Center（莱顿大学医学中心公共卫生与初级保健系） ； Leiden Institute of Advanced Computer Science, Leiden University（莱顿大学高级计算机科学研究所） ； Center for Medicine for Older People, Leiden University Medical Center（莱顿大学医学中心老年医学中心） ； Department of Internal Medicine, Leiden University Medical Center（莱顿大学医学中心内科系）
Comments Forthcoming in the Proceedings of the Fourth Workshop on Bridging Human Computer Interaction and Natural Language Processing HCINLP (EMNLP)
What if Othello-Playing Language Models Could See?
机构 * University of Amsterdam（阿姆斯特丹大学） ； ETH Zürich（苏黎世联邦理工学院） ； University of Copenhagen（哥本哈根大学）
Comments ICML 2025 Assessing World Models Workshop; EMNLP 2025 Findings
Are Knowledge and Reference in Multilingual Language Models Cross-Lingually Consistent?
Comments EMNLP'25 Findings Camera Ready
Leaky Thoughts: Large Reasoning Models Are Not Private Thinkers
机构 * Parameter Lab（参数实验室） ； Data and Web Science Group（数据与网络科学小组） ； University of Mannheim（曼海姆大学） ； UKP Lab（UKP实验室） ； Technical University of Darmstadt（达姆施塔特技术大学） ； NAVER AI Lab（NAVER人工智能实验室） ； University of Tübingen（图宾根大学） ； Tübingen AI Center（图宾根人工智能中心）
Comments Accepted to EMNLP 2025 (Main)
Steering LLM Reasoning Through Bias-Only Adaptation
机构 * T-Tech ； Central University（中央大学）
Comments EMNLP 2025
Resolving UnderEdit & OverEdit with Iterative & Neighbor-Assisted Model Editing
机构 * Department of Computer Science, University of Pittsburgh, PA, USA（计算机科学系，匹兹堡大学，宾夕法尼亚州，美国）
Comments Accepted at EMNLP 2025 as Findings
Exploring and Controlling Diversity in LLM-Agent Conversation
机构 * The University of Tokyo（东京大学）
Comments EMNLP 2025 Findings
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
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
