EMNLP

MEXA: Towards General Multimodal Reasoning with Dynamic Multi-Expert Aggregation

Shoubin Yu, Yue Zhang, Ziyang Wang, Jaehong Yoon, Mohit Bansal

机构 * UNC Chapel Hill（北卡罗来纳大学教堂山分校） ； Nanyang Technological University（南洋理工大学） 纠错

Comments EMNLP 2025 Findings; The first two authors contributed equally; Github link: https://github.com/Yui010206/MEXA

COUNTDOWN: Contextually Sparse Activation Filtering Out Unnecessary Weights in Down Projection

Jaewon Cheon, Pilsung Kang

Comments EMNLP 2025 (Main Track)

LyapLock: Bounded Knowledge Preservation in Sequential Large Language Model Editing

Peng Wang, Biyu Zhou, Xuehai Tang, Jizhong Han, Songlin Hu

机构 * Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所） ； School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络空间安全学院） 纠错

Comments EMNLP 2025 main

SAGE: A Generic Framework for LLM Safety Evaluation

Madhur Jindal, Hari Shrawgi, Parag Agrawal, Sandipan Dandapat

Comments Accepted to EMNLP 2025

MOSAIC: Modeling Social AI for Content Dissemination and Regulation in Multi-Agent Simulations

Genglin Liu, Vivian Le, Salman Rahman, Elisa Kreiss, Marzyeh Ghassemi, Saadia Gabriel

机构 * University of California, Los Angeles（加州大学洛杉矶分校） ； MIT CSAIL（麻省理工学院计算机科学与人工智能实验室） 纠错

Comments Accepted into EMNLP 2025 Main Conference, Oral Presentation

FaithUn: Toward Faithful Forgetting in Language Models by Investigating the Interconnectedness of Knowledge

Nakyeong Yang, Minsung Kim, Seunghyun Yoon, Joongbo Shin, Kyomin Jung

机构 * Seoul National University（首尔国立大学） ； Adobe Research（Adobe研究） ； LG AI Research（LG人工智能研究） 纠错

Comments accepted to EMNLP 2025

Scaling Down, Serving Fast: Compressing and Deploying Efficient LLMs for Recommendation Systems

Kayhan Behdin, Ata Fatahibaarzi, Qingquan Song, Yun Dai, Aman Gupta, Zhipeng Wang, Shao Tang, Hejian Sang, Gregory Dexter, Sirou Zhu, Siyu Zhu, Tejas Dharamsi, Vignesh Kothapalli, Zhoutong Fu, Yihan Cao, Pin-Lun Hsu, Fedor Borisyuk, Natesh Pillai, Luke Simon, Rahul Mazumder

机构 * LinkedIn ； LinkedIn LLM Efficiency Core Team（LinkedIn LLM效率核心团队） ； MIT（麻省理工学院） 纠错

Comments Accepted to EMNLP 2025 Industry Track - Oral Presentation

ControlText: Unlocking Controllable Fonts in Multilingual Text Rendering without Font Annotations

Bowen Jiang, Yuan Yuan, Xinyi Bai, Zhuoqun Hao, Alyson Yin, Yaojie Hu, Wenyu Liao, Lyle Ungar, Camillo J. Taylor

机构 * University of Pennsylvania（宾夕法尼亚大学） ； Cornell University（康奈尔大学） ； University of California, Irvine（加州大学伊藤分校） 纠错

Comments The 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP) Findings

Leveraging Large Language Models for Code-Mixed Data Augmentation in Sentiment Analysis

Linda Zeng

机构 * The Harker School（哈克尔学校） 纠错

Comments 17 pages, 4 figures, 11 tables, To be published in the Proceedings of the Second Workshop on Social Influence in Conversations (SICon 2024), co-located with EMNLP 2024

Chatbot To Help Patients Understand Their Health

Won Seok Jang, Hieu Tran, Manav Mistry, SaiKiran Gandluri, Yifan Zhang, Sharmin Sultana, Sunjae Kown, Yuan Zhang, Zonghai Yao, Hong Yu

机构 * Center for Healthcare Organization and Implementation Research, VA Bedford Health Care（VA贝德福德医疗中心健康组织与实施研究中心） ； Miner School of Computer and Information Sciences, University of Massachusetts Lowell（马萨诸塞大学洛厄尔分校计算机与信息科学学院） ； Manning College of Information and Computer Sciences, University of Massachusetts Amherst（马萨诸塞大学阿姆赫斯特分校信息与计算机科学学院） 纠错

Comments Accepted in EMNLP 2025 Findings

Dipper: Diversity in Prompts for Producing Large Language Model Ensembles in Reasoning tasks

Gregory Kang Ruey Lau, Wenyang Hu, Diwen Liu, Jizhuo Chen, See-Kiong Ng, Bryan Kian Hsiang Low

机构 * National University of Singapore（新加坡国立大学） ； SAP（SAP公司） 纠错

Comments Accepted to EMNLP 2025 Main Conference

Generative Annotation for ASR Named Entity Correction

Yuanchang Luo, Daimeng Wei, Shaojun Li, Hengchao Shang, Jiaxin Guo, Zongyao Li, Zhanglin Wu, Xiaoyu Chen, Zhiqiang Rao, Jinlong Yang, Hao Yang

机构 * Huawei Translation Service Center, Beijing, China（华为翻译服务中心，北京，中国） 纠错

Comments 12 pages, 7 figures, 7 tables, EMNLP 2025

Marcel: A Lightweight and Open-Source Conversational Agent for University Student Support

Jan Trienes, Anastasiia Derzhanskaia, Roland Schwarzkopf, Markus Mühling, Jörg Schlötterer, Christin Seifert

机构 * Marburg University（马尔堡大学） 纠错

Comments Accepted at EMNLP 2025 (System Demonstrations)

Video-RTS: Rethinking Reinforcement Learning and Test-Time Scaling for Efficient and Enhanced Video Reasoning

Ziyang Wang, Jaehong Yoon, Shoubin Yu, Md Mohaiminul Islam, Gedas Bertasius, Mohit Bansal

机构 * UNC Chapel Hill（北卡罗来纳大学教堂山分校） ； Nanyang Technological University（南洋理工大学） 纠错

Comments EMNLP 2025. The first two authors contributed equally. Project page: https://sites.google.com/cs.unc.edu/videorts2025/

DiscoSG: Towards Discourse-Level Text Scene Graph Parsing through Iterative Graph Refinement

Shaoqing Lin, Chong Teng, Fei Li, Donghong Ji, Lizhen Qu, Zhuang Li

Comments EMNLP 2025 (oral), 26 pages

Sketch-of-Thought: Efficient LLM Reasoning with Adaptive Cognitive-Inspired Sketching

Simon A. Aytes, Jinheon Baek, Sung Ju Hwang

机构 * KAIST（韩国科学技术院） 纠错

Comments EMNLP 2025

Do Large Language Models Know How Much They Know?

Gabriele Prato, Jerry Huang, Prasanna Parthasarathi, Shagun Sodhani, Sarath Chandar

机构 * Chandar Research Lab（昌达尔研究实验室） ； Mila – Quebec AI Institute（魁北克人工智能研究所） ； Université de Montréal（蒙特利尔大学） ； Meta FAIR ； Polytechnique Montréal（蒙特利尔理工学院） ； Canada CIFAR AI Chair（加拿大CIFAR人工智能主席） 纠错

Comments Published as a long paper at the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP). Official version of paper within conference proceedings is available at https://aclanthology.org/2024.emnlp-main.348/

LVLMs are Bad at Overhearing Human Referential Communication

Zhengxiang Wang, Weiling Li, Panagiotis Kaliosis, Owen Rambow, Susan E. Brennan

机构 * Department of Linguistics（语言学系） ； Institute for Advanced Computational Science（先进计算科学研究所） ； Department of Psychology（心理学系） ； Department of Computer Science, Stony Brook University（石溪大学计算机科学系） 纠错

Comments EMNLP 2025 (Main)

Uniform Information Density and Syntactic Reduction: Revisiting $\textit{that}$-Mentioning in English Complement Clauses

Hailin Hao, Elsi Kaiser

机构 * University of Southern California（南加州大学） 纠错

Comments To appear in EMNLP 2025

Structure-Conditional Minimum Bayes Risk Decoding

Bryan Eikema, Anna Rutkiewicz, Mario Giulianelli

机构 * University of Amsterdam（阿姆斯特丹大学） ； University of Zurich（苏黎世大学） ； UCL（伦敦大学学院） 纠错

Comments EMNLP 2025 Camera-Ready

Teacher Demonstrations in a BabyLM's Zone of Proximal Development for Contingent Multi-Turn Interaction

Suchir Salhan, Hongyi Gu, Donya Rooein, Diana Galvan-Sosa, Gabrielle Gaudeau, Andrew Caines, Zheng Yuan, Paula Buttery

机构 * ALTA Institute（ALTA研究所） ； Dept. of Computer Science & Technology, Cambridge University（计算机科学与技术系，剑桥大学） ； Bocconi University（博科尼大学） ； Sheffield University（谢菲尔德大学） 纠错

Comments Outstanding Paper Award, EMNLP 2025 BabyLM Workshop - Oral presentation, Suzhou, China

The Impact of Negated Text on Hallucination with Large Language Models

Jaehyung Seo, Hyeonseok Moon, Heuiseok Lim

Comments Accepted to the EMNLP 2025

Are Stereotypes Leading LLMs' Zero-Shot Stance Detection ?

Anthony Dubreuil, Antoine Gourru, Christine Largeron, Amine Trabelsi

机构 * Laboratoire Hubert Curien, UMR CNRS 5516（Hubert Curien实验室，CNRS UMR 5516） ； Department of Computer Science, Université de Sherbrooke（计算机科学系，Sherbrooke大学） 纠错

Comments Accepted in EMNLP 2025 (Main)

ixi-GEN: Efficient Industrial sLLMs through Domain Adaptive Continual Pretraining

Seonwu Kim, Yohan Na, Kihun Kim, Hanhee Cho, Geun Lim, Mintae Kim, Seongik Park, Ki Hyun Kim, Youngsub Han, Byoung-Ki Jeon

Comments Accepted at EMNLP 2025 Industry Track

Breaking Bad Tokens: Detoxification of LLMs Using Sparse Autoencoders

Agam Goyal, Vedant Rathi, William Yeh, Yian Wang, Yuen Chen, Hari Sundaram

机构 * Siebel School of Computing and Data Science（计算机与数据科学学院） 纠错

Comments EMNLP 2025

MoMoE: Mixture of Moderation Experts Framework for AI-Assisted Online Governance

Agam Goyal, Xianyang Zhan, Yilun Chen, Koustuv Saha, Eshwar Chandrasekharan

机构 * Siebel School of Computing and Data Science（计算机与数据科学学院） 纠错

Comments EMNLP 2025 (Oral)

Is Safety Standard Same for Everyone? User-Specific Safety Evaluation of Large Language Models

Yeonjun In, Wonjoong Kim, Kanghoon Yoon, Sungchul Kim, Mehrab Tanjim, Sangwu Park, Kibum Kim, Chanyoung Park

Comments EMNLP 2025 Findings

Permutative Preference Alignment from Listwise Ranking of Human Judgments

Yang Zhao, Yixin Wang, Mingzhang Yin

机构 * University of Texas at Austin（德克萨斯大学奥斯汀分校） ； University of Michigan, Ann Arbor（密歇根大学安娜堡分校） ； University of Florida（佛罗里达大学） 纠错

Comments Published at EMNLP 2025 Main Conference

Can They Dixit? Yes they Can! Dixit as a Playground for Multimodal Language Model Capabilities

Nishant Balepur, Dang Nguyen, Dayeon Ki

机构 * University of Maryland（马里兰大学） 纠错

Comments Accepted as a Spotlight paper at the EMNLP 2025 Wordplay Workshop

What is the Best Sequence Length for BABYLM?

Suchir Salhan, Richard Diehl Martinez, Zébulon Goriely, Paula Buttery

机构 * Department of Computer Science & Technology, University of Cambridge, U.K.（计算机科学与技术系，剑桥大学，英国） ； ALTA Institute, University of Cambridge, U.K.（ALTA研究所，剑桥大学，英国） 纠错

Comments Paper Accepted at the 2025 BabyLM Workshop @ EMNLP (Suzhou, China)