EMNLP

DRISHTIKON: A Multimodal Multilingual Benchmark for Testing Language Models' Understanding on Indian Culture

Arijit Maji, Raghvendra Kumar, Akash Ghosh, Anushka, Nemil Shah, Abhilekh Borah, Vanshika Shah, Nishant Mishra, Sriparna Saha

机构 * Indian Institute of Technology Patna（印度理工学院帕纳巴分校） ； Banasthali Vidyapeeth University（班纳萨利大学） ； Pandit Deendayal Energy University（德英德能源大学） ； Manipal University Jaipur（马哈拉施特拉邦大学贾伊普尔分校） ； Dwarkadas J. Sanghvi College of Engineering（德瓦尔卡斯J.桑格维工程学院） 纠错

Comments EMNLP MAINS 2025

Cross-Cultural Transfer of Commonsense Reasoning in LLMs: Evidence from the Arab World

Saeed Almheiri, Rania Hossam, Mena Attia, Chenxi Wang, Preslav Nakov, Timothy Baldwin, Fajri Koto

机构 * Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学） 纠错

Comments EMNLP 2025 - Findings

AgentInit: Initializing LLM-based Multi-Agent Systems via Diversity and Expertise Orchestration for Effective and Efficient Collaboration

Chunhao Tian, Yutong Wang, Xuebo Liu, Zhexuan Wang, Liang Ding, Miao Zhang, Min Zhang

Comments EMNLP 2025 Findings

Vision-Free Retrieval: Rethinking Multimodal Search with Textual Scene Descriptions

Ioanna Ntinou, Alexandros Xenos, Yassine Ouali, Adrian Bulat, Georgios Tzimiropoulos

机构 * Queen Mary University of London（伦敦女王大学） ； Samsung AI Centre（三星人工智能中心） ； Technical University of Iași（伊阿苏技术大学） 纠错

Comments Accepted at EMNLP 2025

Anecdoctoring: Automated Red-Teaming Across Language and Place

Alejandro Cuevas, Saloni Dash, Bharat Kumar Nayak, Dan Vann, Madeleine I. G. Daepp

机构 * Carnegie Mellon University（卡内基梅隆大学） ； University of Washington（华盛顿大学） ； Microsoft Research（微软研究院） ； Independent Researcher（独立研究者） 纠错

Comments To be published in EMNLP 2025

Context-Aware Hierarchical Taxonomy Generation for Scientific Papers via LLM-Guided Multi-Aspect Clustering

Kun Zhu, Lizi Liao, Yuxuan Gu, Lei Huang, Xiaocheng Feng, Bing Qin

Comments Accepted to EMNLP 2025 Main

Reward-Shifted Speculative Sampling Is An Efficient Test-Time Weak-to-Strong Aligner

Bolian Li, Yanran Wu, Xinyu Luo, Ruqi Zhang

机构 * Department of Computer Science, Purdue University（计算机科学系，普渡大学） 纠错

Comments EMNLP 2025 Main Conference

Columbo: Expanding Abbreviated Column Names for Tabular Data Using Large Language Models

Ting Cai, Stephen Sheen, AnHai Doan

机构 * University of Wisconsin-Madison（威斯康星大学麦迪逊分校） 纠错

Comments Accepted to Findings of EMNLP 2025; 19 pages, 14 figures

Are Vision-Language Models Safe in the Wild? A Meme-Based Benchmark Study

DongGeon Lee, Joonwon Jang, Jihae Jeong, Hwanjo Yu

机构 * Pohang University of Science and Technology (POSTECH)（釜山科学技术大学） 纠错

Comments Accepted to EMNLP 2025

Beyond Input Activations: Identifying Influential Latents by Gradient Sparse Autoencoders

Dong Shu, Xuansheng Wu, Haiyan Zhao, Mengnan Du, Ninghao Liu

机构 * Northwestern University（西北大学） ； University of Georgia（佐治亚大学） ； New Jersey Institute of Technology（新泽西理工学院） 纠错

Comments EMNLP 2025 Main

A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Models

Dong Shu, Xuansheng Wu, Haiyan Zhao, Daking Rai, Ziyu Yao, Ninghao Liu, Mengnan Du

机构 * Northwestern University（西北大学） ； University of Georgia（佐治亚大学） ； New Jersey Institute of Technology（新泽西理工学院） ； George Mason University（乔治·马歇尔大学） 纠错

Comments EMNLP 2025 Findings

LightThinker: Thinking Step-by-Step Compression

Jintian Zhang, Yuqi Zhu, Mengshu Sun, Yujie Luo, Shuofei Qiao, Lun Du, Da Zheng, Huajun Chen, Ningyu Zhang

Comments EMNLP 2025 (oral)

DeepResonance: Enhancing Multimodal Music Understanding via Music-centric Multi-way Instruction Tuning

Zhuoyuan Mao, Mengjie Zhao, Qiyu Wu, Hiromi Wakaki, Yuki Mitsufuji

机构 * Sony Group Corporation（索尼集团公司） ； Sony AI（索尼人工智能） 纠错

Comments Accepted to EMNLP 2025 main conference

Large Vision-Language Model Alignment and Misalignment: A Survey Through the Lens of Explainability

Dong Shu, Haiyan Zhao, Jingyu Hu, Weiru Liu, Ali Payani, Lu Cheng, Mengnan Du

机构 * Northwestern University（西北大学） ； New Jersey Institute of Technology（新泽西理工学院） ； University of Bristol（布里斯托大学） ； Cisco Research（思科研究） ； University of Illinois Chicago（伊利诺伊大学芝加哥分校） 纠错

Comments EMNLP 2025 Findings

Exploring Model Kinship for Merging Large Language Models

Yedi Hu, Yunzhi Yao, Ningyu Zhang, Huajun Chen, Shumin Deng

机构 * Zhejiang University（浙江大学） ； National University of Singapore（新加坡国立大学） ； NUS-NCS Joint Lab（新加坡国立大学NCS联合实验室） 纠错

Comments EMNLP 2025 Findings

Extractive Fact Decomposition for Interpretable Natural Language Inference in one Forward Pass

Nicholas Popovič, Michael Färber

机构 * TU Dresden（德累斯顿技术大学） 纠错

Comments EMNLP 2025

Beyond the Leaderboard: Understanding Performance Disparities in Large Language Models via Model Diffing

Sabri Boughorbel, Fahim Dalvi, Nadir Durrani, Majd Hawasly

机构 * Qatar Computing Research Institute, HBKU（卡塔尔计算研究所，哈瓦那大学） 纠错

Comments 12 pages, accepted to the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP 2025)

Analyzing Uncertainty of LLM-as-a-Judge: Interval Evaluations with Conformal Prediction

Huanxin Sheng, Xinyi Liu, Hangfeng He, Jieyu Zhao, Jian Kang

机构 * University of Rochester（罗切斯特大学） ； University of Southern California（南加州大学） ； MBZUAI 纠错

Comments To appear in EMNLP 2025. Our code and data are available at \url{https://github.com/BruceSheng1202/Analyzing_Uncertainty_of_LLM-as-a-Judge

A Good Plan is Hard to Find: Aligning Models with Preferences is Misaligned with What Helps Users

Nishant Balepur, Matthew Shu, Yoo Yeon Sung, Seraphina Goldfarb-Tarrant, Shi Feng, Fumeng Yang, Rachel Rudinger, Jordan Lee Boyd-Graber

Comments EMNLP 2025

The Ranking Blind Spot: Decision Hijacking in LLM-based Text Ranking

Yaoyao Qian, Yifan Zeng, Yuchao Jiang, Chelsi Jain, Huazheng Wang

机构 * Northeastern University（东北大学） ； Oregon State University（俄勒冈州立大学） ； University of Macau（澳门大学） 纠错

Comments Accepted by EMNLP 2025

CCQA: Generating Question from Solution Can Improve Inference-Time Reasoning in SLMs

Jin Young Kim, Ji Won Yoon

Comments Published as a main conference paper at EMNLP 2025

Speech Vecalign: an Embedding-based Method for Aligning Parallel Speech Documents

Chutong Meng, Philipp Koehn

机构 * George Mason University（乔治·马歇尔大学） ； Johns Hopkins University（约翰霍普金斯大学） 纠错

Comments Accepted by EMNLP 2025 (main)

TurnBack: A Geospatial Route Cognition Benchmark for Large Language Models through Reverse Route

Hongyi Luo, Qing Cheng, Daniel Matos, Hari Krishna Gadi, Yanfeng Zhang, Lu Liu, Yongliang Wang, Niclas Zeller, Daniel Cremers, Liqiu Meng

机构 * Huawei Riemann Lab（华为里emann实验室） ； Technische Universität München（技术大学慕尼黑） ； Hochschule Karlsruhe（卡尔斯鲁厄应用科学大学） 纠错

Comments Accepted to EMNLP 2025 (Main). This is the camera-ready/author version

Event Causality Identification with Synthetic Control

Haoyu Wang, Fengze Liu, Jiayao Zhang, Dan Roth, Kyle Richardson

机构 * Department of Computer and Information Science, UPenn（计算机与信息科学系，宾夕法尼亚大学） ； Allen Institute for AI（人工智能研究院） 纠错

Journal ref EMNLP 2024

From Parameters to Performance: A Data-Driven Study on LLM Structure and Development

Suqing Wang, Zuchao Li, Luohe Shi, Bo Du, Hai Zhao, Yun Li, Qianren Wang

机构 * School of Artificial Intelligence, Wuhan University（武汉大学人工智能学院） ； School of Computer Science, Wuhan University（武汉大学计算机学院） ； School of Computer Science, Shanghai Jiao Tong University（上海交通大学计算机学院） ； Cognitive AI Lab, Shanghai Huawei Technologies, China（上海华为技术有限公司认知人工智能实验室） 纠错

Comments Accepted by EMNLP 2025

Breaking Token Into Concepts: Exploring Extreme Compression in Token Representation Via Compositional Shared Semantics

Kavin R, Pawan Goyal

机构 * Indian Institute of Technology Kharagpur（印度理工学院Khargapur） 纠错

Comments 5 pages, 1 figure Accepted at EMNLP 2025 Findings (Short)

Journal ref EMNLP 2025 Findings (Short)

PruneCD: Contrasting Pruned Self Model to Improve Decoding Factuality

Byeongho Yu, Changhun Lee, Jungyu Jin, Eunhyeok Park

Comments accepted at EMNLP 2025 Main Conference

PolBiX: Detecting LLMs' Political Bias in Fact-Checking through X-phemisms

Charlott Jakob, David Harbecke, Patrick Parschan, Pia Wenzel Neves, Vera Schmitt

机构 * Quality & Usability Lab, Technische Universität Berlin（柏林技术大学质量与可用性实验室） ； German Research Center for Artificial Intelligence (DFKI), Berlin（德国人工智能研究中心（DFKI）） ； Department of Media and Communication, Ludwig-Maximilians-Universität München（慕尼黑路德维希-马克西米利安大学媒体与传播系） 纠错

Comments Accepted at Findings of EMNLP 2025, camera-ready version

Toxicity Red-Teaming: Benchmarking LLM Safety in Singapore's Low-Resource Languages

Yujia Hu, Ming Shan Hee, Preslav Nakov, Roy Ka-Wei Lee

机构 * Singapore University of Technology and Design（新加坡科技设计大学） ； Mohamed bin Zayed University of Artificial Intelligence（马尔代夫 bin Zayed 人工智能大学） 纠错

Comments 9 pages, EMNLP 2025

Linguistic Neuron Overlap Patterns to Facilitate Cross-lingual Transfer on Low-resource Languages

Yuemei Xu, Kexin Xu, Jian Zhou, Ling Hu, Lin Gui

机构 * School of Information Science and Technology, Beijing Foreign Studies University（信息科学与技术学院，北京外国语大学） ； Department of Informatics, King’s College London（信息学院，伦敦国王学院） 纠错

Comments Accepted by EMNLP 2025