EMNLP

LogicTree: Structured Proof Exploration for Coherent and Rigorous Logical Reasoning with Large Language Models

Kang He, Kaushik Roy

机构 * Electrical and Computer Engineering, Purdue University（电子与计算机工程系，普渡大学） 纠错

Comments EMNLP 2025 Main Conference

DSMoE: Matrix-Partitioned Experts with Dynamic Routing for Computation-Efficient Dense LLMs

Minxuan Lv, Zhenpeng Su, Leiyu Pan, Yizhe Xiong, Zijia Lin, Hui Chen, Wei Zhou, Jungong Han, Guiguang Ding, Cheng Luo, Di Zhang, Kun Gai, Songlin Hu

机构 * Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所） ； University of Chinese Academy of Sciences（中国科学院大学） ； Kuaishou Technology（快手科技） ； Tianjin University（天津大学） ； Tsinghua University（清华大学） 纠错

Comments Accepted by EMNLP main conference

From Personas to Talks: Revisiting the Impact of Personas on LLM-Synthesized Emotional Support Conversations

Shenghan Wu, Yimo Zhu, Wynne Hsu, Mong-Li Lee, Yang Deng

机构 * National University of Singapore（国立新加坡大学） ； Singapore Management University（新加坡管理大学） 纠错

Comments Accepted by EMNLP 2025 Main Conference

FM2DS: Few-Shot Multimodal Multihop Data Synthesis with Knowledge Distillation for Question Answering

Amirhossein Abaskohi, Spandana Gella, Giuseppe Carenini, Issam H. Laradji

机构 * Department of Computer Science（计算机科学系） ； The University of British Columbia（不列颠哥伦比亚大学） ； ServiceNow Research（ServiceNow研究） 纠错

Comments Findings of EMNLP 2025

LATTE: Learning to Think with Vision Specialists

Zixian Ma, Jianguo Zhang, Zhiwei Liu, Jieyu Zhang, Juntao Tan, Manli Shu, Juan Carlos Niebles, Shelby Heinecke, Huan Wang, Caiming Xiong, Ranjay Krishna, Silvio Savarese

机构 * University of Washington（华盛顿大学） ； Salesforce Research（Salesforce研究） 纠错

Journal ref EMNLP 2025

Evaluating Automatic Speech Recognition Systems for Korean Meteorological Experts

ChaeHun Park, Hojun Cho, Jaegul Choo

机构 * KAIST AI（韩国国立信息科学院人工智能研究所） 纠错

Comments EMNLP 2025 Findings

Revealing the Inherent Instructability of Pre-Trained Language Models

Seokhyun An, Minji Kim, Hyounghun Kim

机构 * Department of Computer Science and Engineering, UNIST（UNIST计算机科学与工程系） ； Graduate School of Artificial Intelligence, POSTECH（POSTECH人工智能研究生院） ； Department of Computer Science and Engineering, POSTECH（POSTECH计算机科学与工程系） 纠错

Comments Findings of EMNLP 2025 (32 pages). Code available at https://github.com/seokhyunan/response-tuning

FairCoT: Enhancing Fairness in Text-to-Image Generation via Chain of Thought Reasoning with Multimodal Large Language Models

Zahraa Al Sahili, Ioannis Patras, Matthew Purver

机构 * School of Electronic Engineering and Computer Science, Queen Mary University of London（伦敦女王学院电子工程与计算机科学学院） ； Department of Knowledge Technologies, Jožef Stefan Institute（Jožef Stefan研究所知识技术系） 纠错

Comments Accepted at EMNLP 2025

!MSA at BAREC Shared Task 2025: Ensembling Arabic Transformers for Readability Assessment

Mohamed Basem, Mohamed Younes, Seif Ahmed, Abdelrahman Moustafa

机构 * Faculty of Computer Science, MSA University（计算机科学学院，MSA大学） 纠错

Comments 10 Pages , 8 figures , ArabicNLP 2025 , Co-located with EMNLP 2025

Unsupervised Hallucination Detection by Inspecting Reasoning Processes

Ponhvoan Srey, Xiaobao Wu, Anh Tuan Luu

机构 * Nanyang Technological University（南洋理工大学） 纠错

Comments To appear in EMNLP 2025

Reframe Your Life Story: Interactive Narrative Therapist and Innovative Moment Assessment with Large Language Models

Yi Feng, Jiaqi Wang, Wenxuan Zhang, Zhuang Chen, Yutong Shen, Xiyao Xiao, Minlie Huang, Liping Jing, Jian Yu

机构 * Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence（北京交通大数据挖掘与具身智能重点实验室） ； Beijing Jiaotong University（北京交通大学） ； CoAI Group（CoAI集团） ； DCST（国防科技大学） ； IAI（人工智能院） ； BNRIST（北航机器人与智能技术研究院） ； Tsinghua University（清华大学） ； Tencent Jarvis Lab（腾讯Jarvis实验室） ； Singapore University of Technology and Design（新加坡科技与设计大学） ； Central South University（中南大学） ； Lingxin AI（灵犀AI） 纠错

Comments EMNLP 2025 Main

Comparing Apples to Oranges: A Dataset & Analysis of LLM Humour Understanding from Traditional Puns to Topical Jokes

Tyler Loakman, William Thorne, Chenghua Lin

机构 * Department of Computer Science, The University of Sheffield, UK（谢菲尔德大学计算机科学系） ； Department of Computer Science, The University of Manchester, UK（曼彻斯特大学计算机科学系） 纠错

Comments Accepted to Findings of EMNLP 2025

Alignment-Augmented Speculative Decoding with Alignment Sampling and Conditional Verification

Jikai Wang, Zhenxu Tian, Juntao Li, Qingrong Xia, Xinyu Duan, Zhefeng Wang, Baoxing Huai, Min Zhang

机构 * Soochow University（苏州大学） ； Key Laboratory of Data Intelligence and Advanced Computing, Soochow University（数据智能与先进计算关键实验室） ； Huawei Cloud（华为云） 纠错

Comments Accepted at EMNLP 2025 Main

FinMTEB: Finance Massive Text Embedding Benchmark

Yixuan Tang, Yi Yang

Comments EMNLP 2025, https://github.com/yixuantt/FinMTEB

Router-Tuning: A Simple and Effective Approach for Enabling Dynamic-Depth in Transformers

Shwai He, Tao Ge, Guoheng Sun, Bowei Tian, Xiaoyang Wang, Dong Yu

机构 * University of Maryland, College Park（马里兰大学 College Park 分校） ； Tencent AI Lab（腾讯AI实验室） 纠错

Comments EMNLP 2025 Main Conference

Direct Judgement Preference Optimization

Peifeng Wang, Austin Xu, Yilun Zhou, Caiming Xiong, Shafiq Joty

Comments EMNLP 2025

All for One: LLMs Solve Mental Math at the Last Token With Information Transferred From Other Tokens

Siddarth Mamidanna, Daking Rai, Ziyu Yao, Yilun Zhou

机构 * University of California, Santa Cruz（加州大学圣克鲁兹分校） ； George Mason University（乔治·马歇尔大学） ； Datadog AI Research（Datadog人工智能研究） 纠错

Comments EMNLP 2025 Main Conference

Bridging the Capability Gap: Joint Alignment Tuning for Harmonizing LLM-based Multi-Agent Systems

Minghang Zhu, Zhengliang Shi, Zhiwei Xu, Shiguang Wu, Lingjie Wang, Pengjie Ren, Zhaochun Ren, Zhumin Chen

机构 * Shandong University（山东大学） ； Leiden University（莱顿大学） 纠错

Comments EMNLP 2025 Findings

DeMeVa at LeWiDi-2025: Modeling Perspectives with In-Context Learning and Label Distribution Learning

Daniil Ignatev, Nan Li, Hugh Mee Wong, Anh Dang, Shane Kaszefski Yaschuk

机构 * Utrecht University（乌特雷赫大学） 纠错

Comments 11 pages, 4 figures; to appear at NLPerspectives@EMNLP-2025

Boosting Data Utilization for Multilingual Dense Retrieval

Chao Huang, Fengran Mo, Yufeng Chen, Changhao Guan, Zhenrui Yue, Xinyu Wang, Jinan Xu, Kaiyu Huang

Comments Accepted by EMNLP 2025 (main)

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations

Harry Mayne, Ryan Othniel Kearns, Yushi Yang, Andrew M. Bean, Eoin Delaney, Chris Russell, Adam Mahdi

机构 * University of Oxford（牛津大学） ； Trinity College Dublin（都柏林三一学院） 纠错

Comments Accepted to EMNLP 2025 Main

Hierarchical Bracketing Encodings Work for Dependency Graphs

Ana Ezquerro, Carlos Gómez-Rodríguez, David Vilares

机构 * Universidade da Coruña, CITIC Departamento de Ciencias de la Computación y Tecnologías de la Información（乌拉圭科鲁纳大学，CITIC计算机科学与信息技术系） 纠错

Comments Accepted at EMNLP 2025 (main)

Improving Alignment in LVLMs with Debiased Self-Judgment

Sihan Yang, Chenhang Cui, Zihao Zhao, Yiyang Zhou, Weilong Yan, Ying Wei, Huaxiu Yao

机构 * Nanyang Technological University（南洋理工大学） ； National University of Singapore（新加坡国立大学） ； UNC-Chapel Hill（北卡罗来纳大学教堂山分校） 纠错

Comments EMNLP 2025 Findings

Can Vision-Language Models Solve Visual Math Equations?

Monjoy Narayan Choudhury, Junling Wang, Yifan Hou, Mrinmaya Sachan

机构 * IIIT Bangalore（班加罗尔印度理工学院） ； ETH Zürich（苏黎世联邦理工学院） 纠错

Comments Monjoy Narayan Choudhury and Junling Wang contributed equally to this work. Accepted at EMNLP2025 main. Code and datasets are open-sourced with links in the paper

Journal ref Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing

POW: Political Overton Windows of Large Language Models

Leif Azzopardi, Yashar Moshfeghi

Comments Accepted in EMNLP 2025

MIND: Towards Immersive Psychological Healing with Multi-agent Inner Dialogue

Yujia Chen, Changsong Li, Yiming Wang, Tianjie Ju, Qingqing Xiao, Nan Zhang, Zifan Kong, Peng Wang, Binyu Yan

机构 * Sichuan University（四川大学） ； Shanghai Jiao Tong University（上海交通大学） ； Mental Health Center, West China Hospital, Sichuan University（四川大学西昌医院心理健康中心） ； WestChina School of Nursing, Sichuan University（四川大学西昌护理学院） ； National University of Singapore（新加坡国立大学） 纠错

Comments Accepted by EMNLP 2025 Findings

SimMark: A Robust Sentence-Level Similarity-Based Watermarking Algorithm for Large Language Models

Amirhossein Dabiriaghdam, Lele Wang

机构 * Department of ECE, University of British Columbia（电子工程系，不列颠哥伦比亚大学） 纠错

Comments Accepted to EMNLP 25 main

CondAmbigQA: A Benchmark and Dataset for Conditional Ambiguous Question Answering

Zongxi Li, Yang Li, Haoran Xie, S. Joe Qin

机构 * School of Data Science, Lingnan University（数据科学学院） ； School of Science and Technology, Hong Kong Metropolitan University（科技学院） 纠错

Comments Accepted by EMNLP 2025 (Main Conference)

Do All Autoregressive Transformers Remember Facts the Same Way? A Cross-Architecture Analysis of Recall Mechanisms

Minyeong Choe, Haehyun Cho, Changho Seo, Hyunil Kim

机构 * Chosun University（全州大学） ； Soongsil University（顺天大学） ； Kongju National University（康州国立大学） 纠错

Comments Accepted at EMNLP 2025

Simulating Identity, Propagating Bias: Abstraction and Stereotypes in LLM-Generated Text

Pia Sommerauer, Giulia Rambelli, Tommaso Caselli

机构 * Computational Linguistics and Text Mining Lab, Vrije Universiteit, Amsterdam（自由大学计算语言学与文本挖掘实验室） ； Università di Bologna（博洛尼亚大学） ； CLCG, University of Groningen（格罗宁根大学CLCG） 纠错

Comments Accepted to EMNLP Findings 2025