EMNLP

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)