EMNLP

Towards Robust Mathematical Reasoning

Thang Luong, Dawsen Hwang, Hoang H. Nguyen, Golnaz Ghiasi, Yuri Chervonyi, Insuk Seo, Junsu Kim, Garrett Bingham, Jonathan Lee, Swaroop Mishra, Alex Zhai, Clara Huiyi Hu, Henryk Michalewski, Jimin Kim, Jeonghyun Ahn, Junhwi Bae, Xingyou Song, Trieu H. Trinh, Quoc V. Le, Junehyuk Jung

机构 * Georgia Institute of Technology（佐治亚理工学院） ； Seoul National University（首尔国立大学） ； Microsoft（微软） ； Massachusetts Institute of Technology（麻省理工学院） ； Brown University（布朗大学） 纠错

Comments EMNLP 2025 (main conference), https://aclanthology.org/2025.emnlp-main.1794/

Efficient Tool-Calling Multi-Expert NPC Agent for Commonsense Persona-Grounded Dialogue

Mahammad Nuriyev

机构 * Université Paris-Saclay（巴黎-萨克雷大学） 纠错

Comments 10 pages, 1 figure, 2 tables. Technical report for the Commonsense Persona-Grounded Dialogue Challenge (CPDC) 2025, part of the Wordplay 2025 Workshop @ EMNLP 2025

BIRD: Bronze Inscription Restoration and Dating

Wenjie Hua, Hoang H. Nguyen, Gangyan Ge

机构 * Wuhan University（武汉大学） ； University of Illinois, Chicago（伊利诺伊大学芝加哥分校） ； Xinjiang University（新疆大学） 纠错

Comments Accepted at EMNLP 2025 (Main Conference)

ECO Decoding: Entropy-Based Control for Controllability and Fluency in Controllable Dialogue Generation

Seungmin Shin, Dooyoung Kim, Youngjoong Ko

机构 * SungKyunKwan University（顺 Kyun 島大学） 纠错

Comments Published at EMNLP 2025 main

Confounding Factors in Relating Model Performance to Morphology

Wessel Poelman, Thomas Bauwens, Miryam de Lhoneux

机构 * NLP, Department of Computer Science, KU Leuven（自然语言处理，计算机科学系，鲁文大学） 纠错

Comments EMNLP 2025: Main Conference

Thinking with DistilQwen: A Tale of Four Distilled Reasoning and Reward Model Series

Wenrui Cai, Chengyu Wang, Junbing Yan, Jun Huang, Xiangzhong Fang

机构 * Shanghai Jiao Tong University（上海交通大学） ； Alibaba Cloud Computing（阿里云计算） 纠错

Comments emnlp 2025 industry track

Enhancing Time Awareness in Generative Recommendation

Sunkyung Lee, Seongmin Park, Jonghyo Kim, Mincheol Yoon, Jongwuk Lee

Comments EMNLP 2025 (Findings)

Teaching According to Talents! Instruction Tuning LLMs with Competence-Aware Curriculum Learning

Yangning Li, Tingwei Lu, Yinghui Li, Yankai Chen, Wei-Chieh Huang, Wenhao Jiang, Hui Wang, Hai-Tao Zheng, Philip S. Yu

机构 * Tsinghua University（清华大学） ； Peng Cheng Laboratory（鹏城实验室） ； Cornell University（康奈尔大学） ； University of Illinois Chicago（伊利诺伊大学芝加哥分校） ； Guangming Laboratory（光明实验室） 纠错

Comments EMNLP 2025 Findings

Trustworthy Medical Question Answering: An Evaluation-Centric Survey

Yinuo Wang, Baiyang Wang, Robert E. Mercer, Frank Rudzicz, Sudipta Singha Roy, Pengjie Ren, Zhumin Chen, Xindi Wang

机构 * Shandong University（山东大学） ； University of Western Ontario（西方大学） ； Dalhousie University（达尔豪斯大学） ； University of Toronto（多伦多大学） 纠错

Comments accepted to EMNLP 2025

From Grounding to Manipulation: Case Studies of Foundation Model Integration in Embodied Robotic Systems

Xiuchao Sui, Daiying Tian, Qi Sun, Ruirui Chen, Dongkyu Choi, Kenneth Kwok, Soujanya Poria

机构 * IHPC, Agency for Science, Technology and Research, Singapore（科技研究局智能技术中心，新加坡） ； Nanyang Technological University, Singapore（南洋理工大学，新加坡） 纠错

Comments EMNLP 2025 camera ready

Enhancing Reasoning Abilities of Small LLMs with Cognitive Alignment

Wenrui Cai, Chengyu Wang, Junbing Yan, Jun Huang, Xiangzhong Fang

机构 * Shanghai Jiao Tong University（上海交通大学） ； Alibaba Cloud Computing（阿里云计算） 纠错

Comments emnlp 2025 main conference

Assessing LLM Reasoning Steps via Principal Knowledge Grounding

Hyeon Hwang, Yewon Cho, Chanwoong Yoon, Yein Park, Minju Song, Kyungjae Lee, Gangwoo Kim, Jaewoo Kang

机构 * Korea University（韩国大学） ； University of Seoul（首尔大学） ； AWS AI Labs（AWS人工智能实验室） ； AIGEN Sciences（AIGEN科学） 纠错

Comments Accepted to EMNLP 2025 Findings

Do You Know About My Nation? Investigating Multilingual Language Models' Cultural Literacy Through Factual Knowledge

Eshaan Tanwar, Anwoy Chatterjee, Michael Saxon, Alon Albalak, William Yang Wang, Tanmoy Chakraborty

机构 * Indian Institute of Technology Delhi（印度理工学院德里） ； University of Washington（华盛顿大学） ； Lila Sciences（Lila科学） ； University of California, Santa Barbara（加州大学圣芭芭拉分校） 纠错

Comments Accepted in EMNLP 2025. Code at: https://github.com/EshaanT/XNationQA

Certain but not Probable? Differentiating Certainty from Probability in LLM Token Outputs for Probabilistic Scenarios

Autumn Toney-Wails, Ryan Wails

机构 * SciTech Strategies, Inc.（SciTech Strategies公司） ； Georgetown University（乔治城大学） 纠错

Comments To appear at the Second Workshop on Uncertainty-Aware NLP @EMNLP 2025 (UncertaiNLP '25)

ToM: Leveraging Tree-oriented MapReduce for Long-Context Reasoning in Large Language Models

Jiani Guo, Zuchao Li, Jie Wu, Qianren Wang, Yun Li, Lefei Zhang, Hai Zhao, Yujiu Yang

机构 * School of Computer Science, Wuhan University, Wuhan, China（武汉大学计算机学院） ； School of Artificial Intelligence, Wuhan University, Wuhan, China（武汉大学人工智能学院） ； Tsinghua University（清华大学） ； Cognitive AI Lab（认知人工智能实验室） ； School of Computer Science, Shanghai Jiao Tong University, Shanghai, China（上海交通大学计算机学院） 纠错

Comments EMNLP 2025 Main Conference

Leveraging the Cross-Domain & Cross-Linguistic Corpus for Low Resource NMT: A Case Study On Bhili-Hindi-English Parallel Corpus

Pooja Singh, Shashwat Bhardwaj, Vaibhav Sharma, Sandeep Kumar

机构 * Department of Electrical Engineering, Indian Institute of Technology Delhi（电子工程系，印度理工学院德里） ； Bharti School of Telecommunication, Indian Institute of Technology Delhi（电信学院，印度理工学院德里） ； Yardi School of Artificial Intelligence, Indian Institute of Technology Delhi（人工智能学院，印度理工学院德里） 纠错

Comments Accepted in EMNLP 2025

G2: Guided Generation for Enhanced Output Diversity in LLMs

Zhiwen Ruan, Yixia Li, Yefeng Liu, Yun Chen, Weihua Luo, Peng Li, Yang Liu, Guanhua Chen

机构 * Southern University of Science and Technology（南方科技大学） ； Tsinghua University（清华大学） ； Shanghai University of Finance and Economics（上海财经大学） ； Alibaba International Digital Commerce（阿里巴巴国际数字商业） 纠错

Comments EMNLP 2025

LingGym: How Far Are LLMs from Thinking Like Field Linguists?

Changbing Yang, Franklin Ma, Freda Shi, Jian Zhu

机构 * University of British Columbia（不列颠哥伦比亚大学） ； University of Waterloo（滑铁卢大学） ； Vector Institute（向量研究所） 纠错

Comments EMNLP 2025 Main

Calibration Across Layers: Understanding Calibration Evolution in LLMs

Abhinav Joshi, Areeb Ahmad, Ashutosh Modi

机构 * Department of Computer Science and Engineering（计算机科学与工程系） ； Indian Institute of Technology Kanpur (IIT Kanpur)（印度理工学院坎浦尔（IIT坎浦尔）） 纠错

Comments Accepted at EMNLP 2025 (main)

POSESTITCH-SLT: Linguistically Inspired Pose-Stitching for End-to-End Sign Language Translation

Abhinav Joshi, Vaibhav Sharma, Sanjeet Singh, Ashutosh Modi

机构 * Department of Computer Science and Engineering（计算机科学与工程系） ； Indian Institute of Technology Kanpur (IIT Kanpur)（印度理工学院坎浦尔学院（IIT坎浦尔）） 纠错

Comments Accepted at EMNLP 2025 (Main)

IL-PCSR: Legal Corpus for Prior Case and Statute Retrieval

Shounak Paul, Dhananjay Ghumare, Pawan Goyal, Saptarshi Ghosh, Ashutosh Modi

机构 * IIT Kharagpur（印度克哈格普尔理工学院） ； IIT Kanpur（印度坎普尔理工学院） 纠错

Comments Accepted at EMNLP 2025 (Main)

Comprehensive and Efficient Distillation for Lightweight Sentiment Analysis Models

Guangyu Xie, Yice Zhang, Jianzhu Bao, Qianlong Wang, Yang Sun, Bingbing Wang, Ruifeng Xu

机构 * Harbin Institute of Technology（哈尔滨工业大学） ； Peng Cheng Laboratory（鹏城实验室） ； Nanyang Technological University（南洋理工大学） 纠错

Comments Accepted by EMNLP 2025. 22 pages, 9 figures. The first two authors contribute equally

Computational Analysis of Conversation Dynamics through Participant Responsivity

Margaret Hughes, Brandon Roy, Elinor Poole-Dayan, Deb Roy, Jad Kabbara

机构 * MIT Center for Constructive Communication（麻省理工学院建设性沟通中心） ； Massachusetts Institute of Technology（麻省理工学院） 纠错

Journal ref Proc. EMNLP (2025) 35500--35519

Beyond Pointwise Scores: Decomposed Criteria-Based Evaluation of LLM Responses

Fangyi Yu, Nabeel Seedat, Dasha Herrmannova, Frank Schilder, Jonathan Richard Schwarz

机构 * Thomson Reuters Foundational Research（汤姆森·路透基础研究） ； Thomson Reuters Labs（汤姆森·路透实验室） ； Imperial College London（帝国理工学院伦敦分校） 纠错

Comments Accepted by 2025 EMNLP industry track

SynthTextEval: Synthetic Text Data Generation and Evaluation for High-Stakes Domains

Krithika Ramesh, Daniel Smolyak, Zihao Zhao, Nupoor Gandhi, Ritu Agarwal, Margrét Bjarnadóttir, Anjalie Field

机构 * Johns Hopkins University（约翰霍普金斯大学） ； University of Maryland, College Park（马里兰大学学院公园分校） ； Carnegie Mellon University（卡内基梅隆大学） 纠错

Comments EMNLP 2025 System Demonstration

AnyMAC: Cascading Flexible Multi-Agent Collaboration via Next-Agent Prediction

Song Wang, Zhen Tan, Zihan Chen, Shuang Zhou, Tianlong Chen, Jundong Li

机构 * University of Virginia（弗吉尼亚大学） ； Arizona State University（亚利桑那州立大学） ； University of Minnesota Twin Cities（明尼苏达大学双城分校） ； University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校） 纠错

Comments EMNLP Main 2025

MultiMatch: Multihead Consistency Regularization Matching for Semi-Supervised Text Classification

Iustin Sirbu, Robert-Adrian Popovici, Cornelia Caragea, Stefan Trausan-Matu, Traian Rebedea

机构 * National University of Science and Technology POLITEHNICA Bucharest（波兰技术大学科学与技术国立大学） ； University of Illinois Chicago（伊利诺伊大学芝加哥分校） ； NVIDIA（NVIDIA公司） ； Renius Technologies（Renius技术公司） 纠错

Comments This is the camera-ready version of the paper, accepted for publication in the Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP 2025)

A Closer Look at Bias and Chain-of-Thought Faithfulness of Large (Vision) Language Models

Sriram Balasubramanian, Samyadeep Basu, Soheil Feizi

机构 * Department of Computer Science University of Maryland, College Park（计算机科学系马里兰大学 College Park） 纠错

Comments Accepted in EMNLP 2025, 34 pages, 25 figures

GreekBarBench: A Challenging Benchmark for Free-Text Legal Reasoning and Citations

Odysseas S. Chlapanis, Dimitrios Galanis, Nikolaos Aletras, Ion Androutsopoulos

机构 * Department of Informatics, Athens University of Economics and Business（信息学院，雅典经济与商业大学） ； Archimedes, Athena Research Center（阿提卡研究中心-阿基米德） ； Athena Research Center（阿提卡研究中心） ； University of Sheffield（谢菲尔德大学） 纠错

Comments 19 pages, 17 figures, accepted in EMNLP 2025

Editing Across Languages: A Survey of Multilingual Knowledge Editing

Nadir Durrani, Basel Mousi, Fahim Dalvi

机构 * Qatar Computing Research Institute, HBKU（卡塔尔计算研究所，哈姆扎大学） 纠错

Comments Accepted at EMNLP 2025