EMNLP

Large Language Models Have Intrinsic Meta-Cognition, but Need a Good Lens

Ziyang Ma, Qingyue Yuan, Zhenglin Wang, Deyu Zhou

机构 * School of Computer Science and Engineering, Key Laboratory of Computer Network and Information Integration, Ministry of Education, Southeast University, China（计算机科学与工程学院、计算机网络与信息集成重点实验室、教育部、东南大学，中国） ； Department of Neurosurgery, Shanghai Tenth People’s Hospital, School of Clinical Medicine of Nanjing Medical University, China（神经外科科、上海第十人民医院、南京医科大学临床医学学院，中国） 纠错

Comments Accepted to EMNLP 2025

Unstructured Evidence Attribution for Long Context Query Focused Summarization

Dustin Wright, Zain Muhammad Mujahid, Lu Wang, Isabelle Augenstein, David Jurgens

机构 * Department of Computer Science, University of Copenhagen（哥本哈根大学计算机科学系） ； Department of Computer Science and Engineering, University of Michigan（密歇根大学计算机科学与工程系） ； School of Information, University of Michigan（密歇根大学信息学院） 纠错

Comments EMNLP 2025 Main; 29 pages; 24 figures; 8 tables

Counterfactual-based Agent Influence Ranker for Agentic AI Workflows

Amit Giloni, Chiara Picardi, Roy Betser, Shamik Bose, Aishvariya Priya Rathina Sabapathy, Roman Vainshtein

机构 * Fujitsu Research of Europe, UK（富士通欧洲研究中心） 纠错

Comments Accepted to EMNLP 2025, 27 pages, 6 figures

LLMs are Better Than You Think: Label-Guided In-Context Learning for Named Entity Recognition

Fan Bai, Hamid Hassanzadeh, Ardavan Saeedi, Mark Dredze

机构 * Johns Hopkins University（约翰霍普金斯大学） ； Optum（奥普姆） 纠错

Comments Accepted to EMNLP 2025

Precise In-Parameter Concept Erasure in Large Language Models

Yoav Gur-Arieh, Clara Suslik, Yihuai Hong, Fazl Barez, Mor Geva

机构 * Blavatnik School of Computer Science and AI, Tel Aviv University（塔尔斯基大学计算机科学与人工智能学院） ； New York University（纽约大学） ； University of Oxford & WhiteBox（牛津大学及WhiteBox） 纠错

Comments Accepted to EMNLP 2025 Main Conference

Spontaneous Giving and Calculated Greed in Language Models

Yuxuan Li, Hirokazu Shirado

机构 * School of Computer Science Carnegie Mellon University（计算机科学学院卡内基梅隆大学） 纠错

Comments Accepted to EMNLP 2025 main conference and selected as an Oral Presentation

RLMEval: Evaluating Research-Level Neural Theorem Proving

Auguste Poiroux, Antoine Bosselut, Viktor Kunčak

Comments Accepted to EMNLP 2025 Findings. RLMEval benchmark released: https://github.com/augustepoiroux/RLMEval

Taming the Real-world Complexities in CPT E/M Coding with Large Language Models

Islam Nassar, Yang Lin, Yuan Jin, Rongxin Zhu, Chang Wei Tan, Zenan Zhai, Nitika Mathur, Thanh Tien Vu, Xu Zhong, Long Duong, Yuan-Fang Li

机构 * Oracle Health & AI（Oracle健康与人工智能） 纠错

Comments EMNLP 2025 Industry Track

Certainty in Uncertainty: Reasoning over Uncertain Knowledge Graphs with Statistical Guarantees

Yuqicheng Zhu, Jingcheng Wu, Yizhen Wang, Hongkuan Zhou, Jiaoyan Chen, Evgeny Kharlamov, Steffen Staab

机构 * University of Stuttgart（斯图加特大学） ； Bosch Center for AI（博世人工智能中心） ； The University of Manchester（曼彻斯特大学） ； University of Oslo（奥斯陆大学） ； University of Southampton（南安普顿大学） 纠错

Comments Accepted as a main conference paper at EMNLP 2025

Beyond Function-Level Search: Repository-Aware Dual-Encoder Code Retrieval with Adversarial Verification

Aofan Liu, Shiyuan Song, Haoxuan Li, Cehao Yang, Yiyan Qi

机构 * International Digital Economy Academy (IDEA)（国际数字经济学院） ； School of Electronic and Computer Engineering, Peking University（电子与计算机工程学院，北京大学） ； Shenzhen International Graduate School, Tsinghua University（深圳国际研究生院，清华大学） 纠错

Comments Accepted by EMNLP 2025

FT-MDT: Extracting Decision Trees from Medical Texts via a Novel Low-rank Adaptation Method

Yuheng Li, Jiechao Gao, Wei Han, Wenwen Ouyang, Wei Zhu, Hui Yi Leong

机构 * Johns Hopkins University（约翰霍普金斯大学） ； Stanford University（斯坦福大学） ； Carnegie Mellon University（卡内基梅隆大学） ； University of Hong Kong（香港大学） 纠错

Comments Accepted by EMNLP-2025

AMAS: Adaptively Determining Communication Topology for LLM-based Multi-Agent System

Hui Yi Leong, Yuheng Li, Yuqing Wu, Wenwen Ouyang, Wei Zhu, Jiechao Gao, Wei Han

机构 * Johns Hopkins University（约翰霍普金斯大学） ； Carnegie Mellon University（卡内基梅隆大学） ； University of Hong Kong（香港大学） ； Stanford University（斯坦福大学） 纠错

Comments Accepted by EMNLP-2025

UrduFactCheck: An Agentic Fact-Checking Framework for Urdu with Evidence Boosting and Benchmarking

Sarfraz Ahmad, Hasan Iqbal, Momina Ahsan, Numaan Naeem, Muhammad Ahsan Riaz Khan, Arham Riaz, Muhammad Arslan Manzoor, Yuxia Wang, Preslav Nakov

Comments 15 pages, 4 figures, 5 tables, 6 Listings, Published in Proceeding of The 2025 Conference on Empirical Methods in Natural Language Processing

OpenFactCheck: A Unified Framework for Factuality Evaluation of LLMs

Hasan Iqbal, Yuxia Wang, Minghan Wang, Georgi Georgiev, Jiahui Geng, Iryna Gurevych, Preslav Nakov

机构 * MBZUAI ； Monash University（墨尔本大学） ； Sofia University（索菲亚大学） 纠错

Comments 11 pages, 4 Figures, 3 Tables, Published In Proceedings of The 2024 Conference on Empirical Methods in Natural Language Processing

Journal ref In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 219-229, Miami, Florida, USA. Association for Computational Linguistics

Reliable Evaluation and Benchmarks for Statement Autoformalization

Auguste Poiroux, Gail Weiss, Viktor Kunčak, Antoine Bosselut

Comments Accepted to EMNLP 2025. New benchmarks released, see https://github.com/augustepoiroux/RLMEval , https://huggingface.co/datasets/PAug/ProofNetSharp , and https://huggingface.co/datasets/PAug/ProofNetVerif . For code, see https://github.com/augustepoiroux/LeanInteract

LongWeave: A Long-Form Generation Benchmark Bridging Real-World Relevance and Verifiability

Zikai Xiao, Fei Huang, Jianhong Tu, Jianhui Wei, Wen Ma, Yuxuan Zhou, Jian Wu, Bowen Yu, Zuozhu Liu, Junyang Lin

机构 * Zhejiang University（浙江大学） ； Alibaba Group（阿里巴巴集团） 纠错

Comments EMNLP Findings 2025

Arena-Lite: Efficient and Reliable Large Language Model Evaluation via Tournament-Based Direct Comparisons

Seonil Son, Ju-Min Oh, Heegon Jin, Cheolhun Jang, Jeongbeom Jeong, Kuntae Kim

机构 * NC AI ； RLWRLD Inc.（RLWRLD公司） ； Samsung AI Research（三星人工智能研究所） ； Global AI Platform（全球人工智能平台） ； Samsung Life Insurance（三星人寿保险） 纠错

Comments 8 pages for main body, 19 pages in total

Journal ref EMNLP 2025 Main

Can LLMs Narrate Tabular Data? An Evaluation Framework for Natural Language Representations of Text-to-SQL System Outputs

Jyotika Singh, Weiyi Sun, Amit Agarwal, Viji Krishnamurthy, Yassine Benajiba, Sujith Ravi, Dan Roth

机构 * Oracle AI 纠错

Comments Accepted at EMNLP 2025

PanicToCalm: A Proactive Counseling Agent for Panic Attacks

Jihyun Lee, Yejin Min, San Kim, Yejin Jeon, SungJun Yang, Hyounghun Kim, Gary Geunbae Lee

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

Comments Accepted in EMNLP 2025

Semantic Agreement Enables Efficient Open-Ended LLM Cascades

Duncan Soiffer, Steven Kolawole, Virginia Smith

机构 * Carnegie Mellon University（卡内基梅隆大学） 纠错

Comments 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP) Industry Track

AdaRewriter: Unleashing the Power of Prompting-based Conversational Query Reformulation via Test-Time Adaptation

Yilong Lai, Jialong Wu, Zhenglin Wang, Deyu Zhou

机构 * School of Computer Science and Engineering, Key Laboratory of Computer Network and Information Integration, Ministry of Education, Southeast University（计算机科学与工程学院、计算机网络与信息集成重点实验室、教育部、东南大学） 纠错

Comments Accepted by EMNLP 2025

LimRank: Less is More for Reasoning-Intensive Information Reranking

Tingyu Song, Yilun Zhao, Siyue Zhang, Chen Zhao, Arman Cohan

机构 * Yale NLP Lab（耶鲁大学自然语言处理实验室） 纠错

Comments EMNLP 2025 Main (Short)

Are LLMs Empathetic to All? Investigating the Influence of Multi-Demographic Personas on a Model's Empathy

Ananya Malik, Nazanin Sabri, Melissa Karnaze, Mai Elsherief

机构 * Northeastern University（东北大学） ； University of California, San Diego（加州大学圣地亚哥分校） 纠错

Comments 9 pages, 4 figures, 4 tables, EMNLP 2025 Findings

Superficial Self-Improved Reasoners Benefit from Model Merging

Xiangchi Yuan, Chunhui Zhang, Zheyuan Liu, Dachuan Shi, Leyan Pan, Soroush Vosoughi, Wenke Lee

机构 * Georgia Institute of Technology（佐治亚理工学院） ； Dartmouth College（达特茅斯学院） ； University of Notre Dame（诺丁汉大学） 纠错

Comments EMNLP 2025

Can Large Language Models Unlock Novel Scientific Research Ideas?

Sandeep Kumar, Tirthankar Ghosal, Vinayak Goyal, Asif Ekbal

机构 * Department of Computer Science and Engineering, Indian Institute of Technology Patna（计算机科学与工程系，印度理工学院帕纳布分校） ； National Center for Computational Sciences, Oak Ridge National Laboratory（计算科学国家中心，橡树岭国家实验室） 纠错

Comments EMNLP 2025 (Main)

Quality-Aware Translation Tagging in Multilingual RAG system

Hoyeon Moon, Byeolhee Kim, Nikhil Verma

机构 * Yonsei University（延世大学） ； University of Ulsan College of Medicine（釜山大学医学院） ； LG Electronics, Toronto AI Lab（LG电子，多伦多AI实验室） 纠错

Comments EMNLP 2025 MRL Workshop

Tagging-Augmented Generation: Assisting Language Models in Finding Intricate Knowledge In Long Contexts

Anwesan Pal, Karen Hovsepian, Tinghao Guo, Mengnan Zhao, Somendra Tripathi, Nikos Kanakaris, George Mihaila, Sumit Nigam

机构 * AWS AI Labs（AWS人工智能实验室） ； Amazon Web Services（亚马逊网络服务） ； Amazon OTS（亚马逊OTS） ； Amazon Catalog AI（亚马逊目录人工智能） 纠错

Comments Paper accepted at EMNLP 2025

VEHME: A Vision-Language Model For Evaluating Handwritten Mathematics Expressions

Thu Phuong Nguyen, Duc M. Nguyen, Hyotaek Jeon, Hyunwook Lee, Hyunmin Song, Sungahn Ko, Taehwan Kim

Comments EMNLP 2025. Project Website: https://vehme.github.io/

Dynamic Retriever for In-Context Knowledge Editing via Policy Optimization

Mahmud Wasif Nafee, Maiqi Jiang, Haipeng Chen, Yanfu Zhang

机构 * Rensselaer Polytechnic Institute（拉特格斯理工学院） ； Bangladesh University of Engineering and Technology（孟加拉工程与技术大学） ； College of William & Mary（威廉与玛丽学院） 纠错

Comments Accepted at EMNLP 2025. Copyright 2025 Association for Computational Linguistics (CC BY 4.0). 12 pages, 5 figures

Aligning LLMs for Multilingual Consistency in Enterprise Applications

Amit Agarwal, Hansa Meghwani, Hitesh Laxmichand Patel, Tao Sheng, Sujith Ravi, Dan Roth

机构 * Oracle AI 纠错

Comments Accepted at EMNLP 2025