EMNLP

Efficient Prompt Optimisation for Legal Text Classification with Proxy Prompt Evaluator

Hyunji Lee, Kevin Chenhao Li, Matthias Grabmair, Shanshan Xu

机构 * Technical University of Munich（慕尼黑技术大学） ； Department of Computer Science, University of Copenhagen（哥本哈根大学计算机科学系） ； Faculty of Law, University of Copenhagen（哥本哈根大学法学院） 纠错

Comments Accepted at NLLP@EMNLP 2025

Looking to Learn: Token-wise Dynamic Gating for Low-Resource Vision-Language Modelling

Bianca-Mihaela Ganescu, Suchir Salhan, Andrew Caines, Paula Buttery

机构 * ALTA Institute（ALTA研究院） ； Department of Computer Science & Technology, University of Cambridge（计算机科学与技术系，剑桥大学） 纠错

Comments Accepted to the EMNLP 2025 BabyLM Workshop

DACIP-RC: Domain Adaptive Continual Instruction Pre-Training via Reading Comprehension on Business Conversations

Elena Khasanova, Harsh Saini, Md Tahmid Rahman Laskar, Xue-Yong Fu, Cheng Chen, Shashi Bhushan TN

机构 * Dialpad Inc.（Dialpad公司） 纠错

Comments Accepted to the EMNLP 2025 Industry Track. Equal contribution from the first four authors

AI Knowledge Assist: An Automated Approach for the Creation of Knowledge Bases for Conversational AI Agents

Md Tahmid Rahman Laskar, Julien Bouvier Tremblay, Xue-Yong Fu, Cheng Chen, Shashi Bhushan TN

机构 * Dialpad Inc.（Dialpad公司） 纠错

Comments Accepted to the EMNLP 2025 Industry Track

DACP: Domain-Adaptive Continual Pre-Training of Large Language Models for Phone Conversation Summarization

Xue-Yong Fu, Elena Khasanova, Md Tahmid Rahman Laskar, Harsh Saini, Shashi Bhushan TN

机构 * Dialpad Inc.（Dialpad公司） 纠错

Comments Accepted to the NewSumm Workshop at EMNLP 2025. Equal contribution from the first four authors

Scaling Laws Are Unreliable for Downstream Tasks: A Reality Check

Nicholas Lourie, Michael Y. Hu, Kyunghyun Cho

机构 * New York University（纽约大学） ； Prescient Design ； CIFAR LMB 纠错

Comments EMNLP Findings 2025 Camera Ready

Dissecting Logical Reasoning in LLMs: A Fine-Grained Evaluation and Supervision Study

Yujun Zhou, Jiayi Ye, Zipeng Ling, Yufei Han, Yue Huang, Haomin Zhuang, Zhenwen Liang, Kehan Guo, Taicheng Guo, Xiangqi Wang, Xiangliang Zhang

机构 * University of Notre Dame（诺丁汉大学） ； MBZUAI（马克斯·普朗克人工智能研究所） ； University of Pennsylvania（宾夕法尼亚大学） ； INRIA（法国国家信息与自动化研究所） 纠错

Comments Accepted by the Findings of EMNLP 2025

T-VEC: A Telecom-Specific Vectorization Model with Enhanced Semantic Understanding via Deep Triplet Loss Fine-Tuning

Vignesh Ethiraj, Ashwath David, Sidhanth Menon, Divya Vijay, Vidhyakshaya Kannan

机构 * NetoAI 纠错

Comments Accepted to EMNLP 2025 (Industry Track)

Evaluating LLM-Generated Legal Explanations for Regulatory Compliance in Social Media Influencer Marketing

Haoyang Gui, Thales Bertaglia, Taylor Annabell, Catalina Goanta, Tjomme Dooper, Gerasimos Spanakis

机构 * Utrecht University（乌特雷赫大学） ； Stichting Reclame Code（Reclame Code基金会） ； Maastricht University（马斯特里赫特大学） 纠错

Comments Accepted for publication at the Natural Legal Language Processing Workshop (NLLP) 2025, co-located with EMNLP

AutoQual: An LLM Agent for Automated Discovery of Interpretable Features for Review Quality Assessment

Xiaochong Lan, Jie Feng, Yinxing Liu, Xinlei Shi, Yong Li

机构 * Department of Electronic Engineering, BNRist, Tsinghua University（电子工程系、百度研究院、清华大学） 纠错

Comments EMNLP 2025

STEPER: Step-wise Knowledge Distillation for Enhancing Reasoning Ability in Multi-Step Retrieval-Augmented Language Models

Kyumin Lee, Minjin Jeon, Sanghwan Jang, Hwanjo Yu

Comments EMNLP 2025 Main

Multilingual Generative Retrieval via Cross-lingual Semantic Compression

Yuxin Huang, Simeng Wu, Ran Song, Yan Xiang, Yantuan Xian, Shengxiang Gao, Zhengtao Yu

机构 * Faculty of Information Engineering and Automation, Kunming University of Science and Technology（信息工程与自动化学院，昆明理工大学） ； Yunnan Key Laboratory of Artificial Intelligence（云南省人工智能重点实验室） 纠错

Comments EMNLP 2025, Findings, Long

Multilingual Knowledge Graph Completion via Efficient Multilingual Knowledge Sharing

Cunli Mao, Xiaofei Gao, Ran Song, Shizhu He, Shengxiang Gao, Kang Liu, Zhengtao Yu

机构 * Faculty of Information Engineering and Automation, Kunming University of Science and Technology（昆明理工大学信息工程与自动化学院） ； Yunnan Key Laboratory of Artificial Intelligence（云南人工智能重点实验室） ； The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences（复杂系统认知与决策智能重点实验室，中国科学院自动化研究所） ； School of Artificial Intelligence, University of Chinese Academy of Science（中国科学院大学人工智能学院） 纠错

Comments EMNLP 2025, Findings, Long Paper

Multi-Task Pre-Finetuning of Lightweight Transformer Encoders for Text Classification and NER

Junyi Zhu, Savas Ozkan, Andrea Maracani, Sinan Mutlu, Cho Jung Min, Mete Ozay

机构 * Samsung R&D Institute UK (SRUK)（三星英国研发中心（SRUK）） ； Samsung Electronics Korea（三星电子韩国） 纠错

Comments Accepted by EMNLP 2025 Industry Track

LASER: An LLM-based ASR Scoring and Evaluation Rubric

Amruta Parulekar, Preethi Jyothi

机构 * Indian Institute of Technology Bombay（印度理工学院班加罗尔） 纠错

Comments Accepted to EMNLP 2025

Lemma Dilemma: On Lemma Generation Without Domain- or Language-Specific Training Data

Olia Toporkov, Alan Akbik, Rodrigo Agerri

机构 * HiTZ Center - Ixa, University of the Basque Country UPV/EHU（巴斯克大学希茨中心 - Ixa，巴斯克国家大学UPV/EHU） ； Humboldt-Universität zu Berlin（柏林洪堡大学） 纠错

Comments 14 pages, 2 figures, 5 tables. Accepted to EMNLP Findings 2025

Incremental Summarization for Customer Support via Progressive Note-Taking and Agent Feedback

Yisha Wu, Cen Mia Zhao, Yuanpei Cao, Xiaoqing Su, Yashar Mehdad, Mindy Ji, Claire Na Cheng

机构 * Airbnb Inc.（Airbnb公司） 纠错

Comments Accepted at EMNLP 2025 Industry Track

Agent-in-the-Loop: A Data Flywheel for Continuous Improvement in LLM-based Customer Support

Cen Mia Zhao, Tiantian Zhang, Hanchen Su, Yufeng Wayne Zhang, Shaowei Su, Mingzhi Xu, Yu Elaine Liu, Wei Han, Jeremy Werner, Claire Na Cheng, Yashar Mehdad

机构 * Airbnb, Inc.（Airbnb公司） 纠错

Comments EMNLP 2025 Industry Track submission (Paper #305). Preprint. Main text within the 7-page industry limit (references/appendices excluded). Contains multiple figures and tables

SimulatorArena: Are User Simulators Reliable Proxies for Multi-Turn Evaluation of AI Assistants?

Yao Dou, Michel Galley, Baolin Peng, Chris Kedzie, Weixin Cai, Alan Ritter, Chris Quirk, Wei Xu, Jianfeng Gao

Comments Accepted at EMNLP 2025 Main

Training LLMs to be Better Text Embedders through Bidirectional Reconstruction

Chang Su, Dengliang Shi, Siyuan Huang, Jintao Du, Changhua Meng, Yu Cheng, Weiqiang Wang, Zhouhan Lin

机构 * LUMIA Lab, Shanghai Jiao Tong University（上海交通大学LUMIA实验室） ； Tiansuan Lab, Ant Group Co., Ltd.（蚂蚁集团天算实验室） ； LUMIA Lab, School of Artificial Intelligence, Shanghai Jiao Tong University（上海交通大学人工智能学院LUMIA实验室） 纠错

Comments accepted by EMNLP 2025 Main Conference

MAGIC: A Multi-Hop and Graph-Based Benchmark for Inter-Context Conflicts in Retrieval-Augmented Generation

Jungyeon Lee, Kangmin Lee, Taeuk Kim

机构 * Hanyang University（翰阳大学） ； KT Corporation（KT公司） 纠错

Comments EMNLP 2025 Findings

From Feedback to Checklists: Grounded Evaluation of AI-Generated Clinical Notes

Karen Zhou, John Giorgi, Pranav Mani, Peng Xu, Davis Liang, Chenhao Tan

机构 * University of Chicago（芝加哥大学） ； Abridge 纠错

Comments Accepted to EMNLP 2025 Industry Track

Efficiency-Effectiveness Reranking FLOPs for LLM-based Rerankers

Zhiyuan Peng, Ting-ruen Wei, Tingyu Song, Yilun Zhao

机构 * Santa Clara University（圣克拉拉大学） ； Yale University（耶鲁大学） 纠错

Comments Accepted by EMNLP Industry Track 2025

LLMs on a Budget? Say HOLA

Zohaib Hasan Siddiqui, Jiechao Gao, Ebad Shabbir, Mohammad Anas Azeez, Rafiq Ali, Gautam Siddharth Kashyap, Usman Naseem

机构 * Jamia Hamdard（贾迈亚哈马达尔大学） ； Center for SDGC, Stanford University（SDGC研究中心，斯坦福大学） ； DSEU-Okhla ； Macquarie University（麦考瑞大学） 纠错

Comments Accepted at EMNLP 2025 (Industry Track)

The Role of Model Confidence on Bias Effects in Measured Uncertainties for Vision-Language Models

Xinyi Liu, Weiguang Wang, Hangfeng He

机构 * University of Rochester（罗切斯特大学） ； Johns Hopkins University（约翰霍普金斯大学） 纠错

Comments Accepted to EMNLP Findings

Search Wisely: Mitigating Sub-optimal Agentic Searches By Reducing Uncertainty

Peilin Wu, Mian Zhang, Xinlu Zhang, Xinya Du, Zhiyu Zoey Chen

机构 * Department of Computer Science, The University of Texas at Dallas（德克萨斯大学达拉斯分校计算机科学系） ； Department of Computer Science, University of California, Santa Barbara（加州大学圣巴巴拉分校计算机科学系） 纠错

Comments Accepted to EMNLP 2025 Main Conference

UNCLE: Benchmarking Uncertainty Expressions in Long-Form Generation

Ruihan Yang, Caiqi Zhang, Zhisong Zhang, Xinting Huang, Dong Yu, Nigel Collier, Deqing Yang

机构 * Fudan University（复旦大学） ； University of Cambridge（剑桥大学） ； Tencent AI Lab（腾讯AI实验室） ； City University of Hong Kong（香港城市大学） 纠错

Comments EMNLP 2025 Main

What Media Frames Reveal About Stance: A Dataset and Study about Memes in Climate Change Discourse

Shijia Zhou, Siyao Peng, Simon M. Luebke, Jörg Haßler, Mario Haim, Saif M. Mohammad, Barbara Plank

机构 * MaiNLP & MCML, LMU Munich, Germany（LMU慕尼黑媒体与传播系） ； Department of Media and Communication, LMU Munich, Germany（LMU慕尼黑媒体与传播系） ； National Research Council Canada, Ottawa, Canada（加拿大国家研究委员会） 纠错

Comments 20 pages, 9 figures, EMNLP Findings

WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning

Zhepei Wei, Wenlin Yao, Yao Liu, Weizhi Zhang, Qin Lu, Liang Qiu, Changlong Yu, Puyang Xu, Chao Zhang, Bing Yin, Hyokun Yun, Lihong Li

机构 * University of Virginia（弗吉尼亚大学） ； Amazon（亚马逊） ； Georgia Institute of Technology（佐治亚理工学院） 纠错

Comments EMNLP 2025. Code: https://github.com/weizhepei/WebAgent-R1

Building Resource-Constrained Language Agents: A Korean Case Study on Chemical Toxicity Information

Hojun Cho, Donghu Kim, Soyoung Yang, Chan Lee, Hunjoo Lee, Jaegul Choo

Comments EMNLP 2025 Industry track