EMNLP

$\mathcal{V}isi\mathcal{P}runer$: Decoding Discontinuous Cross-Modal Dynamics for Efficient Multimodal LLMs

Yingqi Fan, Anhao Zhao, Jinlan Fu, Junlong Tong, Hui Su, Yijie Pan, Wei Zhang, Xiaoyu Shen

机构 * Ningbo Key Laboratory of Spatial Intelligence and Digital Derivative, Institute of Digital Twin, EIT, Ningbo（宁波空间智能与数字衍生关键实验室，数字孪生研究院，EIT，宁波） ； Shanghai Jiao Tong University（上海交通大学） ； Hong Kong Polytechnic University（香港理工大学） ； Meituan Inc.（美团公司） ； National University of Singapore（新加坡国立大学） 纠错

Comments EMNLP 2025 Main

Real-Time World Crafting: Generating Structured Game Behaviors from Natural Language with Large Language Models

Austin Drake, Hang Dong

机构 * University of Exeter Department of Computer Science（埃克塞特大学计算机科学系） 纠错

Comments 16 pages, 11 figures (including appendix). To be presented at the 5th Wordplay @ EMNLP workshop (2025)

Does Visual Grounding Enhance the Understanding of Embodied Knowledge in Large Language Models?

Zhihui Yang, Yupei Wang, Kaijie Mo, Zhe Zhao, Renfen Hu

机构 * Beijing Normal University（北京师范大学） ； Tencent AI Lab（腾讯AI实验室） 纠错

Comments Accepted to EMNLP 2025 (Findings). This version corrects a redundant sentence in the Results section that appeared in the camera-ready version

DICE: Structured Reasoning in LLMs through SLM-Guided Chain-of-Thought Correction

Yiqi Li, Yusheng Liao, Zhe Chen, Yanfeng Wang, Yu Wang

机构 * Shanghai Jiao Tong University（上海交通大学） ； Shanghai Artificial Intelligence Laboratory（上海人工智能实验室） 纠错

Comments This paper was accepted to the EMNLP 2025 main conference

Thinking Out Loud: Do Reasoning Models Know When They're Right?

Qingcheng Zeng, Weihao Xuan, Leyang Cui, Rob Voigt

机构 * Northwestern University（西北大学） ； The University of Tokyo（东京大学） ； RIKEN AIP（理化学研究所AIP） ； Westlake University（西湖大学） ； University of California, Davis（加州大学戴维斯分校） 纠错

Comments EMNLP 2025

When Words Smile: Generating Diverse Emotional Facial Expressions from Text

Haidong Xu, Meishan Zhang, Hao Ju, Zhedong Zheng, Erik Cambria, Min Zhang, Hao Fei

Comments Accepted by EMNLP 2025 (Oral); Project Page: https://walkermitty.github.io/EmoAva

Towards Low-Resource Alignment to Diverse Perspectives with Sparse Feedback

Chu Fei Luo, Samuel Dahan, Xiaodan Zhu

机构 * Department of Electrical and Computer Engineering & Ingenuity Labs Research Institute（电气与计算机工程系及创新实验室研究机构） ； Conflict Analytics Lab, Queen’s University（冲突分析实验室，女王大学） ； Cornell Law School（康奈尔法学院） 纠错

Comments Findings of EMNLP 2025, 5 pages

Humanity's Last Code Exam: Can Advanced LLMs Conquer Human's Hardest Code Competition?

Xiangyang Li, Xiaopeng Li, Kuicai Dong, Quanhu Zhang, Rongju Ruan, Xinyi Dai, Xiaoshuang Liu, Shengchun Xu, Yasheng Wang, Ruiming Tang

机构 * Huawei Noah’s Ark Lab（华为诺亚实验室） 纠错

Comments EMNLP 2025 Findings

Code Execution as Grounded Supervision for LLM Reasoning

Dongwon Jung, Wenxuan Zhou, Muhao Chen

机构 * University of California, Davis（加州大学戴维斯分校） ； University of Southern California（南加州大学） 纠错

Comments EMNLP 2025

Enhancing Efficiency and Exploration in Reinforcement Learning for LLMs

Mengqi Liao, Xiangyu Xi, Ruinian Chen, Jia Leng, Yangen Hu, Ke Zeng, Shuai Liu, Huaiyu Wan

机构 * School of Computer Science and Technology, Beijing Jiaotong University（计算机科学与技术学院，北京交通大学） ； Meituan（美团） ； Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence（北京交通数据挖掘与具身智能重点实验室） 纠错

Comments Accept by EMNLP 2025 main

Hard Negatives, Hard Lessons: Revisiting Training Data Quality for Robust Information Retrieval with LLMs

Nandan Thakur, Crystina Zhang, Xueguang Ma, Jimmy Lin

Comments EMNLP 2025 Findings

MiLQ: Benchmarking IR Models for Bilingual Web Search with Mixed Language Queries

Jonghwi Kim, Deokhyung Kang, Seonjeong Hwang, Yunsu Kim, Jungseul Ok, Gary Lee

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

Comments 17 pages, 9 figures, EMNLP 2025 Main Conference

Hallucination Detection in LLMs Using Spectral Features of Attention Maps

Jakub Binkowski, Denis Janiak, Albert Sawczyn, Bogdan Gabrys, Tomasz Kajdanowicz

机构 * Wroclaw University of Science and Technology（沃拉日-克拉夫大学科学与技术学院） ； University of Technology Sydney（悉尼技术大学） 纠错

Comments Accepted to EMNLP 2025. Code available at https://github.com/graphml-lab-pwr/lapeigvals

A Knapsack by Any Other Name: Presentation impacts LLM performance on NP-hard problems

Alex Duchnowski, Ellie Pavlick, Alexander Koller

Comments 24 pages, 6 figures, EMNLP 2025

Familiarity-Aware Evidence Compression for Retrieval-Augmented Generation

Dongwon Jung, Qin Liu, Tenghao Huang, Ben Zhou, Muhao Chen

机构 * University of California, Davis（加州大学戴维斯分校） ； University of Southern California（南加州大学） ； Arizona State University（亚利桑那州立大学） 纠错

Comments EMNLP 2025 Findings

EasyRec: Simple yet Effective Language Models for Recommendation

Xubin Ren, Chao Huang

机构 * The University of Hong Kong（香港大学） 纠错

Comments Published as an EMNLP'25 main paper

SpeechLLMs for Large-scale Contextualized Zero-shot Slot Filling

Kadri Hacioglu, Manjunath K E, Andreas Stolcke

机构 * Uniphore 纠错

Comments 13 pages, EMNLP 2025

GraphMind: Interactive Novelty Assessment System for Accelerating Scientific Discovery

Italo Luis da Silva, Hanqi Yan, Lin Gui, Yulan He

机构 * Department of Informatics（信息学系） 纠错

Comments 9 pages, 6 figures, 3 tables, EMNLP 2025 Demo paper

Temporal Referential Consistency: Do LLMs Favor Sequences Over Absolute Time References?

Ashutosh Bajpai, Tanmoy Chakraborty

机构 * Indian Institute of Technology Delhi（印度理工学院德里分校） ； MongoDB, Inc.（MongoDB公司） 纠错

Comments EMNLP Main Long Paper 2025

Readability Reconsidered: A Cross-Dataset Analysis of Reference-Free Metrics

Catarina G Belem, Parker Glenn, Alfy Samuel, Anoop Kumar, Daben Liu

机构 * University of California Irvine（加州大学尔湾分校） ； Capital One 纠错

Comments Accepted at the TSAR Workshop @ EMNLP 2025

VERITAS: Leveraging Vision Priors and Expert Fusion to Improve Multimodal Data

Tingqiao Xu, Ziru Zeng, Jiayu Chen

机构 * Shanghai Jiao Tong University（上海交通大学） ； Fudan University（复旦大学） 纠错

Comments Accepted to EMNLP 2025 (Main Conference)

FinTrust: A Comprehensive Benchmark of Trustworthiness Evaluation in Finance Domain

Tiansheng Hu, Tongyan Hu, Liuyang Bai, Yilun Zhao, Arman Cohan, Chen Zhao

机构 * NYU Shanghai（纽约大学上海校区） ； National University of Singapore（新加坡国立大学） ； Yale University（耶鲁大学） ； Center for Data Science, New York University（纽约大学数据科学中心） 纠错

Comments EMNLP 2025 Main

Train a Unified Multimodal Data Quality Classifier with Synthetic Data

Weizhi Wang, Rongmei Lin, Shiyang Li, Colin Lockard, Ritesh Sarkhel, Sanket Lokegaonkar, Jingbo Shang, Xifeng Yan, Nasser Zalmout, Xian Li

机构 * UC Santa Barbara（加州大学圣芭芭拉分校） ； Amazon Stores Foundational AI（亚马逊商店基础人工智能） ； UC San Diego（加州大学圣地亚哥分校） 纠错

Comments EMNLP 2025 Findings

DocMMIR: A Framework for Document Multi-modal Information Retrieval

Zirui Li, Siwei Wu, Yizhi Li, Xingyu Wang, Yi Zhou, Chenghua Lin

Comments Accepted for publication at EMNLP 2025 Findings. Code and data publicly available at https://github.com/J1mL1/DocMMIR

WebInject: Prompt Injection Attack to Web Agents

Xilong Wang, John Bloch, Zedian Shao, Yuepeng Hu, Shuyan Zhou, Neil Zhenqiang Gong

Comments Appeared in EMNLP 2025 main conference. To better understand prompt injection attacks, see https://people.duke.edu/~zg70/code/PromptInjection.pdf

Journal ref The 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP 2025)

Summarizing Speech: A Comprehensive Survey

Fabian Retkowski, Maike Züfle, Andreas Sudmann, Dinah Pfau, Shinji Watanabe, Jan Niehues, Alexander Waibel

Comments Accepted to EMNLP 2025

Harmonizing Diverse Models: A Layer-wise Merging Strategy for Consistent Generation

Xujun Peng, Anoop Kumar, Jingyu Wu, Parker Glenn, Daben Liu

机构 * AI Foundations, Capital One McLean, VA, USA（AI基础研究，Capital One麦莱恩，美国弗吉尼亚州） 纠错

Comments EMNLP 2025 Industry track

Semantic Prosody in Machine Translation: the English-Chinese Case of Passive Structures

Xinyue Ma, Pol Pastells, Mireia Farrús, Mariona Taulé

Comments 11 pages, 2 figures, *SEM workshop at EMNLP 2025 conference

Watermarking for Factuality: Guiding Vision-Language Models Toward Truth via Tri-layer Contrastive Decoding

Kyungryul Back, Seongbeom Park, Milim Kim, Mincheol Kwon, SangHyeok Lee, Hyunyoung Lee, Junhee Cho, Seunghyun Park, Jinkyu Kim

机构 * CSE, Korea University（韩国大学计算机科学与工程系） ； KT Corporation（KT公司） ； Soongsil University（顺成大学） 纠错

Comments EMNLP 2025 Findings; Project: https://github.com/KR-0822/TCD

Think Globally, Group Locally: Evaluating LLMs Using Multi-Lingual Word Grouping Games

César Guerra-Solano, Zhuochun Li, Xiang Lorraine Li

机构 * School of Computing and Information（计算与信息学院） ； University of Pittsburgh（匹兹堡大学） 纠错

Comments EMNLP Main 2025