EMNLP

SpecVLM: Enhancing Speculative Decoding of Video LLMs via Verifier-Guided Token Pruning

Yicheng Ji, Jun Zhang, Heming Xia, Jinpeng Chen, Lidan Shou, Gang Chen, Huan Li

机构 * The State Key Laboratory of Blockchain and Data Security（区块链与数据安全国家重点实验室） ； Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security（杭州高新技术区（滨江）区块链与数据安全研究院） ； Department of Computing, The Hong Kong Polytechnic University（香港理工大学计算机系） ； School of Computer Science, Beijing University of Posts and Telecommunications（北京邮电大学计算机学院） 纠错

Comments Accepted at EMNLP 2025 Main

GLProtein: Global-and-Local Structure Aware Protein Representation Learning

Yunqing Liu, Wenqi Fan, Xiaoyong Wei, Qing Li

机构 * Department of Computing (COMP), The Hong Kong Polytechnic University（计算机学院（COMP），香港理工大学） ； Department of Management and Marketing (MM), The Hong Kong Polytechnic University（管理与营销学院（MM），香港理工大学） ； Department of Computer Science, Sichuan University（计算机学院，四川大学） 纠错

Comments Accepted to EMNLP 2025 Findings

CoMoE: Contrastive Representation for Mixture-of-Experts in Parameter-Efficient Fine-tuning

Jinyuan Feng, Chaopeng Wei, Tenghai Qiu, Tianyi Hu, Zhiqiang Pu

机构 * Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所） ； School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院） ； University of Science and Technology Beijing（北京科技大学） 纠错

Comments Accepted by EMNLP Findings 2025

Joint Enhancement of Relational Reasoning for Long-Context LLMs

Zhirui Chen, Wei Shen, Jiashui Huang, Ling Shao

机构 * UCAS-Terminus AI Lab, University of Chinese Academy of Sciences, China（中国科学院大学Terminus AI实验室，中国科学院大学） 纠错

Comments 9 pages, 5 pages Accepted by EMNLP 2025 Findings

Seeing is Believing: Emotion-Aware Audio-Visual Language Modeling for Expressive Speech Generation

Weiting Tan, Jiachen Lian, Hirofumi Inaguma, Paden Tomasello, Philipp Koehn, Xutai Ma

机构 * Johns Hopkins University（约翰霍普金斯大学） ； Meta AI Research（Meta AI 研究） 纠错

Comments EMNLP 2025 (Findings)

Safeguard Fine-Tuned LLMs Through Pre- and Post-Tuning Model Merging

Hua Farn, Hsuan Su, Shachi H Kumar, Saurav Sahay, Shang-Tse Chen, Hung-yi Lee

机构 * National Taiwan University（国立台湾大学） ； Intel Lab（英特尔实验室） 纠错

Comments EMNLP 2025 Findings

HEAL: A Hypothesis-Based Preference-Aware Analysis Framework

Yifu Huo, Chenglong Wang, Qiren Zhu, Shunjie Xing, Tong Xiao, Chunliang Zhang, Tongran Liu, Jinbo Zhu

机构 * School of Computer Science and Engineering, Northeastern University（计算机科学与工程学院，东北大学） ； NiuTrans Research（NiuTrans研究院） ； CAS Key Laboratory of Behavioral Science, Institute of Psychology, CAS（行为科学重点实验室，心理学研究所） 纠错

Comments Accepted by EMNLP 2025 Findings

Logical Reasoning with Outcome Reward Models for Test-Time Scaling

Ramya Keerthy Thatikonda, Wray Buntine, Ehsan Shareghi

机构 * Department of Data Science & AI, Monash University（数据科学与人工智能系，莫纳什大学） ； College of Engineering and Computer Science, VinUniversity（工程与计算机科学学院，文大学） 纠错

Comments EMNLP 2025

Analysing Chain of Thought Dynamics: Active Guidance or Unfaithful Post-hoc Rationalisation?

Samuel Lewis-Lim, Xingwei Tan, Zhixue Zhao, Nikolaos Aletras

机构 * School of Computer Science, University of Sheffield（计算机科学学院，谢菲尔德大学） 纠错

Comments Accepted at EMNLP 2025 Main Conference

A Symbolic Adversarial Learning Framework for Evolving Fake News Generation and Detection

Chong Tian, Qirong Ho, Xiuying Chen

机构 * MBZUAI 纠错

Comments Accepted to EMNLP 2025 Main Conference

Towards a Holistic and Automated Evaluation Framework for Multi-Level Comprehension of LLMs in Book-Length Contexts

Jiaqi Deng, Yuho Lee, Nicole Hee-Yeon Kim, Hyangsuk Min, Taewon Yun, Minjeong Ban, Kim Yul, Hwanjun Song

机构 * Korea Advanced Institute of Science and Technology（韩国科学技术院） 纠错

Comments Accepted to EMNLP 2025 (Main)

Alignment with Fill-In-the-Middle for Enhancing Code Generation

Houxing Ren, Zimu Lu, Weikang Shi, Haotian Hou, Yunqiao Yang, Ke Wang, Aojun Zhou, Junting Pan, Mingjie Zhan, Hongsheng Li

机构 * CUHK MMLab（CUHK语音实验室） ； SenseTime Research（商汤科技研究院） ； CPII under InnoHK（创新香港下的CPII） ； Shanghai AI Laboratory（上海人工智能实验室） ； Beihang University（北航） 纠错

Comments Accepted to EMNLP 2025 (main conference)

SLIM: Subtrajectory-Level Elimination for More Effective Reasoning

Xifeng Yao, Chengyuan Ma, Dongyu Lang, Yinhao Ni, Zhiwei Xu, Huarui Xie, Zihao Chen, Guang Shen, Dandan Tu, Yi Bai, Changzheng Zhang

机构 * Huawei Technologies Co., Ltd.（华为技术有限公司） 纠错

Comments EMNLP 2025 Findings

Thinking Before You Speak: A Proactive Test-time Scaling Approach

Cong Liu, Wenchang Chai, Hejun Wu, Yan Pan, Pengxu Wei, Liang Lin

机构 * Sun Yat-sen University（中山大学） ； Hong Kong Polytechnic University（香港理工大学） 纠错

Journal ref EMNLP 2025

CoCoA: Confidence and Context-Aware Adaptive Decoding for Resolving Knowledge Conflicts in Large Language Models

Anant Khandelwal, Manish Gupta, Puneet Agrawal

机构 * Microsoft（微软） 纠错

Comments Accepted to EMNLP'25, Main. 21 pages, 17 tables, 3 Figures

VideoEraser: Concept Erasure in Text-to-Video Diffusion Models

Naen Xu, Jinghuai Zhang, Changjiang Li, Zhi Chen, Chunyi Zhou, Qingming Li, Tianyu Du, Shouling Ji

机构 * Zhejiang University（浙江大学） ； University of California, Los Angeles（加州大学洛杉矶分校） ； Palo Alto Networks（帕洛阿尔托网络公司） ； University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） 纠错

Comments To appear in the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Doc2Chart: Intent-Driven Zero-Shot Chart Generation from Documents

Akriti Jain, Pritika Ramu, Aparna Garimella, Apoorv Saxena

机构 * Adobe Research（Adobe研究院） 纠错

Comments Accepted to EMNLP 2025 Main Conference

Decoding Dense Embeddings: Sparse Autoencoders for Interpreting and Discretizing Dense Retrieval

Seongwan Park, Taeklim Kim, Youngjoong Ko

机构 * SungKyunKwan University（顺天妇女大学） 纠错

Comments Published at EMNLP 2025 main

PromptKeeper: Safeguarding System Prompts for LLMs

Zhifeng Jiang, Zhihua Jin, Guoliang He

Comments Accepted to the Findings of EMNLP 2025. 17 pages, 6 figures, 3 tables

On Domain-Adaptive Post-Training for Multimodal Large Language Models

Daixuan Cheng, Shaohan Huang, Ziyu Zhu, Xintong Zhang, Wayne Xin Zhao, Zhongzhi Luan, Bo Dai, Zhenliang Zhang

机构 * BIGAI ； BUAA（北京航空航天大学） ； THU（清华大学） ； BIT（北京理工大学） ； RUC（中国人民大学） 纠错

Comments EMNLP 2025 Findings, Project Page: https://huggingface.co/AdaptLLM/Adapt-MLLM-to-Domains

FiRST: Finetuning Router-Selective Transformers for Input-Adaptive Latency Reduction

Akriti Jain, Saransh Sharma, Koyel Mukherjee, Soumyabrata Pal

机构 * Adobe Research（Adobe研究院） ； Indian Institute of Technology, Kharagpur（印度理工学院，哈里科普尔） 纠错

Comments Accepted to EMNLP 2025 Findings

Stand on The Shoulders of Giants: Building JailExpert from Previous Attack Experience

Xi Wang, Songlei Jian, Shasha Li, Xiaopeng Li, Bin Ji, Jun Ma, Xiaodong Liu, Jing Wang, Feilong Bao, Jianfeng Zhang, Baosheng Wang, Jie Yu

机构 * National University of Defense and Technology（国防科技大学） ； Inner Mongolia University（内蒙古大学） 纠错

Comments 18 pages, EMNLP 2025 Main Conference

FLAIRR-TS -- Forecasting LLM-Agents with Iterative Refinement and Retrieval for Time Series

Gunjan Jalori, Preetika Verma, Sercan Ö Arık

Comments EMNLP

It's All About In-Context Learning! Teaching Extremely Low-Resource Languages to LLMs

Yue Li, Zhixue Zhao, Carolina Scarton

机构 * Department of Computer Science, University of Sheffield, UK（计算机科学系，谢菲尔德大学） 纠错

Comments Accepted by EMNLP 2025

ProPy: Building Interactive Prompt Pyramids upon CLIP for Partially Relevant Video Retrieval

Yi Pan, Yujia Zhang, Michael Kampffmeyer, Xiaoguang Zhao

机构 * State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences（多模态人工智能系统国家重点实验室，自动化研究所，中国科学院） ； School of Artificial Intelligence, University of Chinese Academy of Sciences（人工智能学院，中国科学院大学） ； Department of Physics and Technology, UiT The Arctic University of Norway（物理与技术系，UiT 北极大学） 纠错

Comments Accepted by EMNLP 2025 Findings

Beyond the Textual: Generating Coherent Visual Options for MCQs

Wanqiang Wang, Longzhu He, Wei Zheng

Comments EMNLP 2025

Dynamic Collaboration of Multi-Language Models based on Minimal Complete Semantic Units

Chao Hao, Zezheng Wang, Yanhua Huang, Ruiwen Xu, Wenzhe Niu, Xin Liu, Zitong Yu

Comments Accepted by EMNLP 2025 Main Conference

BTW: A Non-Parametric Variance Stabilization Framework for Multimodal Model Integration

Jun Hou, Le Wang, Xuan Wang

机构 * Department of Computer Science, Virginia Tech, Blacksburg, VA, USA（计算机科学系，弗吉尼亚理工学院，布莱克斯堡，VA，美国） ； Department of Agricultural and Applied Economics, Virginia Tech, Blacksburg, VA, USA（农业与应用经济学系，弗吉尼亚理工学院，布莱克斯堡，VA，美国） 纠错

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

Can Out-of-Distribution Evaluations Uncover Reliance on Shortcuts? A Case Study in Question Answering

Michal Štefánik, Timothee Mickus, Marek Kadlčík, Michal Spiegel, Josef Kuchař

机构 * Language Technology, University of Helsinki（赫尔辛基大学语言技术中心） ； Kempelen Institute of Intelligent Technologies（智能技术研究所） 纠错

Comments To appear in Findings of EMNLP 2025

Integral Transformer: Denoising Attention, Not Too Much Not Too Little

Ivan Kobyzev, Abbas Ghaddar, Dingtao Hu, Boxing Chen

机构 * Huawei Noah’s Ark Lab, Montreal Research Center, Canada（华为诺亚实验室，蒙特利尔研究中心，加拿大） 纠错

Comments EMNLP 2025 Main