EMNLP

SEAL: Structure and Element Aware Learning to Improve Long Structured Document Retrieval

Xinhao Huang, Zhibo Ren, Yipeng Yu, Ying Zhou, Zulong Chen, Zeyi Wen

机构 * HKUST (Guangzhou)（香港科技大学（广州）） ； HKUST（香港科技大学） ； Alibaba Group（阿里巴巴集团） ； Zhejiang Lab（浙江实验室） 纠错

Comments Accepted at EMNLP 2025 Main Conference

KRETA: A Benchmark for Korean Reading and Reasoning in Text-Rich VQA Attuned to Diverse Visual Contexts

Taebaek Hwang, Minseo Kim, Gisang Lee, Seonuk Kim, Hyunjun Eun

机构 * Waddle ； Seoul National University（首尔国立大学） ； Krafton ； UNIST（全南大学） ； SK Telecom（SK电信） 纠错

Comments Accepted to EMNLP 2025 (Main Conference)

Continuously Steering LLMs Sensitivity to Contextual Knowledge with Proxy Models

Yilin Wang, Heng Wang, Yuyang Bai, Minnan Luo

机构 * Xi’an Jiaotong University（西安交通大学） 纠错

Comments emnlp 2025

CoViPAL: Layer-wise Contextualized Visual Token Pruning for Large Vision-Language Models

Zicong Tang, Ziyang Ma, Suqing Wang, Zuchao Li, Lefei Zhang, Hai Zhao, Yun Li, Qianren Wang

机构 * School of Artificial Intelligence, Wuhan University（武汉大学人工智能学院） ； School of Computer Science, Wuhan University（武汉大学计算机学院） ； School of Computer Science, Shanghai Jiao Tong University（上海交通大学计算机学院） ； Cognitive AI Lab, Shanghai Huawei Technologies, China（上海华为技术有限公司认知人工智能实验室） 纠错

Comments Accepted by EMNLP 2025

From Disagreement to Understanding: The Case for Ambiguity Detection in NLI

Chathuri Jayaweera, Bonnie J. Dorr

机构 * University of Florida（佛罗里达大学） 纠错

Comments Accepted at Workshop on Perspectivist Approaches to NLP (NLPerspectives), EMNLP 2025, 10 pages, 7 figures

Agentic-R1: Distilled Dual-Strategy Reasoning

Weihua Du, Pranjal Aggarwal, Sean Welleck, Yiming Yang

机构 * Language Technologies Institute, Carnegie Mellon University（语言技术研究所，卡内基梅隆大学） 纠错

Comments Accepted by EMNLP 2025. 15 pages. Project available at https://github.com/StigLidu/DualDistill

PreGenie: An Agentic Framework for High-quality Visual Presentation Generation

Xiaojie Xu, Xinli Xu, Sirui Chen, Haoyu Chen, Fan Zhang, Ying-Cong Chen

机构 * The Hong Kong University of Science and Technology(Guangzhou)（香港科技大学（广州）） ； The Hong Kong University of Science and Technology（香港科技大学） ； Shanghai AI Laboratory（上海人工智能实验室） 纠错

Comments Accepted at EMNLP 2025, Findings

Does Acceleration Cause Hidden Instability in Vision Language Models? Uncovering Instance-Level Divergence Through a Large-Scale Empirical Study

Yizheng Sun, Hao Li, Chang Xu, Hongpeng Zhou, Chenghua Lin, Riza Batista-Navarro, Jingyuan Sun

机构 * University of Manchester（曼彻斯特大学） ； Microsoft Research（微软研究院） 纠错

Comments Accepted to EMNLP 2025 Main Conference

Injecting Domain-Specific Knowledge into Large Language Models: A Comprehensive Survey

Zirui Song, Bin Yan, Yuhan Liu, Miao Fang, Mingzhe Li, Rui Yan, Xiuying Chen

机构 * Mohamed bin Zayed University of Artificial Intelligence（Mohamed bin Zayed大学） ； Northeastern University（东北大学） ； Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学人工智能学院） ； ByteDance（字节跳动） ； Wuhan University（武汉大学） 纠错

Comments EMNLP 2025 findings

Distill Visual Chart Reasoning Ability from LLMs to MLLMs

Wei He, Zhiheng Xi, Wanxu Zhao, Xiaoran Fan, Yiwen Ding, Zifei Shan, Tao Gui, Qi Zhang, Xuanjing Huang

机构 * School of Computer Science, Fudan University（复旦大学计算机学院） ； Weixin Group, Tencent（腾讯Weixin部门） ； Shanghai Innovation Institute（上海创新研究院） ； Shanghai Key Lab of Intelligent Information Processing（上海智能信息处理重点实验室） 纠错

Comments Accepted to EMNLP 2025 Findings. The code and dataset are publicly available at https://github.com/hewei2001/ReachQA

Advancing Grounded Multimodal Named Entity Recognition via LLM-Based Reformulation and Box-Based Segmentation

Jinyuan Li, Ziyan Li, Han Li, Jianfei Yu, Rui Xia, Di Sun, Gang Pan

机构 * College of Intelligence and Computing, Tianjin University（智能与计算学院，天津大学） ； NJUST（南京理工大学） ； College of Mathematics, Taiyuan University of Technology（数学学院，太原科技大学） ； Tianjin University of Science and Technology（天津科技大学） 纠错

Comments Extension of our Findings of EMNLP 2023 & ACL 2024 paper, IEEE Transactions on Multimedia accepted on July 19, 2025

Active Domain Knowledge Acquisition with 100-Dollar Budget: Enhancing LLMs via Cost-Efficient, Expert-Involved Interaction in Sensitive Domains

Yang Wu, Raha Moraffah, Rujing Yao, Jinhong Yu, Zhimin Tao, Xiaozhong Liu

机构 * Worcester Polytechnic Institute（沃斯特理工学院） ； Nankai University（南开大学） ； Jiangsu University（江苏大学） 纠错

Comments EMNLP 2025 Findings

Interpretable Mnemonic Generation for Kanji Learning via Expectation-Maximization

Jaewook Lee, Alexander Scarlatos, Andrew Lan

机构 * University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校） 纠错

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

ROSE: A Reward-Oriented Data Selection Framework for LLM Task-Specific Instruction Tuning

Yang Wu, Huayi Zhang, Yizheng Jiao, Lin Ma, Xiaozhong Liu, Jinhong Yu, Dongyu Zhang, Dezhi Yu, Wei Xu

机构 * Worcester Polytechnic Institute（沃斯特理工学院） ； ByteDance Inc.（字节跳动公司） 纠错

Comments EMNLP 2025 Findings

Personality Matters: User Traits Predict LLM Preferences in Multi-Turn Collaborative Tasks

Sarfaroz Yunusov, Kaige Chen, Kazi Nishat Anwar, Ali Emami

机构 * Brock University（布鲁克大学） ； Emory University（埃默里大学） 纠错

Comments Accepted to EMNLP 2025 Main Conference

Summarize-Exemplify-Reflect: Data-driven Insight Distillation Empowers LLMs for Few-shot Tabular Classification

Yifei Yuan, Jiatong Li, Weijia Zhang, Mohammad Aliannejadi, Evangelos Kanoulas, Renjun Hu

机构 * ETH Zürich（苏黎世联邦理工学院） ； University of Copenhagen（哥本哈根大学） ； University of Science and Technology of China（中国科学技术大学） ； University of Amsterdam（阿姆斯特丹大学） ； East China Normal University（东华大学） 纠错

Comments EMNLP 25 Findings

Igniting Creative Writing in Small Language Models: LLM-as-a-Judge versus Multi-Agent Refined Rewards

Xiaolong Wei, Bo Lu, Xingyu Zhang, Zhejun Zhao, Dongdong Shen, Long Xia, Dawei Yin

机构 * Beihang University（北航） ； Baidu Inc.（百度公司） ； Beijing Jiaotong University（北京交通大学） 纠错

Comments EMNLP 2025 Main

TrInk: Ink Generation with Transformer Network

Zezhong Jin, Shubhang Desai, Xu Chen, Biyi Fang, Zhuoyi Huang, Zhe Li, Chong-Xin Gan, Xiao Tu, Man-Wai Mak, Yan Lu, Shujie Liu

机构 * The Hong Kong Polytechnic University（香港理工大学） ； Microsoft Corporation（微软公司） ； Microsoft Research Asia（微软亚洲研究院） 纠错

Comments Accepted to EMNLP 2025 Main Conference

Mapping Toxic Comments Across Demographics: A Dataset from German Public Broadcasting

Jan Fillies, Michael Peter Hoffmann, Rebecca Reichel, Roman Salzwedel, Sven Bodemer, Adrian Paschke

机构 * Freie Universität Berlin（柏林自由大学） ； Fraunhofer FOKUS（弗劳恩霍夫研究所（FOKUS）） ； MSB Medical School Berlin（柏林医学学校（MSB）） ； funk - Content-Netzwerk ARD / ZDF（ARD/ZDF内容网络） ； InfAI Leipzig（莱比锡InfAI） 纠错

Comments The paper has been accepted to the EMNLP 2025 main track

Refining Text Generation for Realistic Conversational Recommendation via Direct Preference Optimization

Manato Tajiri, Michimasa Inaba

Comments Accepted to EMNLP 2025 Main Conference

Uncovering the Bigger Picture: Comprehensive Event Understanding Via Diverse News Retrieval

Yixuan Tang, Yuanyuan Shi, Yiqun Sun, Anthony Kum Hoe Tung

机构 * National University of Singapore（国立新加坡大学） ； Shanghai Jiao Tong University（上海交通大学） 纠错

Comments Accepted by EMNLP 2025

SKA-Bench: A Fine-Grained Benchmark for Evaluating Structured Knowledge Understanding of LLMs

Zhiqiang Liu, Enpei Niu, Yin Hua, Mengshu Sun, Lei Liang, Huajun Chen, Wen Zhang

机构 * School of Software Technology, Zhejiang University（浙江大学软件学院） ； College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院） ； ZJU-Ant Group Joint Lab of Knowledge Graph（浙江大学蚂蚁集团知识图谱联合实验室） ； Ant Group（蚂蚁集团） 纠错

Comments EMNLP 2025

Retrieval-Augmented Machine Translation with Unstructured Knowledge

Jiaan Wang, Fandong Meng, Yingxue Zhang, Jie Zhou

机构 * Pattern Recognition Center, WeChat AI, Tencent Inc（模式识别中心、微信AI、腾讯公司） 纠错

Comments EMNLP 2025 Findings

RevPRAG: Revealing Poisoning Attacks in Retrieval-Augmented Generation through LLM Activation Analysis

Xue Tan, Hao Luan, Mingyu Luo, Xiaoyan Sun, Ping Chen, Jun Dai

机构 * School of Computer Science, Fudan University（复旦大学计算机科学学院） ； Department of Computer Science, Worcester Polytechnic Institute（沃思堡理工学院计算机科学系） ； Institute of Big Data, Fudan University（复旦大学大数据研究院） 纠错

Comments Accepted to Findings of EMNLP 2025

Revealing Fine-Grained Values and Opinions in Large Language Models

Dustin Wright, Arnav Arora, Nadav Borenstein, Srishti Yadav, Serge Belongie, Isabelle Augenstein

机构 * University of Copenhagen（哥本哈根大学） 纠错

Comments Findings of EMNLP 2024; 28 pages, 20 figures, 7 tables

STARE at the Structure: Steering ICL Exemplar Selection with Structural Alignment

Jiaqian Li, Qisheng Hu, Jing Li, Wenya Wang

机构 * Nanyang Technological University, Singapore（南洋理工大学） ； Harbin Institute of Technology, Shenzhen, China（哈尔滨工业大学（深圳）） 纠错

Comments EMNLP 2025 Main

GDLLM: A Global Distance-aware Modeling Approach Based on Large Language Models for Event Temporal Relation Extraction

Jie Zhao, Wanting Ning, Yuxiao Fei, Yubo Feng, Lishuang Li

机构 * School of Computer Science and Technology, Dalian University of Technology, China（大连理工大学计算机科学与技术学院） ； Luddy School of Informatics, Computing, and Engineering, Indiana University Indianapolis, the United States（印第安纳大学印第安纳波利斯分校信息学院） 纠错

Comments Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP Findings)

Leveraging Semantic Triples for Private Document Generation with Local Differential Privacy Guarantees

Stephen Meisenbacher, Maulik Chevli, Florian Matthes

机构 * Technical University of Munich School of Computation, Information and Technology Department of Computer Science（慕尼黑技术大学计算、信息与技术学院计算机科学系） 纠错

Comments 17 pages, 2 figures, 11 tables. Accepted to EMNLP 2025 (Main)

Languages Still Left Behind: Toward a Better Multilingual Machine Translation Benchmark

Chihiro Taguchi, Seng Mai, Keita Kurabe, Yusuke Sakai, Georgina Agyei, Soudabeh Eslami, David Chiang

机构 * University of Notre Dame（诺特达姆大学） ； University of Washington（华盛顿大学） ； Tokyo University of Foreign Studies（东京外国语大学） ； Nara Institute of Science and Technology（奈良科学技術大学） ； University of Tübingen（图宾根大学） 纠错

Comments 13 pages, 7 tables, 2 figures. Accepted at EMNLP Main 2025. Code and data released at https://github.com/ctaguchi/LSLB

Graph-R1: Incentivizing the Zero-Shot Graph Learning Capability in LLMs via Explicit Reasoning

Yicong Wu, Guangyue Lu, Yuan Zuo, Huarong Zhang, Junjie Wu

Comments Accepted at EMNLP 2025