EMNLP

The Geometry of Creative Variability: How Credal Sets Expose Calibration Gaps in Language Models

Esteban Garces Arias, Julian Rodemann, Christian Heumann

机构 * Department of Statistics, LMU Munich（统计系，慕尼黑大学） ； Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心） ； CISPA Helmholtz Center for Information Security（信息安全赫尔姆霍兹研究中心） 纠错

Comments Accepted at the 2nd UncertaiNLP Workshop @ EMNLP 2025

Emergent morpho-phonological representations in self-supervised speech models

Jon Gauthier, Canaan Breiss, Matthew Leonard, Edward F. Chang

机构 * Department of Neurological Surgery, University of California, San Francisco（加州大学旧金山分校神经外科系） ； Department of Linguistics, University of Southern California（南加州大学语言学系） ； Center for Computational Language Sciences, University of Southern California（南加州大学计算语言科学中心） 纠错

Comments Accepted at EMNLP 2025

LLMs Behind the Scenes: Enabling Narrative Scene Illustration

Melissa Roemmele, John Joon Young Chung, Taewook Kim, Yuqian Sun, Alex Calderwood, Max Kreminski

机构 * Midjourney ； Northwestern University（西北大学） ； University of California, Santa Cruz（加州大学圣克鲁兹分校） 纠错

Comments Accepted at EMNLP 2025

TRUEBench: Can LLM Response Meet Real-world Constraints as Productivity Assistant?

Jiho Park, Jongyoon Song, Minjin Choi, Kyuho Heo, Taehun Huh, Ji Won Kim

Comments Accepted to EMNLP 2025 Findings

RAR$^2$: Retrieval-Augmented Medical Reasoning via Thought-Driven Retrieval

Kaishuai Xu, Wenjun Hou, Yi Cheng, Wenjie Li

机构 * Department of Computing, The Hong Kong Polytechnic University（计算机系，香港理工大学） ； Research Institute of Trustworthy Autonomous Systems and Department of Computer Science and Engineering, Southern University of Science and Technology（可信自主系统研究院和计算机科学与工程系，南方科技大学） 纠错

Comments Accepted by EMNLP 2025 Findings

On the Same Wavelength? Evaluating Pragmatic Reasoning in Language Models across Broad Concepts

Linlu Qiu, Cedegao E. Zhang, Joshua B. Tenenbaum, Yoon Kim, Roger P. Levy

机构 * MIT CSAIL（麻省理工学院计算机科学与人工智能实验室） ； MIT BCS（麻省理工学院脑科学与认知研究中心） 纠错

Comments EMNLP 2025 (Main)

Speculative Safety-Aware Decoding

Xuekang Wang, Shengyu Zhu, Xueqi Cheng

机构 * State Key Laboratory of AI Safety, Institute of Computing Technology, CAS（人工智能安全国家重点实验室，计算技术研究所，中国科学院） ； School of Computer Science & Technology, Beijing Institute of Technology（计算机科学与技术学院，北京理工大学） 纠错

Comments Camera-ready version of EMNLP 2025 main conference. Code: https://github.com/k-k1w-w1x-x/Speculative-Safety-Aware-Decoding

LionGuard 2: Building Lightweight, Data-Efficient & Localised Multilingual Content Moderators

Leanne Tan, Gabriel Chua, Ziyu Ge, Roy Ka-Wei Lee

机构 * GovTech, Singapore（新加坡政府科技局） ； Singapore University of Technology and Design（新加坡科技设计大学） 纠错

Comments EMNLP 2025 System Demonstration Track

Probabilistic Soundness Guarantees in LLM Reasoning Chains

Weiqiu You, Anton Xue, Shreya Havaldar, Delip Rao, Helen Jin, Chris Callison-Burch, Eric Wong

机构 * University of Pennsylvania（宾夕法尼亚大学） ； University of Texas at Austin（德克萨斯大学奥斯汀分校） 纠错

Comments EMNLP 2025 camera ready

PRIME: Large Language Model Personalization with Cognitive Dual-Memory and Personalized Thought Process

Xinliang Frederick Zhang, Nick Beauchamp, Lu Wang

机构 * Computer Science and Engineering, University of Michigan, Ann Arbor, MI（计算机科学与工程系，密歇根大学，安娜堡分校） ； Department of Political Science, Northeastern University, Boston, MA（政治学系，东北大学，波士顿分校） 纠错

Comments EMNLP'25 Main

Query-Focused Retrieval Heads Improve Long-Context Reasoning and Re-ranking

Wuwei Zhang, Fangcong Yin, Howard Yen, Danqi Chen, Xi Ye

机构 * Princeton Language and Intelligence, Princeton University（普林斯顿语言与智能研究所，普林斯顿大学） ； The University of Texas at Austin（德克萨斯大学奥斯汀分校） 纠错

Comments EMNLP 2025; Code at https://github.com/princeton-pli/QRHead

Improving LLM Reasoning through Interpretable Role-Playing Steering

Anyi Wang, Dong Shu, Yifan Wang, Yunpu Ma, Mengnan Du

机构 * Center for Information and Language Processing, LMU Munich（信息与语言处理中心，慕尼黑大学） ； Northwestern University（西北大学） ； Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心（MCML）） ； New Jersey Institute of Technology（新泽西理工学院） 纠错

Comments Accepted at EMNLP 2025 Findings

Hanfu-Bench: A Multimodal Benchmark on Cross-Temporal Cultural Understanding and Transcreation

Li Zhou, Lutong Yu, Dongchu Xie, Shaohuan Cheng, Wenyan Li, Haizhou Li

机构 * The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）） ； Shenzhen Research Institute of Big Data（深圳大数据研究院） ； Chengdu Technological University（成都理工大学） ； University of Copenhagen（哥本哈根大学） 纠错

Comments Cultural Analysis, Cultural Visual Understanding, Cultural Image Transcreation. Accepted by EMNLP 2025 (Oral)

TRAPDOC: Deceiving LLM Users by Injecting Imperceptible Phantom Tokens into Documents

Hyundong Jin, Sicheol Sung, Shinwoo Park, SeungYeop Baik, Yo-Sub Han

机构 * Yonsei University（延世大学） 纠错

Comments EMNLP 2025 Findings

BRIT: Bidirectional Retrieval over Unified Image-Text Graph

Ainulla Khan, Yamada Moyuru, Srinidhi Akella

机构 * Fujitsu Research India（富士通印度研究） 纠错

Comments Accepted in EMNLP-2025 Findings

ToDi: Token-wise Distillation via Fine-Grained Divergence Control

Seongryong Jung, Suwan Yoon, DongGeon Kim, Hwanhee Lee

Comments EMNLP 2025 (Oral)

No Black Boxes: Interpretable and Interactable Predictive Healthcare with Knowledge-Enhanced Agentic Causal Discovery

Xiaoxue Han, Pengfei Hu, Jun-En Ding, Chang Lu, Feng Liu, Yue Ning

机构 * Stevens Institute of Technology（史蒂文斯理工学院） 纠错

Comments EMNLP 2025

Multilingual Prompting for Improving LLM Generation Diversity

Qihan Wang, Shidong Pan, Tal Linzen, Emily Black

机构 * New York University（纽约大学） ； Columbia University（哥伦比亚大学） 纠错

Comments Accepted by EMNLP 2025

Internal Chain-of-Thought: Empirical Evidence for Layer-wise Subtask Scheduling in LLMs

Zhipeng Yang, Junzhuo Li, Siyu Xia, Xuming Hu

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） ； Southeast University（东南大学） 纠错

Comments EMNLP 2025 Main

Efficient Unstructured Pruning of Mamba State-Space Models for Resource-Constrained Environments

Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma

机构 * Department of Computer Science, Iowa State University（计算机科学系，爱荷华州立大学） ； Department of Civil, Construction and Environmental Engineering, Iowa State University（土木、建设与环境工程系，爱荷华州立大学） 纠错

Journal ref Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing

Cache-Efficient Posterior Sampling for Reinforcement Learning with LLM-Derived Priors Across Discrete and Continuous Domains

Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma

机构 * Department of Computer Science, Iowa State University, Ames, IA, USA（计算机科学系，爱荷华州立大学） ； Department of Civil, Construction and Environmental Engineering, Iowa State University, Ames, IA, USA（土木、建设与环境工程系，爱荷华州立大学） 纠错

Journal ref Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing

XL-Suite: Cross-Lingual Synthetic Training and Evaluation Data for Open-Ended Generation

Vivek Iyer, Pinzhen Chen, Ricardo Rei, Alexandra Birch

机构 * University of Edinburgh（爱丁堡大学） ； Sword Health ； Queen’s University Belfast（贝尔法斯特女王大学） 纠错

Comments Accepted to EMNLP 2025 (Findings)

Audio-centric Video Understanding Benchmark without Text Shortcut

Yudong Yang, Jimin Zhuang, Guangzhi Sun, Changli Tang, Yixuan Li, Peihan Li, Yifan Jiang, Wei Li, Zejun Ma, Chao Zhang

机构 * Tsinghua University（清华大学） ； University of Cambridge（剑桥大学） ； ByteDance（字节跳动） 纠错

Comments Accepted for publication in the Proceedings of EMNLP 2025 (Main Conference)

UltraIF: Advancing Instruction Following from the Wild

Kaikai An, Li Sheng, Ganqu Cui, Shuzheng Si, Ning Ding, Yu Cheng, Baobao Chang

Comments Accepted by EMNLP 2025

ExeCoder: Empowering Large Language Models with Executability Representation for Code Translation

Minghua He, Yue Chen, Fangkai Yang, Pu Zhao, Wenjie Yin, Yu Kang, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang

Comments EMNLP 2025 (Oral)

Molecular Facts: Desiderata for Decontextualization in LLM Fact Verification

Anisha Gunjal, Greg Durrett

机构 * The University of Texas at Austin（德克萨斯大学奥斯汀分校） 纠错

Journal ref Findings of the Association for Computational Linguistics: EMNLP 2024 (2024) 3751-3768

Thread: A Logic-Based Data Organization Paradigm for How-To Question Answering with Retrieval Augmented Generation

Kaikai An, Fangkai Yang, Liqun Li, Junting Lu, Sitao Cheng, Shuzheng Si, Lu Wang, Pu Zhao, Lele Cao, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang, Baobao Chang

机构 * Peking University（北京大学） ； Microsoft（微软） ； Nanjing University（南京大学） 纠错

Comments Accepted by EMNLP 2025

VCSearch: Bridging the Gap Between Well-Defined and Ill-Defined Problems in Mathematical Reasoning

Shi-Yu Tian, Zhi Zhou, Kun-Yang Yu, Ming Yang, Lin-Han Jia, Lan-Zhe Guo, Yu-Feng Li

机构 * National Key Laboratory for Novel Software Technology, Nanjing University（南京大学新型软件技术国家重点实验室） ； School of Artificial Intelligence, Nanjing University（南京大学人工智能学院） ； School of Intelligence Science and Technology, Nanjing University（南京大学智能科学与技术学院） 纠错

Comments Accepted by EMNLP 2025

Query2Triple: Unified Query Encoding for Answering Diverse Complex Queries over Knowledge Graphs

Yao Xu, Shizhu He, Cunguang Wang, Li Cai, Kang Liu, Jun Zhao

机构 * The Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences（认知与决策智能复杂系统实验室，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） ； Meituan（美团） ； Shanghai Artificial Intelligence Laboratory（上海人工智能实验室） 纠错

Comments Accepted by EMNLP 2023 findings

Your RAG is Unfair: Exposing Fairness Vulnerabilities in Retrieval-Augmented Generation via Backdoor Attacks

Gaurav Bagwe, Saket S. Chaturvedi, Xiaolong Ma, Xiaoyong Yuan, Kuang-Ching Wang, Lan Zhang

Comments Accepted by EMNLP 2025