EMNLP

LinguaLens: Towards Interpreting Linguistic Mechanisms of Large Language Models via Sparse Auto-Encoder

Yi Jing, Zijun Yao, Hongzhu Guo, Lingxu Ran, Xiaozhi Wang, Lei Hou, Juanzi Li

机构 * DCST, BNRist（DCST、BNRist；KIRC、人工智能研究院、清华大学，中国） ； KIRC, Institute for Artificial Intelligence, Tsinghua University, China（中文语言文学系、北京大学，中国） ； Department of Chinese Language and Literature, Peking University, China 纠错

Comments Accepted by EMNLP 2025 MainConference

Are Generative Models Underconfident? Better Quality Estimation with Boosted Model Probability

Tu Anh Dinh, Jan Niehues

机构 * Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院） 纠错

Comments Accepted to EMNLP 2025 Main Conference

GATEAU: Selecting Influential Samples for Long Context Alignment

Shuzheng Si, Haozhe Zhao, Gang Chen, Yunshui Li, Kangyang Luo, Chuancheng Lv, Kaikai An, Fanchao Qi, Baobao Chang, Maosong Sun

机构 * Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系） ； Peking University（北京大学） ； DeepLang AI ； Institute for AI, Tsinghua University（清华大学人工智能研究院） 纠错

Comments EMNLP 2025

AesBiasBench: Evaluating Bias and Alignment in Multimodal Language Models for Personalized Image Aesthetic Assessment

Kun Li, Lai-Man Po, Hongzheng Yang, Xuyuan Xu, Kangcheng Liu, Yuzhi Zhao

Comments Accepted by EMNLP 2025

Decoding in Latent Spaces for Efficient Inference in LLM-based Recommendation

Chengbing Wang, Yang Zhang, Zhicheng Wang, Tianhao Shi, Keqin Bao, Fuli Feng, Tat-Seng Chua

Comments Accepted for publication in EMNLP'25

!MSA at AraHealthQA 2025 Shared Task: Enhancing LLM Performance for Arabic Clinical Question Answering through Prompt Engineering and Ensemble Learning

Mohamed Tarek, Seif Ahmed, Mohamed Basem

机构 * Faculty of Computer Science, MSA University（计算机科学学院，MSA大学） 纠错

Comments 8 Pages , ArabicNLP 2025 , Co-located with EMNLP 2025

Mitigating Hallucinations in Large Vision-Language Models by Self-Injecting Hallucinations

Yifan Lu, Ziqi Zhang, Chunfeng Yuan, Jun Gao, Congxuan Zhang, Xiaojuan Qi, Bing Li, Weiming Hu

机构 * Beijing Key Laboratory of Super Intelligent Security of Multi-Modal Information, CASIA（北京多模态信息超级智能安全重点实验室，中国科学院自动化所） ； State Key Laboratory of Multimodal Artificial Intelligence Systems, CASIA（多模态人工智能系统国家重点实验室，中国科学院自动化所） ； School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院） ； Hello Group（Hello集团） ； Nanchang Hangkong University（南昌航空大学） ； The University of Hong Kong（香港大学） ； School of Information Science and Technology, ShanghaiTech University（上海科技大学信息科学与技术学院） 纠错

Comments emnlp 2025 accepted

We Argue to Agree: Towards Personality-Driven Argumentation-Based Negotiation Dialogue Systems for Tourism

Priyanshu Priya, Saurav Dudhate, Desai Vishesh Yasheshbhai, Asif Ekbal

机构 * Department of Computer Science and Engineering, Indian Institute of Technology Patna（计算机科学与工程系，印度理工学院帕纳布） 纠错

Comments Paper is accepted at EMNLP (Findings) 2025

Public Data Assisted Differentially Private In-Context Learning

Seongho Joo, Hyukhun Koh, Kyomin Jung

机构 * Seoul National University（首尔国立大学） 纠错

Comments EMNLP 2025 Findings

Harmful Prompt Laundering: Jailbreaking LLMs with Abductive Styles and Symbolic Encoding

Seongho Joo, Hyukhun Koh, Kyomin Jung

Comments EMNLP 2025

CultureSynth: A Hierarchical Taxonomy-Guided and Retrieval-Augmented Framework for Cultural Question-Answer Synthesis

Xinyu Zhang, Pei Zhang, Shuang Luo, Jialong Tang, Yu Wan, Baosong Yang, Fei Huang

机构 * Tongyi Lab, Alibaba Group Inc（通义实验室，阿里集团） 纠错

Comments Accepted as a Findings paper at EMNLP 2025

Pre-Storage Reasoning for Episodic Memory: Shifting Inference Burden to Memory for Personalized Dialogue

Sangyeop Kim, Yohan Lee, Sanghwa Kim, Hyunjong Kim, Sungzoon Cho

机构 * Seoul National University（首尔国立大学） ； Coxwave ； KAIST（韩国科学技术院） 纠错

Comments Accepted by EMNLP 2025 (Findings)

Towards Automated Error Discovery: A Study in Conversational AI

Dominic Petrak, Thy Thy Tran, Iryna Gurevych

机构 * Ubiquitous Knowledge Processing Lab (UKP Lab), Department of Computer Science and Hessian Center for AI (hessian.AI), Technical University of Darmstadt（德累斯顿技术大学） 纠错

Comments Accepted to EMNLP 2025 main conference

TORSO: Template-Oriented Reasoning Towards General Tasks

Minhyuk Kim, Seungyoon Lee, Heuiseok Lim

机构 * Korea University, Republic of Korea（韩国大学） 纠错

Comments Accepted to EMNLP 2025 Main Conference

CM-Align: Consistency-based Multilingual Alignment for Large Language Models

Xue Zhang, Yunlong Liang, Fandong Meng, Songming Zhang, Yufeng Chen, Jinan Xu, Jie Zhou

机构 * Key Laboratory of Big Data & Artificial Intelligence in Transportation, Beijing Jiaotong University, Ministry of Education（大数据与人工智能交通运输 key laboratory，北京交通大学，教育部） ； School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China（计算机科学与技术学院，北京交通大学，北京，中国） ； Pattern Recognition Center, WeChat AI, Tencent Inc, China（模式识别中心，微信AI，腾讯公司，中国） 纠错

Comments EMNLP 2025 Findings

Too Helpful, Too Harmless, Too Honest or Just Right?

Gautam Siddharth Kashyap, Mark Dras, Usman Naseem

机构 * School of Computing, Macquarie University（计算机学院，麦考瑞大学） 纠错

Comments EMNLP'25 Main

From perception to production: how acoustic invariance facilitates articulatory learning in a self-supervised vocal imitation model

Marvin Lavechin, Thomas Hueber

Comments Accepted at EMNLP 2025 (Main Conference)

MEPT: Mixture of Expert Prompt Tuning as a Manifold Mapper

Runjia Zeng, Guangyan Sun, Qifan Wang, Tong Geng, Sohail Dianat, Xiaotian Han, Raghuveer Rao, Xueling Zhang, Cheng Han, Lifu Huang, Dongfang Liu

Comments EMNLP 2025

CAC-CoT: Connector-Aware Compact Chain-of-Thought for Efficient Reasoning Data Synthesis Across Dual-System Cognitive Tasks

Sunguk Choi, Yonghoon Kwon, Heondeuk Lee

Comments Accepted at EMNLP 2025 findings

Less Is More? Examining Fairness in Pruned Large Language Models for Summarising Opinions

Nannan Huang, Haytham M. Fayek, Xiuzhen Zhang

机构 * RMIT University（皇家墨尔本理工大学） 纠错

Comments Accepted to EMNLP 2025 Main Conference

Humanizing Machines: Rethinking LLM Anthropomorphism Through a Multi-Level Framework of Design

Yunze Xiao, Lynnette Hui Xian Ng, Jiarui Liu, Mona T. Diab

机构 * Carnegie Mellon University（卡内基梅隆大学） 纠错

Comments Accepted in EMNLP main proceedings; Updated citations

Transplant Then Regenerate: A New Paradigm for Text Data Augmentation

Guangzhan Wang, Hongyu Zhang, Beijun Shen, Xiaodong Gu

机构 * Shanghai Jiao Tong University（上海交通大学） ； Chongqing University（重庆大学） 纠错

Comments Accepted by EMNLP 2025

'Hello, World!': Making GNNs Talk with LLMs

Sunwoo Kim, Soo Yong Lee, Jaemin Yoo, Kijung Shin

机构 * Kim Jaechul Graduate School of AI, KAIST（金 Jaechul人工智能研究生院，韩国科学技术院） 纠错

Comments Published as a conference paper at EMNLP 2025 Findings. Code and datasets are in https://github.com/kswoo97/GLN-Code

ALRPHFS: Adversarially Learned Risk Patterns with Hierarchical Fast \& Slow Reasoning for Robust Agent Defense

Shiyu Xiang, Tong Zhang, Ronghao Chen

Comments EMNLP 2025 findings, 20 pages, 2 figures

STRICT: Stress Test of Rendering Images Containing Text

Tianyu Zhang, Xinyu Wang, Lu Li, Zhenghan Tai, Jijun Chi, Jingrui Tian, Hailin He, Suyuchen Wang

机构 * Mila, University of Montreal（蒙特利尔大学Mila） ； McGill University（麦吉尔大学） ； University of Pennsylvania（宾夕法尼亚大学） ； University of Toronto（多伦多大学） ； University of California, Los Angeles（加州大学洛杉矶分校） ； Southwestern University of Finance and Economics（西南财经大学） 纠错

Comments Accepted as a main conference paper at EMNLP 2025

Steering LVLMs via Sparse Autoencoder for Hallucination Mitigation

Zhenglin Hua, Jinghan He, Zijun Yao, Tianxu Han, Haiyun Guo, Yuheng Jia, Junfeng Fang

机构 * School of Computer Science and Engineering, Southeast University（东南大学计算机科学与工程学院） ； Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University)（东南大学新一代人工智能技术及其交叉应用关键实验室） ； Foundation Model Research Center, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所基础模型研究中心） ； School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院） ； Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系） ； Wuhan University of Technology（武汉理工大学） ； National University of Singapore（新加坡国立大学） 纠错

Comments Accepted to Findings of EMNLP 2025

ConvSearch-R1: Enhancing Query Reformulation for Conversational Search with Reasoning via Reinforcement Learning

Changtai Zhu, Siyin Wang, Ruijun Feng, Kai Song, Xipeng Qiu

机构 * Fudan University（复旦大学） ； ByteDance Inc（字节跳动公司） ； University of New South Wales（新南威尔士大学） 纠错

Comments Accepted by EMNLP 2025 at the Main Conference

MAC-Tuning: LLM Multi-Compositional Problem Reasoning with Enhanced Knowledge Boundary Awareness

Junsheng Huang, Zhitao He, Yucheng Huang, Sandeep Polisetty, Qingyun Wang, Yi. R Fung

机构 * Hong Kong University of Science and Technology（香港科技大学） ； University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） ； UMass Amherst（马萨诸塞大学阿姆赫斯特分校） ； William & Mary（威廉与玛丽学院） 纠错

Comments We release our code and resource at https://github.com/no-touch-fish/Multi-QA-Tuning. The paper is accepted into EMNLP 2025 main

Static or Dynamic: Towards Query-Adaptive Token Selection for Video Question Answering

Yumeng Shi, Quanyu Long, Wenya Wang

机构 * Nanyang Technological University（南洋理工大学） 纠错

Comments Accepted to EMNLP 2025 (main)

EasyEdit2: An Easy-to-use Steering Framework for Editing Large Language Models

Ziwen Xu, Shuxun Wang, Kewei Xu, Haoming Xu, Mengru Wang, Xinle Deng, Yunzhi Yao, Guozhou Zheng, Huajun Chen, Ningyu Zhang

机构 * Zhejiang University（浙江大学） ； Ocean Research Center of Zhoushan, Zhejiang University（舟山海洋研究中心，浙江大学） 纠错

Comments EMNLP 2025 System Demonstrations. Demo: https://www.youtube.com/watch?v=AkfoiPfp5rQ; code: https://github.com/zjunlp/EasyEdit