UPLex: Fine-Grained Personality Control in Large Language Models via Unsupervised Lexical Modulation
机构 * School of Computer Science, Fudan University（复旦大学计算机学院）
Comments EMNLP 2025 Findings
期刊&会议
EMNLP
Conference on Empirical Methods in Natural Language Processing · 会议 · Natural Language Processing
Will Annotators Disagree? Identifying Subjectivity in Value-Laden Arguments
机构 * Delft University of Technology（代尔夫特理工大学）
Comments Accepted at Findings of EMNLP 2025
SLiNT: Structure-aware Language Model with Injection and Contrastive Training for Knowledge Graph Completion
机构 * University of Chinese Academy of Sciences（中国科学院大学） ； Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所） ； National Astronomical Observatories, Chinese Academy of Sciences（中国科学院国家天文台）
Comments Accepted by EMNLP Findings 2025
Language Bias in Information Retrieval: The Nature of the Beast and Mitigation Methods
机构 * School of Computing & Information Systems, The University of Melbourne（计算机与信息系统学院，墨尔本大学） ； Mohamed bin Zayed University of Artificial Intelligence, UAE（马尔代夫比兹亚德人工智能大学，阿联酋）
Comments Accepted at EMNLP MRL 2024
Multimodal Fine-grained Context Interaction Graph Modeling for Conversational Speech Synthesis
机构 * Inner Mongolia University（内蒙古大学） ； Center for Language and Speech Processing (CLSP)（语言与语音处理中心） ； School of Artificial Intelligence, The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）人工智能学院）
Comments Accepted by EMNLP 2025
RepoDebug: Repository-Level Multi-Task and Multi-Language Debugging Evaluation of Large Language Models
机构 * School of Computer Science and Engineering, Beihang University（北京航空航天大学计算机科学与工程学院） ； East China Normal University（华东师范大学） ； School of Computer Science and Technology, Beijing Institute of Technology（北京理工大学计算机科学与技术学院） ； Baidu Inc.（百度公司）
Comments 30 pages, 12 figures, EMNLP 2025 Findings
MoSEs: Uncertainty-Aware AI-Generated Text Detection via Mixture of Stylistics Experts with Conditional Thresholds
机构 * Nankai University（南开大学） ； Tsinghua University（清华大学） ； Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳）） ； Peng Cheng Laboratory（鹏城实验室） ； Shenzhen ShenNong Information Technology Co., Ltd.（深圳深农信息技术有限公司）
Comments EMNLP 2025
CodeMixBench: Evaluating Code-Mixing Capabilities of LLMs Across 18 Languages
机构 * NUC（南京大学） ； ETH Zurich（苏黎世联邦理工学院）
Comments EMNLP 2025
Not All Features Deserve Attention: Graph-Guided Dependency Learning for Tabular Data Generation with Language Models
Comments Accepted to EMNLP 2025 (Findings)
Dynamic Injection of Entity Knowledge into Dense Retrievers
机构 * Studio Ousia（Ousia工作室） ； RIKEN AIP（理化学研究所AIP） ； SB Intuitions ； The University of Tokyo（东京大学）
Comments EMNLP Findings
Too Consistent to Detect: A Study of Self-Consistent Errors in LLMs
Comments EMNLP 2025 Main
Soft Token Attacks Cannot Reliably Audit Unlearning in Large Language Models
机构 * Ludwig Maximilian University of Munich（慕尼黑路德维希-马克西米利安大学） ； Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心） ； Aalto University（艾尔沃斯大学） ； Intel Labs（英特尔实验室）
Comments EMNLP 2025 Findings
Revealing the impact of synthetic native samples and multi-tasking strategies in Hindi-English code-mixed humour and sarcasm detection
机构 * Department of Data Science and Engineering（数据科学与工程系） ； Indian Institute of Science Education and Research（印度科学教育与研究学院）
Comments 33 pages; EMNLP 2025 (Findings)
Multi-EuP: The Multilingual European Parliament Dataset for Analysis of Bias in Information Retrieval
Comments Accepted at The 3rd Multilingual Representation Learning (MRL) Workshop (co-located with EMNLP 2023)
Journal ref https://aclanthology.org/2023.mrl-1.21
Support or Refute: Analyzing the Stance of Evidence to Detect Out-of-Context Mis- and Disinformation
Comments Accepted and published by EMNLP 2023. Details can be found in https://aclanthology.org/2023.emnlp-main.259
Journal ref In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 4268-4280, Singapore. Association for Computational Linguistics
Towards an Automated Framework to Audit Youth Safety on TikTok
Comments 7 pages, 3 figures, submitted to EMNLP 2025 and ECAT Research Workshop 2025
Icon$^{2}$: Aligning Large Language Models Using Self-Synthetic Preference Data via Inherent Regulation
机构 * Zhejiang University（浙江大学） ； Soochow Securities Co.,Ltd.（苏州证券有限公司） ； HKUST(GZ)（香港科技大学（广州）） ； Nanjing University（南京大学）
Comments EMNLP 2025 Main
KG-CQR: Leveraging Structured Relation Representations in Knowledge Graphs for Contextual Query Retrieval
机构 * Viettel AI, Viettel Group（越南 Viettel 集团 AI 部门） ； University of Engineering and Technology, Vietnam National University, Hanoi（越南国家大学河内工程大学） ； Department of Computer Engineering, Chung-Ang University（Chung-Ang 大学计算机工程系）
Comments Accepted at Main EMNLP 2025
FlowMalTrans: Unsupervised Binary Code Translation for Malware Detection Using Flow-Adapter Architecture
Comments This paper is accepted to EMNLP 2025 Findings
Self-Critique and Refinement for Faithful Natural Language Explanations
机构 * University of Copenhagen（哥本哈根大学）
Comments EMNLP 2025 Main
VisBias: Measuring Explicit and Implicit Social Biases in Vision Language Models
机构 * University of Southern California（南加州大学） ； University of Bristol（布里斯托大学） ； Centre National de la Recherche Scientifique（法国国家科学研究中心） ； University of California, Los Angeles（加州大学洛杉矶分校）
Comments Accepted to EMNLP 2025 (Main)
Evaluating the Robustness and Accuracy of Text Watermarking Under Real-World Cross-Lingual Manipulations
机构 * University of Central Florida（中央佛罗里达大学）
Comments Accepted by EMNLP 2025 Finding
AI Sees Your Location, But With A Bias Toward The Wealthy World
机构 * University of Southern California（南加州大学） ； University of Georgia（佐治亚大学） ； University of California, Los Angeles（加州大学洛杉矶分校）
Comments Accepted to EMNLP 2025 (Main)
Position: LLMs Can be Good Tutors in English Education
机构 * Squirrel Ai Learning ； Tsinghua University（清华大学） ； HKUST (Guangzhou)（香港科技大学（广州）） ； Peng Cheng Laboratory（鹏城实验室） ； Fudan University（复旦大学） ； The Chinese University of Hong Kong（香港中文大学） ； University of Illinois at Chicago（伊利诺伊大学香槟分校）
Comments Accepted to EMNLP 2025 Main. 20 pages, 4 figures
GASE: Generatively Augmented Sentence Encoding
机构 * Department of Computer Science（计算机科学系） ； Munster Technological University（穆斯堡技术大学）
Comments EMNLP Findings 2025
Extracting and Combining Abilities For Building Multi-lingual Ability-enhanced Large Language Models
机构 * Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学人工智能学院） ； School of Information, Renmin University of China（中国人民大学信息学院） ； Baichuan Inc（百川科技）
Comments EMNLP 2025 Main Conference
Large Language Models Might Not Care What You Are Saying: Prompt Format Beats Descriptions
机构 * National Key Laboratory for Multimedia Information Processing, Peking University（北京大学多媒体信息处理国家重点实验室） ； MOE Key Laboratory of Computational Linguistics, Peking University School of Computer Science, Peking University（教育部计算语言学重点实验室，北京大学计算机科学学院，北京大学）
Comments EMNLP 2025 Findings. 23 pages, 23 figures, 7 tables
Synth-SBDH: A Synthetic Dataset of Social and Behavioral Determinants of Health for Clinical Text
机构 * Manning College of Information and Computer Sciences, University of Massachusetts Amherst（马萨诸塞大学阿姆赫斯特分校信息与计算机科学学院） ； U.S. Department of Veterans Affairs（美国退伍军人事务部） ； Department of Medicine, University of Massachusetts Chan Medical School（马萨诸塞大学查恩医学院医学部） ； Miner School of Computer and Information Sciences, University of Massachusetts Lowell（马萨诸塞大学洛厄尔分校米纳尔计算机与信息科学学院）
Comments Accepted at EMNLP 2025 (main) Github: https://github.com/avipartho/Synth-SBDH
PRIM: Towards Practical In-Image Multilingual Machine Translation
机构 * School of Computer Science and Technology, Beijing Institute of Technology（北京理工大学计算机科学与技术学院） ； School of Computer Science and Engineering, Beihang University（北航计算机科学与工程学院）
Comments Accepted to EMNLP 2025 Main Conference
OSC: Cognitive Orchestration through Dynamic Knowledge Alignment in Multi-Agent LLM Collaboration
机构 * Sun Yat-sen University（中山大学） ； Alibaba Group（阿里巴巴集团）
Comments Accepted at EMNLP 2025 (Long Paper)
