AutoDCWorkflow: LLM-based Data Cleaning Workflow Auto-Generation and Benchmark
机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
Comments EMNLP Findings, 2025
期刊&会议
EMNLP
Conference on Empirical Methods in Natural Language Processing · 会议 · Natural Language Processing
Towards Controllable Speech Synthesis in the Era of Large Language Models: A Systematic Survey
机构 * The Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州）） ； University of Surrey（萨里大学）
Comments The first comprehensive survey on controllable TTS. Accepted to the EMNLP 2025 main conference
Draft Model Knows When to Stop: Self-Verification Speculative Decoding for Long-Form Generation
机构 * Shanghai Jiao Tong University（上海交通大学） ； Tencent（腾讯）
Comments EMNLP 2025
DataTales: A Benchmark for Real-World Intelligent Data Narration
机构 * National University of Singapore（新加坡国立大学） ； Rio Tinto（里奥·廷特公司） ； Sea AI Lab（Sea AI实验室）
Comments Accepted at EMNLP 2024 (main conference, long paper)
VLASCD: A Visual Language Action Model for Simultaneous Chatting and Decision Making
机构 * College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院） ； Home Robotics Lab, E-surfing Digital Life Technology Co., Ltd., China Telecom（E-surfing数字生活技术有限公司） ； Zhejiang Lab（浙江实验室） ； Trinity College Dublin（都柏林大学）
Comments Accepted by EMNLP 2025 (Main Conference)
SensorLLM: Aligning Large Language Models with Motion Sensors for Human Activity Recognition
机构 * University of New South Wales（新南威尔士大学） ； University of Tokyo（东京大学）
Comments Accepted by EMNLP 2025 Main Conference
ModalPrompt: Towards Efficient Multimodal Continual Instruction Tuning with Dual-Modality Guided Prompt
机构 * 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） ； School of Artificial Intelligence, UCAS（人工智能学院） ； Centre for Artificial Intelligence and Robotics, HKISI-CAS（人工智能与机器人中心）
Comments EMNLP 2025 (Main Conference)
Rethinking Cross-Subject Data Splitting for Brain-to-Text Decoding
机构 * College of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics（人工智能学院，南京航空航天大学） ； The Key Laboratory of Brain-Machine Intelligence Technology, Ministry of Education（脑机智能技术重点实验室，教育部）
Journal ref EMNLP 2025 main conference
JUDGEBERT: Assessing Legal Meaning Preservation Between Sentences
机构 * Université Laval（拉瓦尔大学） ； Computer Science Department（计算机科学系） ； Faculty of Law（法学院）
Comments Accepted to EMNLP 2025
QFrCoLA: a Quebec-French Corpus of Linguistic Acceptability Judgments
机构 * Group for Research in Artificial Intelligence of Laval University (GRAIL)（拉瓦尔大学人工智能研究组） ； Université Laval（拉瓦尔大学）
Comments Accepted to EMNLP 2025
Assess and Prompt: A Generative RL Framework for Improving Engagement in Online Mental Health Communities
机构 * IIIT Delhi, India（德里印度理工学院） ； Microsoft, India（微软印度）
Comments Full Paper accepted in EMNLP Findings 2025
WebMMU: A Benchmark for Multimodal Multilingual Website Understanding and Code Generation
机构 * ServiceNow ； Mila ； Université de Montréal（蒙特利尔大学） ； McGill University（麦吉尔大学） ； École de Technologie Supérieure (ETS)（高等技术学院） ； Polytechnique Montréal（蒙特利尔理工学院）
Comments This paper has been accepted to the EMNLP 2025 main conference. Check the project page here: https://webmmu-paper.github.io/
How Good are LLM-based Rerankers? An Empirical Analysis of State-of-the-Art Reranking Models
机构 * University of Innsbruck（因斯布鲁克大学）
Comments EMNLP Findings 2025
Words Like Knives: Backstory-Personalized Modeling and Detection of Violent Communication
机构 * Massachusetts Institute of Technology（麻省理工学院） ； Carnegie Mellon University（卡内基梅隆大学） ； Allen Institute for Artificial Intelligence（人工智能研究院）
Comments Accepted to EMNLP 2025
Evaluating $n$-Gram Novelty of Language Models Using Rusty-DAWG
机构 * New York University（纽约大学） ； Allen Institute for AI（人工智能研究院） ； University of Washington（华盛顿大学）
Comments To appear at EMNLP 2024
ComplexTempQA:A 100m Dataset for Complex Temporal Question Answering
机构 * University of Innsbruck（因斯布鲁克大学） ； Technical University Dresden（德累斯顿技术大学）
Comments Accepted at EMNLP main
FLAMES: Improving LLM Math Reasoning via a Fine-Grained Analysis of the Data Synthesis Pipeline
机构 * Amazon AGI Foundations（亚马逊人工智能基础研究机构） ； Dartmouth College（达特茅斯学院） ； UNC Chapel Hill（北卡罗来纳大学教堂山分校） ； University of California, Los Angeles（加州大学洛杉矶分校）
Comments To appear at EMNLP 2025
A Probabilistic Inference Scaling Theory for LLM Self-Correction
机构 * State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University（多媒体信息处理国家重点实验室，计算机学院，北京大学） ； Alibaba Group（阿里巴巴集团）
Comments EMNLP 2025 Main
XLQA: A Benchmark for Locale-Aware Multilingual Open-Domain Question Answering
机构 * Department of Artificial Intelligence, Korea University（人工智能系，韩国大学）
Comments Accepted to EMNLP 2025 main conference. 12 pages, 4 figures, 7 tables. Code is available at https://github.com/ro-ko/XLQA
CYCLE-INSTRUCT: Fully Seed-Free Instruction Tuning via Dual Self-Training and Cycle Consistency
机构 * Zhejiang University（浙江大学） ； University of Science and Technology of China（中国科学技术大学） ； Tianjin University（天津大学）
Comments EMNLP 2025 Main
Noise, Adaptation, and Strategy: Assessing LLM Fidelity in Decision-Making
机构 * University of Lausanne（洛桑大学） ； Nanyang Technological University（南洋理工大学）
Comments Accepted to EMNLP 2025 (Main Conference)
A Toolbox, Not a Hammer -- Multi-TAG: Scaling Math Reasoning with Multi-Tool Aggregation
机构 * ServiceNow AI ； University of Washington（华盛顿大学）
Comments Published at EMNLP Findings 2025; 21 pages, 3 figures
HypER: Literature-grounded Hypothesis Generation and Distillation with Provenance
Comments EMNLP 2025, 26 pages (9 pages: main paper body)
A Text-Based Recommender System that Leverages Explicit Affective State Preferences
机构 * Department of Computer Science University of North Carolina at Charlotte（计算机科学系北卡罗来纳大学夏洛特分校）
Comments To appear at EMNLP 2025
Soteria: Language-Specific Functional Parameter Steering for Multilingual Safety Alignment
机构 * Indian Institute of Technology Kharagpur（印度理工学院卡里格普尔分校） ； Eindhoven University of Technology（埃因霍温理工大学）
Comments Accepted at EMNLP 2025
On the Role of Entity and Event Level Conceptualization in Generalizable Reasoning: A Survey of Tasks, Methods, Applications, and Future Directions
机构 * Department of Computer Science and Engineering, HKUST, Hong Kong SAR, China（计算机科学与工程系，香港科技大学，香港特别行政区，中国）
Comments Findings of EMNLP 2025
LLM-empowered Dynamic Prompt Routing for Vision-Language Models Tuning under Long-Tailed Distributions
Comments accepted by EMNLP 2025
M-HELP: Using Social Media Data to Detect Mental Health Help-Seeking Signals
机构 * IIIT Dharwad（印度达尔瓦德理工学院） ； Arizona State University（亚利桑那州立大学）
Comments Accepted at Findings of EMNLP 2025
When Audio and Text Disagree: Revealing Text Bias in Large Audio-Language Models
机构 * National University of Singapore（国立新加坡大学） ； Nanyang Technological University（南洋理工大学） ； Tsinghua University（清华大学）
Comments Accepted by EMNLP 2025 Main
IPIGuard: A Novel Tool Dependency Graph-Based Defense Against Indirect Prompt Injection in LLM Agents
Comments EMNLP 2025
