LLM-empowered Dynamic Prompt Routing for Vision-Language Models Tuning under Long-Tailed Distributions
Comments accepted by EMNLP 2025
期刊&会议
EMNLP
Conference on Empirical Methods in Natural Language Processing · 会议 · Natural Language Processing
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
DesignCLIP: Multimodal Learning with CLIP for Design Patent Understanding
机构 * Department of Computer Science, University of Illinois Chicago（计算机科学系，伊利诺伊大学芝加哥分校）
Comments Accepted by EMNLP 2025. 22 pages, 14 figures
UniCoM: A Universal Code-Switching Speech Generator
机构 * Dept. of Electrical & Electronic Engineering, Yonsei University（电子与电气工程系，延世大学）
Comments Accepted to EMNLP 2025 Findings
Are Checklists Really Useful for Automatic Evaluation of Generative Tasks?
机构 * Tohoku University（东洋大学） ； Research and Development Center for Large Language Models, National Institute of Informatics（大型语言模型研究与开发中心，日本信息处理学会） ； National Institute of Informatics（日本信息处理学会）
Comments Accepted to the EMNLP 2025 Main Conference
Multilingual Datasets for Custom Input Extraction and Explanation Requests Parsing in Conversational XAI Systems
机构 * Technische Universität Berlin（技术大学柏林） ； German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心） ； Saarland Informatics Campus（萨尔州信息学校区） ； Centre for European Research in Trusted AI (CERTAIN)（可信人工智能欧洲研究中心） ； BIFOLD – Berlin Institute for the Foundations of Learning and Data（柏林学习与数据基础研究院）
Comments Accepted at EMNLP 2025 Findings, camera-ready version
ThinkTuning: Instilling Cognitive Reflections without Distillation
Comments EMNLP 2025 (Main Conference)
Length Representations in Large Language Models
机构 * Chungnam National University（Chungnam 国立大学） ； Nara Institute of Science and Technology (NAIST)（奈良科学技术研究所） ； Institute of Science Tokyo（东京科学研究所）
Comments Accepted to EMNLP 2025 Findings
SAND: Boosting LLM Agents with Self-Taught Action Deliberation
Comments EMNLP 2025
WebEvolver: Enhancing Web Agent Self-Improvement with Coevolving World Model
Comments EMNLP 2025 Main Conference
VerifiAgent: a Unified Verification Agent in Language Model Reasoning
Comments EMNLP 2025
BannerAgency: Advertising Banner Design with Multimodal LLM Agents
机构 * Sony Group Corporation（索尼集团）
Comments Accepted as a main conference paper at EMNLP 2025
Large Language Models for Automated Literature Review: An Evaluation of Reference Generation, Abstract Writing, and Review Composition
Comments 12 pages, 5 figures, 5 tables, Accepted by EMNLP 2025 Main Conference
Grounded-VideoLLM: Sharpening Fine-grained Temporal Grounding in Video Large Language Models
机构 * University of California, Davis（加州大学戴维斯分校） ； Virginia Tech（弗吉尼亚理工大学） ； The Chinese University of Hong Kong（香港中文大学） ； NVIDIA ； Adobe Research（Adobe研究） ； Fudan University（复旦大学） ； Meta AI
Comments Accepted by EMNLP 2025 Findings
Optimizing Cross-Client Domain Coverage for Federated Instruction Tuning of Large Language Models
机构 * Nanjing University（南京大学） ； Shanghai Jiao Tong University（上海交通大学） ； Fudan University（复旦大学）
Comments EMNLP 2025
