InteGround: On the Evaluation of Verification and Retrieval Planning in Integrative Grounding
机构 * The Hong Kong University of Science and Technology（香港科学与技术大学） ； Shanghai Jiaotong University（上海交通大学）
Comments Accepted to EMNLP 2025 Findings
期刊&会议
EMNLP
Conference on Empirical Methods in Natural Language Processing · 会议 · Natural Language Processing
Challenging the Evaluator: LLM Sycophancy Under User Rebuttal
机构 * Johns Hopkins University（约翰霍普金斯大学）
Comments Accepted to EMNLP 2025 Findings
Leveraging Multilingual Training for Authorship Representation: Enhancing Generalization across Languages and Domains
机构 * University of Michigan（密歇根大学）
Comments Accepted to EMNLP 2025
Seeing Culture: A Benchmark for Visual Reasoning and Grounding
机构 * Singapore Management University（新加坡管理大学） ； Bandung Institute of Technology（班达理工大学）
Comments Accepted to EMNLP 2025 Main Conference, https://seeingculture-benchmark.github.io/
Towards Universal Debiasing for Language Models-based Tabular Data Generation
机构 * Purdue University（普渡大学） ； Georgia Institute of Technology（佐治亚理工学院）
Comments EMNLP 2025 Findings
Implicit Behavioral Alignment of Language Agents in High-Stakes Crowd Simulations
机构 * University of Southern California（南加州大学） ； USC Institute for Creative Technologies（USC创意技术研究所）
Comments Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP 2025), Main Conference
Evaluating the Effectiveness and Scalability of LLM-Based Data Augmentation for Retrieval
机构 * Microsoft Research India（微软研究院印度分部）
Comments EMNLP 2025 (MAIN Conference)
AutoArabic: A Three-Stage Framework for Localizing Video-Text Retrieval Benchmarks
Comments Accepted at ArabicNLP 2025 (EMNLP 2025 workshop)
'Rich Dad, Poor Lad': How do Large Language Models Contextualize Socioeconomic Factors in College Admission ?
机构 * University of Maryland（马里兰大学） ； University of Southern California（南加州大学）
Comments EMNLP 2025, ver 1, 35 pages
Evaluating Behavioral Alignment in Conflict Dialogue: A Multi-Dimensional Comparison of LLM Agents and Humans
机构 * University of Southern California（南加州大学） ； USC for Institute of Creative Technologies（南加州大学创意技术研究所）
Comments Accepted to EMNLP 2025 (Main Conference)
Whisper-UT: A Unified Translation Framework for Speech and Text
机构 * Center for Language and Speech Processing, Johns Hopkins University（语言与语音处理中心，约翰霍普金斯大学） ； Human Language Technology Center of Excellence, Johns Hopkins University（人类语言技术卓越中心，约翰霍普金斯大学） ； Georgetown University（乔治城大学）
Comments EMNLP 2025 Main Conference
Enhancing Financial RAG with Agentic AI and Multi-HyDE: A Novel Approach to Knowledge Retrieval and Hallucination Reduction
机构 * Indian Institute of Technology Madras（印度理工学院马德拉斯学院）
Comments 14 Pages, 8 Tables, 2 Figures. Accepted and to be published in the proceedings of FinNLP, Empirical Methods in Natural Language Processing 2025
DeDisCo at the DISRPT 2025 Shared Task: A System for Discourse Relation Classification
机构 * Georgetown University（乔治·华盛顿大学）
Comments System submission for the DISRPT 2025 - Shared Task on Discourse Relation Parsing and Treebanking In conjunction with CODI-CRAC & EMNLP 2025. 1st place in Task 3: relation classification
Factuality Beyond Coherence: Evaluating LLM Watermarking Methods for Medical Texts
机构 * University of Central Florida（中央佛罗里达大学）
Comments Accepted at EMNLP 2025 Findings. Camera Ready
Reward-Weighted Sampling: Enhancing Non-Autoregressive Characteristics in Masked Diffusion LLMs
机构 * KAIST AI（韩国科学技术院人工智能研究所） ； Applied Artificial Intelligence, Sungkyunkwan University（成均馆大学应用人工智能系）
Comments EMNLP 2025 Main Paper (Long)
Side Effects of Erasing Concepts from Diffusion Models
机构 * University of Maryland, Baltimore County（马里兰大学巴尔的摩分校）
Comments Findings of the Association for Computational Linguistics: EMNLP 2025
AgentMaster: A Multi-Agent Conversational Framework Using A2A and MCP Protocols for Multimodal Information Retrieval and Analysis
机构 * Stanford University（斯坦福大学） ； George Mason University（乔治·马歇尔大学）
Comments Accepted by EMNLP 2025
"What's Up, Doc?": Analyzing How Users Seek Health Information in Large-Scale Conversational AI Datasets
机构 * UNC Chapel Hill（北卡罗来纳大学教堂山分校） ； Duke University（杜克大学） ； University of Washington（华盛顿大学） ； Google（谷歌）
Comments Accepted to EMNLP 2025 Findings - 25 pages, 6 figures, 4 tables
SoundMind: RL-Incentivized Logic Reasoning for Audio-Language Models
机构 * Dartmouth College（达特茅斯学院） ； Shandong University（山东大学）
Comments Accepted to EMNLP 2025 Main Conference (Oral Presentation)
Tau-Eval: A Unified Evaluation Framework for Useful and Private Text Anonymization
机构 * Hornetsecurity, Hem, France（Hornetsecurity） ； Univ. Lille, Inria, CNRS, Centrale Lille, UMR 9189 - CRIStAL, F-59000 Lille, France（Lille大学）
Comments EMNLP 2025 Demo
Matter-of-Fact: A Benchmark for Verifying the Feasibility of Literature-Supported Claims in Materials Science
机构 * University of Arizona（亚利桑那大学） ； Allen Institute for Artificial Intelligence（人工智能 Allen 机构）
Comments 9 pages (Accepted to EMNLP 2025)
Inceptive Transformers: Enhancing Contextual Representations through Multi-Scale Feature Learning Across Domains and Languages
机构 * Bangladesh University of Engineering and Technology（孟加拉工程与技术大学） ； BRAC University（BRAC大学）
Comments Accepted to EMNLP 2025 (long paper). To appear in the Proceedings of EMNLP 2025
We Need to Measure Data Diversity in NLP -- Better and Broader
机构 * Utrecht University（乌得勒支大学） ； Aalborg University（奥胡斯大学）
Comments EMNLP 2025
DisastIR: A Comprehensive Information Retrieval Benchmark for Disaster Management
机构 * Texas A&M University（德克萨斯大学） ； University of Toronto（多伦多大学）
Comments EMNLP 2025 Findings
EmoGist: Efficient In-Context Learning for Visual Emotion Understanding
机构 * Purdue University（普渡大学）
Comments EMNLP 2025 Findings
CIE: Controlling Language Model Text Generations Using Continuous Signals
机构 * University of Maryland, College Park（马里兰大学 College Park分校） ； Carnegie Mellon University（卡内基梅隆大学）
Comments EMNLP Main 2025
GRPO-LEAD: A Difficulty-Aware Reinforcement Learning Approach for Concise Mathematical Reasoning in Language Models
机构 * Johns Hopkins University（约翰霍普金斯大学）
Comments Accepted to EMNLP 2025 (Main)
AfroXLMR-Social: Adapting Pre-trained Language Models for African Languages Social Media Text
机构 * Instituto Politécnico Nacional（智利国家理工学院） ； Saarland University（萨尔兰大学） ； Northeastern University（东北大学） ； Bayero University Kano（卡诺巴耶罗大学） ； Mila-Quebec AI Institute（魁北克AI研究所） ； McGill University（麦吉尔大学） ； University of Pretoria（比勒陀利亚大学） ； Bahir Dar University（巴赫达尔大学） ； Imperial College London（伦敦帝国理工学院） ； University of Hamburg（汉堡大学） ； Wollo University（沃尔洛大学）
Comments EMNLP 2025
ASTRA: A Negotiation Agent with Adaptive and Strategic Reasoning via Tool-integrated Action for Dynamic Offer Optimization
机构 * University of Southern California（美国南加州大学） ； St. Olaf College（圣奥拉夫学院） ； Northwestern University（西北大学） ； USC for Institute of Creative Technologies（美国南加州大学创意技术研究所）
Comments Accepted to EMNLP 2025 (Main Conference)
Re-Align: Aligning Vision Language Models via Retrieval-Augmented Direct Preference Optimization
机构 * Texas A&M University（德克萨斯大学） ； University of Michigan（密歇根大学） ； UIUC（伊利诺伊大学香槟分校） ； UNC Chapel Hill（北卡罗来纳大学教堂山分校）
Comments Published at EMNLP 2025
