VoiceBBQ: Investigating Effect of Content and Acoustics in Social Bias of Spoken Language Model
Comments Accepted EMNLP 2025 main
期刊&会议
EMNLP
Conference on Empirical Methods in Natural Language Processing · 会议 · Natural Language Processing
CafGa: Customizing Feature Attributions to Explain Language Models
Comments 6 Pages (excl. bibliography and appendix), 5 Figures and 2 Tables. Will be presented at EMNLP 2025 (Demo Track)
Distilling Many-Shot In-Context Learning into a Cheat Sheet
机构 * CyberAgent
Comments Accepted to EMNLP 2025 (Findings)
Leveraging What's Overfixed: Post-Correction via LLM Grammatical Error Overcorrection
机构 * Graduate School of Artificial Intelligence, POSTECH, South Korea（POSTECH人工智能研究生院） ； ETH Zurich, ETH AI Center（苏黎世联邦理工学院人工智能中心） ； Department of Computer Science and Engineering, POSTECH, South Korea（POSTECH计算机科学与工程系）
Comments EMNLP 2025
Seeing Through Words, Speaking Through Pixels: Deep Representational Alignment Between Vision and Language Models
机构 * Department of Cognitive Science University of California, San Diego（认知科学系，加州大学圣地亚哥分校）
Comments Accepted at EMNLP 2025 (camera-ready)
Overcoming Black-box Attack Inefficiency with Hybrid and Dynamic Select Algorithms
机构 * Department of Computer Science（计算机科学系） ； Purdue University（普渡大学）
Comments 34 pages, 3 figures, Accepted to Findings of EMNLP 2025
RedHerring Attack: Testing the Reliability of Attack Detection
机构 * Purdue University, Fort Wayne（普渡大学，弗朗西斯维尔）
Comments 16 pages, 3 figures, Accepted to EMNLP 2025
Can Federated Learning Safeguard Private Data in LLM Training? Vulnerabilities, Attacks, and Defense Evaluation
机构 * State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China（虚拟现实技术与系统国家重点实验室，计算机科学与工程学院，北京航空航天大学） ； Hangzhou Innovation Institute of Beihang University, Zhejiang Key Laboratory of Industrial Big Data and Robot Intelligent Systems, Hangzhou, China（北京航空航天大学杭州创新研究院，浙江省工业大数据与机器人智能系统重点实验室） ； Center for AI Business Innovation, Department of Management Science and Systems, University at Buffalo, Buffalo, New York, USA（人工智能商业创新中心，管理科学与系统系，布法罗大学） ； University of North Texas, Denton, Texas, USA（德克萨斯大学达文波特分校） ； Zhongguancun Laboratory, Beijing, China（中关村实验室）
Comments 28 pages, 32 figures, accepted to the Findings of EMNLP 2025
SAMULE: Self-Learning Agents Enhanced by Multi-level Reflection
机构 * AWS AI Labs（AWS人工智能实验室）
Comments Accepted at EMNLP 2025 Main Conference
ZERA: Zero-init Instruction Evolving Refinement Agent -- From Zero Instructions to Structured Prompts via Principle-based Optimization
机构 * Upstage AI Research（Upstage人工智能研究院）
Comments 9 pages, 4 figures. To appear in EMNLP 2025 Main Conference (Oral Presentation)
TactfulToM: Do LLMs Have the Theory of Mind Ability to Understand White Lies?
机构 * EPFL（苏黎世联邦理工学院） ； Tampere University（塔尔库大学） ； University of Tokyo（东京大学） ； National Institute of Informatics（信息研究所）
Comments Accepted to EMNLP 2025
LM-Searcher: Cross-domain Neural Architecture Search with LLMs via Unified Numerical Encoding
机构 * CUHK MMLab（香港中文大学MML实验室） ； CUHK CURI（香港中文大学CURI） ； Tsinghua University（清华大学） ； Shanghai AI Laboratory（上海人工智能实验室） ； CPII under InnoHK（创新香港下的CPII）
Comments EMNLP 2025 Main
MathBuddy: A Multimodal System for Affective Math Tutoring
机构 * IT:U Interdisciplinary Transformation University Austria（奥地利 interdisciplinary Transformation 大学） ； IBM Research India（印度 IBM 研究院）
Comments Accepted at EMNLP 2025 (Demo Track)
THCM-CAL: Temporal-Hierarchical Causal Modelling with Conformal Calibration for Clinical Risk Prediction
机构 * The University of Manchester（曼彻斯特大学） ； Harbin Institute of Technology（哈尔滨工业大学）
Comments Accepted at EMNLP 2025
ConsistentChat: Building Skeleton-Guided Consistent Multi-Turn Dialogues for Large Language Models from Scratch
机构 * Chinese Information Processing Laboratory, Institute of Software, Chinese Academy of Sciences, Beijing, China（中国科学院软件研究所中文信息处理实验室） ； University of Chinese Academy of Sciences, Beijing, China（中国科学院大学）
Comments EMNLP 2025 Main Conference (Oral Presentation)
BabyLM's First Constructions: Causal probing provides a signal of learning
Comments Accepted to EMNLP 2025
VideoPASTA: 7K Preference Pairs That Matter for Video-LLM Alignment
机构 * Arizona State University（亚利桑那州立大学）
Comments EMNLP 2025 (Main)
On the Perception Bottleneck of VLMs for Chart Understanding
机构 * The Hong Kong University of Science and Technology（香港理工大学）
Comments EMNLP 2025: Camera-ready version
Constructions are Revealed in Word Distributions
机构 * Stanford University（斯坦福大学） ； Uppsala University（乌普萨拉大学） ； The University of Texas at Austin（德克萨斯大学奥斯汀分校）
Comments Accepted to EMNLP 2025
Scaling Rich Style-Prompted Text-to-Speech Datasets
机构 * Department of Computer Science, The University of Texas at Austin（德克萨斯大学奥斯汀分校计算机科学系） ； Department of Computer Science and Data Science, New York University（纽约大学计算机科学与数据科学系）
Comments EMNLP 2025
The Validation Gap: A Mechanistic Analysis of How Language Models Compute Arithmetic but Fail to Validate It
机构 * DISI, University of Trento（特伦托大学DISI中心） ； MaiNLP, Center for Information and Language Processing, LMU Munich（慕尼黑大学信息与语言处理中心） ； Munich Center for Machine Learning (MCML), Munich, Germany（慕尼黑机器学习中心） ； Free University of Bozen-Bolzano, Italy（博兹纳自由大学）
Comments EMNLP 2025 Main, 38 pages, 33 figures
Context-Aware Reasoning On Parametric Knowledge for Inferring Causal Variables
机构 * CISPA Helmholtz Center for Information Security（CISPA 欧洲信息安全中心） ； Microsoft（微软公司）
Comments EMNLP'25 Findings
Interdisciplinary Research in Conversation: A Case Study in Computational Morphology for Language Documentation
Comments Accepted to EMNLP 2025
Procedural Environment Generation for Tool-Use Agents
机构 * Department of Language Science and Technology（语言科学与技术系） ； Saarland Informatics Campus（萨尔兰信息学校区） ； Saarland University（萨尔兰大学）
Comments 16 pages, 3 figures; accepted at EMNLP 2025
DISCO Balances the Scales: Adaptive Domain- and Difficulty-Aware Reinforcement Learning on Imbalanced Data
Comments Accepted by EMNLP 2025 Findings
LLMs Reproduce Stereotypes of Sexual and Gender Minorities
机构 * University of Edinburgh（爱丁堡大学）
Comments 13 pages, 5 figures, 9 tables (including bibliography and appendix). Accepted to Findings of EMNLP 2025
UNComp: Can Matrix Entropy Uncover Sparsity? -- A Compressor Design from an Uncertainty-Aware Perspective
Comments Accepted at EMNLP 2025 (Main Conference)
Probing Gender Bias in Multilingual LLMs: A Case Study of Stereotypes in Persian
Comments Accepted and forthcoming at the Widening Natural Language Processing Workshop (WiNLP 2025) at EMNLP 2025
Less is More: The Effectiveness of Compact Typological Language Representations
机构 * University of Toronto（多伦多大学） ； Ontario Tech University（安大略技术大学）
Comments Accepted to EMNLP 2025 Main Conference
Causal Understanding by LLMs: The Role of Uncertainty
机构 * SUPSI, IDSIA（瑞士SUPSI和IDSIA）
Comments Accepted in second UncertaiNLP workshop at EMNLP 2025
