heiDS at ArchEHR-QA 2025: From Fixed-k to Query-dependent-k for Retrieval Augmented Generation
Comments 12 pages, 2 figures, 6 tables, Workshop on BioNLP and Shared Tasks at ACL 2025
期刊&会议
ACL
Annual Meeting of the Association for Computational Linguistics · 会议 · Natural Language Processing
Spotting Out-of-Character Behavior: Atomic-Level Evaluation of Persona Fidelity in Open-Ended Generation
机构 * School of Computing（计算机学院） ； Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院）
Comments Findings of ACL 2025; github repo: https://github.com/ddindidu/atomic-persona-evaluation/
Prompt, Translate, Fine-Tune, Re-Initialize, or Instruction-Tune? Adapting LLMs for In-Context Learning in Low-Resource Languages
机构 * University of California, Irvine（加州大学尔湾分校） ； University of California, Santa Cruz（加州大学圣克ruz分校）
Comments Accepted to ACL GEM 2025
Small Language Models in the Real World: Insights from Industrial Text Classification
机构 * University of Luxembourg（卢森堡大学） ； Foyer S.A.（foyer 公司）
Comments This paper has been accepted as a conference paper in the Industry Track of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL)
Analyzing LLMs' Knowledge Boundary Cognition Across Languages Through the Lens of Internal Representations
机构 * DAMO Academy, Alibaba Group（阿里巴巴集团达摩院） ； Department of Computer Science, Durham University（杜伦大学计算机科学系） ； Hupan Lab, Hangzhou, China（杭州实验室）
Comments ACL 2025 main; camera ready
Local Look-Ahead Guidance via Verifier-in-the-Loop for Automated Theorem Proving
机构 * Language Technology Lab, University of Amsterdam（阿姆斯特丹大学语言技术实验室） ； Qualcomm AI Research（高通人工智能研究）
Comments Accepted at the Findings of ACL 2025, Accepted at ICLR 2025 Workshop on Reasoning and Planning for Large Language Models
PATCH! {P}sychometrics-{A}ssis{T}ed Ben{CH}marking of Large Language Models against Human Populations: A Case Study of Proficiency in 8th Grade Mathematics
机构 * Utrecht University（乌特雷赫大学）
Comments Accepted to GEM2 Workshop: Generation, Evaluation & Metrics - ACL 2025
EMULATE: A Multi-Agent Framework for Determining the Veracity of Atomic Claims by Emulating Human Actions
机构 * National University of Singapore（新加坡国立大学）
Comments FEVER 2025 (co-located with ACL 2025)
SEAL: Scaling to Emphasize Attention for Long-Context Retrieval
机构 * Department of Convergence IT Engineering（融合IT工程系） ； Department of Computer Science and Engineering（计算机科学与工程系） ； Graduate School of Artificial Intelligence（人工智能研究生院）
Comments Accepted at ACL 2025 Main
InspireDebate: Multi-Dimensional Subjective-Objective Evaluation-Guided Reasoning and Optimization for Debating
机构 * Key Laboratory of Embedded System and Service Computing, Ministry of Education, Tongji University（嵌入式系统与服务计算重点实验室，教育部，同济大学） ； School of Computer Science and Technology, Tongji University（计算机科学与技术学院，同济大学）
Comments 20 pages; Accepted to ACL 2025 Main
A Comprehensive Graph Framework for Question Answering with Mode-Seeking Preference Alignment
Comments acl 2025 findings
Zero-Shot Conversational Stance Detection: Dataset and Approaches
机构 * Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University（航空信息安全与可信计算重点实验室、教育部、网络安全科学与工程学院、武汉大学）
Comments ACL 2025 (Findings)
SWE-Dev: Building Software Engineering Agents with Training and Inference Scaling
Comments Accepted to Findings of ACL'25
Dual Debiasing for Noisy In-Context Learning for Text Generation
机构 * University of Michigan Ann Arbor（密歇根大学安娜堡分校）
Comments Accepted by 2025 ACL Findings
Language Models Grow Less Humanlike beyond Phase Transition
Comments Accepted to ACL 2025
HiddenDetect: Detecting Jailbreak Attacks against Large Vision-Language Models via Monitoring Hidden States
机构 * MMLab, The Chinese University of Hong Kong（中文大学香港大学） ； Future Lab, Alibaba Group（阿里集团未来实验室）
Comments Accepted by ACL 2025 (Main)
Cramming 1568 Tokens into a Single Vector and Back Again: Exploring the Limits of Embedding Space Capacity
机构 * AIRI ； Neural Networks and Deep Learning Lab, MIPT（神经网络与深度学习实验室，MIPT） ； London Institute for Mathematical Sciences（伦敦数学科学研究所）
Comments ACL 2025 (main conference)
PlanGenLLMs: A Modern Survey of LLM Planning Capabilities
机构 * University of California, Merced（加州大学梅尔德分校） ； Emory University（埃默里大学） ； PAII Inc.（PAII公司）
Comments Accepted by ACL 2025
Factual Knowledge in Language Models: Robustness and Anomalies under Simple Temporal Context Variations
Comments preprint v6, accepted for publication at ACL 2025 - L2M2 Workshop
GeAR: Graph-enhanced Agent for Retrieval-augmented Generation
Comments ACL 2025 Findings
DiscoGraMS: Enhancing Movie Screen-Play Summarization using Movie Character-Aware Discourse Graph
机构 * IIIT Hyderabad（海得拉巴印度理工学院）
Comments Accepted at NAACL 2025 (Main)
Journal ref In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers), pages 954 - 965, Albuquerque, New Mexico, April 2025
How Numerical Precision Affects Arithmetical Reasoning Capabilities of LLMs
机构 * State Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University（通用人工智能国家重点实验室，智能科学与技术学院，北京大学） ； School of EECS, Peking University（电子工程系，北京大学） ； Huawei Noah’s Ark Lab（华为诺亚实验室） ； Center for Machine Learning Research, Peking University（机器学习研究中心，北京大学）
Comments 40 pages, 4 figures, ACL 2025 Findings
Circuit Compositions: Exploring Modular Structures in Transformer-Based Language Models
机构 * MaiNLP, Center for Information and Language Processing, LMU Munich（MaiNLP、信息与语言处理中心、慕尼黑大学） ； Munich Center for Machine Learning (MCML), Munich（慕尼黑机器学习中心） ； Language Technology Group, University of Oslo（语言技术组、奥斯陆大学）
Comments ACL 2025 main, 22 pages, 21 figures
Multilingual Retrieval Augmented Generation for Culturally-Sensitive Tasks: A Benchmark for Cross-lingual Robustness
机构 * University of Pennsylvania（宾夕法尼亚大学）
Comments ACL 2025 (Findings)
Reasoning Circuits in Language Models: A Mechanistic Interpretation of Syllogistic Inference
机构 * Department of Computer Science, University of Manchester, UK（英国曼彻斯特大学计算机科学系） ； Idiap Research Institute, Switzerland（瑞士Idiap研究所） ； School of Computer Science, University of Sheffield, UK（英国谢菲尔德大学计算机科学学院） ； National Biomarker Centre, CRUK-MI, University of Manchester, UK（英国曼彻斯特大学国家生物标志物中心）
Comments Accepted to Findings of ACL 2025
Advancing African-Accented Speech Recognition: Epistemic Uncertainty-Driven Data Selection for Generalizable ASR Models
机构 * McGill University（麦吉尔大学） ； Mila Quebec AI Institute（魁北克AI研究所）
Comments Accepted at ACL SRW 2025
PRAISE: Enhancing Product Descriptions with LLM-Driven Structured Insights
机构 * IIIT Hyderabad（IIIT海得拉尔学院） ； University of Delaware（德雷塞尔大学） ； University of Pennsylvania（宾夕法尼亚大学） ； Arizona State University（亚利桑那州立大学）
Comments 9 Pages, 9 Figures. Accepted at ACL 2025 System Demonstration Track
Are Bias Evaluation Methods Biased ?
机构 * First Author Affiliation（第一作者机构） ； Second Author Affiliation（第二作者机构）
Comments Accepted to ACL 2025 Workshop GEM
From Data to Knowledge: Evaluating How Efficiently Language Models Learn Facts
机构 * Humboldt-Universität zu Berlin（柏林洪堡大学） ； Science Of Intelligence（智能科学）
Comments Accepted to the First Workshop on Large Language Model Memorization (L2M2), co-located with ACL 2025 in Vienna
Revisiting LoRA through the Lens of Parameter Redundancy: Spectral Encoding Helps
机构 * The Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州））
Comments 18 pages; Accepted to ACL 2025 Findings
