Ranked Voting based Self-Consistency of Large Language Models
机构 * College of Computer Science and Software Engineering, Shenzhen University（深圳大学计算机科学与软件工程学院）
Comments ACL 2025 Findings
期刊&会议
ACL
Annual Meeting of the Association for Computational Linguistics · 会议 · Natural Language Processing
LDIR: Low-Dimensional Dense and Interpretable Text Embeddings with Relative Representations
机构 * College of Computer Science and Software Engineering, Shenzhen University（计算机科学与软件工程学院，深圳大学）
Comments ACL 2025 Findings
From Trade-off to Synergy: A Versatile Symbiotic Watermarking Framework for Large Language Models
机构 * Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所） ； School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络安全学院） ； Hainan Province Fang Binxing Academician Workstation（海南省方斌星院士工作站）
Comments Accepted to ACL 2025 (main)
PIG: Privacy Jailbreak Attack on LLMs via Gradient-based Iterative In-Context Optimization
机构 * Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所） ； School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络安全学院） ； Cyberspace Institute of Advanced Technology, Guangzhou University（广州大学网络空间技术研究院）
Comments Accepted to ACL 2025 (main)
Call for Rigor in Reporting Quality of Instruction Tuning Data
机构 * Department of Computer Science and Engineering, Korea University（韩国大学计算机科学与工程系）
Comments Accepted to the ACL2025-main
When to Speak, When to Abstain: Contrastive Decoding with Abstention
机构 * Seoul National University（首尔国立大学） ； IntelliSys ； Hanyang University（翰阳大学）
Comments ACL 2025 (main)
MergePrint: Merge-Resistant Fingerprints for Robust Black-box Ownership Verification of Large Language Models
机构 * Institute of Science Tokyo（东京科学研究所） ； The University of Tokyo（东京大学） ； SB Intuitions
Comments Accepted at ACL 2025 Main
Self-Tuning: Instructing LLMs to Effectively Acquire New Knowledge through Self-Teaching
机构 * The Chinese University of Hong Kong（香港中文大学） ； Tencent AI Lab（腾讯AI实验室） ； Centre for Perceptual and Interactive Intelligence（感知与交互智能中心）
Comments ACL 2025 Findings
Fourier Transformer: Fast Long Range Modeling by Removing Sequence Redundancy with FFT Operator
机构 * Shanghai Jiao Tong University（上海交通大学） ； Netease BizEase（网易商业Ease）
Journal ref Findings of the Association for Computational Linguistics: ACL 2023
Context-aware Stand-alone Neural Spelling Correction
Comments 8 pages, 5 tables, 1 figure. Findings of the Association for Computational Linguistics: EMNLP 2020
Journal ref https://aclanthology.org/2020.findings-emnlp.37/
Scientific Discourse Tagging for Evidence Extraction
Comments Accepted by The 16th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2021). 9 pages of main texts, 3 pages of references and 1 page of supportive information. 6 figures and 6 tables
Journal ref https://aclanthology.org/2021.eacl-main.218/
MathCoder-VL: Bridging Vision and Code for Enhanced Multimodal Mathematical Reasoning
机构 * Multimedia Laboratory (MMLab)（多媒体实验室） ； The Chinese University of Hong Kong（香港中文大学） ； CPII under InnoHK（创新香港科技署CPII）
Comments Accepted to ACL 2025 Findings
Can You Really Trust Code Copilots? Evaluating Large Language Models from a Code Security Perspective
机构 * National Engineering Research Center for Software Engineering, Peking University, China（软件工程国家工程研究中心，北京大学）
Comments Accepted by ACL2025 Main Conference
Rethinking Repetition Problems of LLMs in Code Generation
Comments Accepted to ACL 2025 (main)
Not All Adapters Matter: Selective Adapter Freezing for Memory-Efficient Fine-Tuning of Language Models
机构 * Korea University（韩国大学） ； Arizona State University（亚利桑那州立大学） ； Soongsil University（顺天大学）
Comments URL: https://aclanthology.org/2025.naacl-long.480/ Volume: Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) Year: 2025 Address: Albuquerque, New Mexico
Disentangling Memory and Reasoning Ability in Large Language Models
机构 * Rutgers University（罗格斯大学） ； The Ohio State University（俄亥俄州立大学） ； University of California, Santa Barbara（加州大学圣巴巴拉分校）
Comments Accepted by ACL 2025
MultiMed: Multilingual Medical Speech Recognition via Attention Encoder Decoder
机构 * University of Toronto（多伦多大学） ； University Health Network（大学健康网络） ； Knovel Engineering Lab（Knovel工程实验室） ； FPT University（佛邦大学） ； Florida Institute of Technology（佛罗里达技术学院） ； KU Leuven（鲁文大学） ； VNU University of Engineering and Technology（越南工程与技术大学） ； Johns Hopkins University（约翰霍普金斯大学） ； University of Alabama at Birmingham（阿拉巴马大学伯明翰分校）
Comments ACL 2025, 38 pages
Scaling Context, Not Parameters: Training a Compact 7B Language Model for Efficient Long-Context Processing
机构 * Amazon Web Services（亚马逊网络服务）
Comments 8 pages, 6 figures, ACL 2025 (Industry Track)
LLMSR@XLLM25: Less is More: Enhancing Structured Multi-Agent Reasoning via Quality-Guided Distillation
机构 * First Author Affiliation（第一作者机构） ； Second Author Affiliation（第二作者机构）
Comments XLLM @ ACL 2025 Shared Task-III: LLM for Structural Reasoning (LLM-SR)
Through the Looking Glass: Common Sense Consistency Evaluation of Weird Images
机构 * Skoltech（斯克利切夫斯克技术大学） ； AIRI（人工智能研究所） ； MTS AI（MTS人工智能） ； Moscow Institute of Physics and Technology（莫斯科物理技术学院）
Journal ref Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)
QUPID: Quantified Understanding for Enhanced Performance, Insights, and Decisions in Korean Search Engines
机构 * Naver Corporation（纳维尔公司）
Journal ref ACL 2025 Industry Track
Order Matters in Hallucination: Reasoning Order as Benchmark and Reflexive Prompting for Large-Language-Models
机构 * University of Science and Technology of China（中国科学技术大学）
Comments 8 pages, submitted to ACL ARR
Attention on Multiword Expressions: A Multilingual Study of BERT-based Models with Regard to Idiomaticity and Microsyntax
机构 * Saarland University（萨尔兰大学）
Comments 10 pages, 3 figures. Findings 2025
Journal ref In Findings of the Association for Computational Linguistics: NAACL 2025, pages 4083–4092, Albuquerque, New Mexico https://aclanthology.org/2025.findings-naacl.228/
Unilogit: Robust Machine Unlearning for LLMs Using Uniform-Target Self-Distillation
机构 * eBay Inc.（eBay公司） ； University of Amsterdam（阿姆斯特丹大学）
Comments 16 pages, 6 figures, 5 tables, under review at ACL
ReLiK: Retrieve and LinK, Fast and Accurate Entity Linking and Relation Extraction on an Academic Budget
机构 * Sapienza NLP Group, Sapienza University of Rome（罗马萨皮恩扎大学萨皮恩扎自然语言处理小组）
Comments Findings of the Association for Computational Linguistics ACL 2024
Atyaephyra at SemEval-2025 Task 4: Low-Rank Negative Preference Optimization
机构 * Charles University, Faculty of Mathematics and Physics（查理大学数学与物理学院）
Comments 8 pages, 3 figures, accepted to SemEval workshop proceedings at ACL 2025
A Fast Algorithm for Computing Prefix Probabilities
Comments Corrected typos, changed the layout of the algorithms, and improved appendix B on the semiring version of the algorithm
Journal ref Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics, Volume 2: Short Papers, pages 57-67, 2003
XrayGPT: Chest Radiographs Summarization using Medical Vision-Language Models
机构 * Mohamed bin Zayed University of AI（穆罕默德·本·扎耶德人工智能大学） ； Aalto University（艾尔沃斯大学）
Comments Accepted at ACL 2024-BIONLP Workshop. Code: https://github.com/mbzuai-oryx/XrayGPT
LibEvolutionEval: A Benchmark and Study for Version-Specific Code Generation
机构 * AWS AI Labs（AWS人工智能实验室） ； NVIDIA（英伟达）
Journal ref Proceedings of the 2025 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Albuquerque, New Mexico, USA, April 2-7, 2025
ELECTRA and GPT-4o: Cost-Effective Partners for Sentiment Analysis
机构 * Stanford Engineering CGOE（斯坦福工程学院）
Comments 19 pages, 4 figures. Source code and data available at https://github.com/jbeno/sentiment
Journal ref Proceedings of the 4th International Workshop on Knowledge-Augmented Methods for Natural Language Processing, Association for Computational Linguistics, Albuquerque, New Mexico, USA (2025) 18-36
