NAACL

Bridging the Visual Gap: Fine-Tuning Multimodal Models with Knowledge-Adapted Captions

Moran Yanuka, Assaf Ben Kish, Yonatan Bitton, Idan Szpektor, Raja Giryes

机构 * Tel Aviv University（特拉维夫大学） ； Google Research（谷歌研究） 纠错

Comments Accepted to NAACL 2025

Journal ref Proceedings of the 2025 Conference of the North American Chapter of the Association for Computational Linguistics, Human Language Technologies, Long Papers, pp. 10497-10518

ReGLA: Refining Gated Linear Attention

Peng Lu, Ivan Kobyzev, Mehdi Rezagholizadeh, Boxing Chen, Philippe Langlais

机构 * DIRO, Université de Montréal（蒙特利尔大学DIRO） ； Huawei Noah’s Ark Lab（华为诺亚实验室） ； Advanced Micro Devices, Inc.（先进微器件公司） 纠错

Comments Accepted by NAACL 2025 (main)

Tree-of-Code: A Tree-Structured Exploring Framework for End-to-End Code Generation and Execution in Complex Task Handling

Ziyi Ni, Yifan Li, Ning Yang, Dou Shen, Pin Lv, Daxiang Dong

机构 * The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences（认知与决策智能复杂系统重点实验室，自动化研究所，中国科学院） ； School of Artificial Intelligence, University of Chinese Academy of Science（人工智能学院，中国科学院大学） ； Baidu, Inc.（百度公司） ； Global Innovation Exchange Institution, Tsinghua University（全球创新交换机构，清华大学） 纠错

Comments This idea was first submitted to the NeuralPS Workshop "System 2 Reasoning At Scale" in September 2024. Its OpenReview: https://openreview.net/forum?id=8NKAL8Ngxk&noteId=8NKAL8Ngxk. It was then submitted to the NAACL 2025 in October 2024, which is recorded in: https://openreview.net/forum?id=S0ZUWD3Vy5&noteId=S0ZUWD3Vy5. Now this paper has been accepted for publication in ACL 2025 Findings

Empowering Retrieval-based Conversational Recommendation with Contrasting User Preferences

Heejin Kook, Junyoung Kim, Seongmin Park, Jongwuk Lee

Comments NAACL 2025

Journal ref Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 7692-7707

Kill two birds with one stone: generalized and robust AI-generated text detection via dynamic perturbations

Yinghan Zhou, Juan Wen, Wanli Peng, Yiming Xue, Ziwei Zhang, Zhengxian Wu

机构 * China Agricultural University（中国农业大学） 纠错

Comments Accepted by NAACL 2025 main conference

Linear Relational Decoding of Morphology in Language Models

Eric Xia, Jugal Kalita

机构 * Brown University（布朗大学） ； University of Colorado Colorado Springs（科罗拉多州立大学） 纠错

Journal ref Proc. NAACL-HLT 2025 Student Research Workshop 4 (2025) 225-235

PerCul: A Story-Driven Cultural Evaluation of LLMs in Persian

Erfan Moosavi Monazzah, Vahid Rahimzadeh, Yadollah Yaghoobzadeh, Azadeh Shakery, Mohammad Taher Pilehvar

机构 * University of Tehran（德黑兰大学） ； Iran University of Science and Technology（伊朗科学技术大学） ； Tehran Institute for Advanced Studies（德黑兰高级研究 institute） ； Institute for Research in Fundamental Sciences (IPM)（基础科学研究 institute） ； Cardiff University（卡迪夫大学） 纠错

Comments Accepted at NAACL 2025 Main Conference, the dataset is available on HuggingFace (see https://huggingface.co/datasets/teias-ai/percul)

Journal ref 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) - Pages: 12670 - 12687

Evaluation of LLMs-based Hidden States as Author Representations for Psychological Human-Centered NLP Tasks

Nikita Soni, Pranav Chitale, Khushboo Singh, Niranjan Balasubramanian, H. Andrew Schwartz

机构 * Stony Brook University（石溪大学） 纠错

Comments To appear in Findings of NAACL 2025

Self-calibration for Language Model Quantization and Pruning

Miles Williams, George Chrysostomou, Nikolaos Aletras

Comments NAACL 2025

Journal ref 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)

DiPT: Enhancing LLM reasoning through diversified perspective-taking

Hoang Anh Just, Mahavir Dabas, Lifu Huang, Ming Jin, Ruoxi Jia

机构 * Virginia Tech（弗吉尼亚理工大学） ； UC Davis（加州大学戴维斯分校） 纠错

Comments LLM Reasoning with Perspectives, NAACL 2025 Findings

An Empirical Study of Validating Synthetic Data for Formula Generation

Usneek Singh, José Cambronero, Sumit Gulwani, Aditya Kanade, Anirudh Khatry, Vu Le, Mukul Singh, Gust Verbruggen

机构 * Microsoft Bangalore, India（微软印度班加罗尔） ； Google Atlanta, USA（谷歌美国亚特兰大） ； Microsoft Redmond, USA（微软美国雷德蒙德） ； University of Texas at Austin（德克萨斯大学奥斯汀） ； Microsoft Keerbergen, Belgium（微软比利时基尔伯根） 纠错

Comments Accepted at Findings of NAACL

TART: An Open-Source Tool-Augmented Framework for Explainable Table-based Reasoning

Xinyuan Lu, Liangming Pan, Yubo Ma, Preslav Nakov, Min-Yen Kan

机构 * National University of Singapore（新加坡国立大学） ； University of Arizona（亚利桑那大学） ； Nanyang Technology University（南洋理工大学） ； MBZUAI 纠错

Comments NAACL 2025 (Findings)

NormAd: A Framework for Measuring the Cultural Adaptability of Large Language Models

Abhinav Rao, Akhila Yerukola, Vishwa Shah, Katharina Reinecke, Maarten Sap

机构 * Language Technologies Institute, Carnegie Mellon University（卡内基梅隆大学语言技术研究所） ； Paul G. Allen School of Computer Science & Engineering, University of Washington（华盛顿大学保罗·G·艾伦计算机科学与工程学院） 纠错

Comments Published at NAACL 2025, Albuquerque, New Mexico, USA

Journal ref 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) 2373-2403

Gradient-guided Attention Map Editing: Towards Efficient Contextual Hallucination Mitigation

Yu Wang, Kamalika Das, Xiang Gao, Wendi Cui, Peng Li, Jiaxin Zhang

机构 * University of California, Santa Barbara（加州大学圣巴巴拉分校） ； Intuit AI Research（Intuit AI研究） 纠错

Comments Accepted as Finding of NAACL 2025

On Positional Bias of Faithfulness for Long-form Summarization

David Wan, Jesse Vig, Mohit Bansal, Shafiq Joty

机构 * UNC Chapel Hill（北卡罗来纳大学教堂山分校） ； Salesforce AI Research（Salesforce人工智能研究） 纠错

Comments NAACL 2025 (20 pages)

From Intentions to Techniques: A Comprehensive Taxonomy and Challenges in Text Watermarking for Large Language Models

Harsh Nishant Lalai, Aashish Anantha Ramakrishnan, Raj Sanjay Shah, Dongwon Lee

机构 * Birla Institute of Technology and Science, Pilani（比拉理工学院和科学学院，比里尼） 纠错

Comments NAACL Findings 2025

GenSim: A General Social Simulation Platform with Large Language Model based Agents

Jiakai Tang, Heyang Gao, Xuchen Pan, Lei Wang, Haoran Tan, Dawei Gao, Yushuo Chen, Xu Chen, Yankai Lin, Yaliang Li, Bolin Ding, Jingren Zhou, Jun Wang, Ji-Rong Wen

机构 * Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学全球化人工智能学院） ； University College London（伦敦大学学院） ； Alibaba Group（阿里巴巴集团） 纠错

Comments NAACL 2025 Demo Track

MALIBU Benchmark: Multi-Agent LLM Implicit Bias Uncovered

Imran Mirza, Cole Huang, Ishwara Vasista, Rohan Patil, Asli Akalin, Sean O'Brien, Kevin Zhu

机构 * Algoverse AI Research（Algoverse AI研究院） 纠错

Comments Accepted to Building Trust in LLMs @ ICLR 2025 and NAACL SRW 2025

Is Your LLM Outdated? A Deep Look at Temporal Generalization

Chenghao Zhu, Nuo Chen, Yufei Gao, Yunyi Zhang, Prayag Tiwari, Benyou Wang

机构 * The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）） ； Shenzhen Research Institute of Big Data（深圳大数据研究院） ； Halmstad University（哈马碧大学） 纠错

Comments NAACL 2025 Oral

Journal ref 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) (2025) 7433-7457

KMI: A Dataset of Korean Motivational Interviewing Dialogues for Psychotherapy

Hyunjong Kim, Suyeon Lee, Yeongjae Cho, Eunseo Ryu, Yohan Jo, Suran Seong, Sungzoon Cho

机构 * Seoul National University（首尔国立大学） ； Korea Counseling Graduate University（韩国咨询研究生大学） 纠错

Comments Accepted at NAACL 2025 Main Conference

K-COMP: Retrieval-Augmented Medical Domain Question Answering With Knowledge-Injected Compressor

Jeonghun Cho, Gary Geunbae Lee

机构 * POSTECH（POSTECH大学） ； GSAI ； POSTECH CSE（POSTECH计算机科学与工程系） 纠错

Comments Accepted at NAACL 2025 (Main, long paper)

Introducing MAPO: Momentum-Aided Gradient Descent Prompt Optimization

Anthony Cui, Pranav Nandyalam, Andrew Rufail, Ethan Cheung, Aiden Lei, Kevin Zhu, Sean O'Brien

机构 * Algoverse AI Research（Algoverse AI研究院） 纠错

Comments Accepted to NAACL SRW 2025. A few revisions since last version

Prompting with Phonemes: Enhancing LLMs' Multilinguality for Non-Latin Script Languages

Hoang H Nguyen, Khyati Mahajan, Vikas Yadav, Julian Salazar, Philip S. Yu, Masoud Hashemi, Rishabh Maheshwary

机构 * University of Illinois at Chicago（伊利诺伊大学芝加哥分校） ； ServiceNow ； Google DeepMind（谷歌DeepMind） 纠错

Comments Accepted to NAACL 2025 (Main Conference). This version contains minor improvements to the camera-ready

Journal ref 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)

Hybrid AI for Responsive Multi-Turn Online Conversations with Novel Dynamic Routing and Feedback Adaptation

Priyaranjan Pattnayak, Amit Agarwal, Hansa Meghwani, Hitesh Laxmichand Patel, Srikant Panda

机构 * OCI, Oracle America Inc.（Oracle美洲公司） ； OCI, Oracle India（Oracle印度公司） 纠错

Comments Proceedings of the 4th International Workshop on Knowledge Augmented Methods for Natural Language Processing in NAACL 2025, pages 215 to 229, Albuquerque, New Mexico, USA. Association for Computational Linguistics

Journal ref Proceedings of the 4th International Workshop on Knowledge-Augmented Methods for Natural Language Processing (KnowledgeNLP 2025), pp. 215 to 229, Association for Computational Linguistics, Albuquerque, New Mexico, May 2025

Faux Polyglot: A Study on Information Disparity in Multilingual Large Language Models

Nikhil Sharma, Kenton Murray, Ziang Xiao

机构 * Johns Hopkins University（约翰霍普金斯大学） ； Center for Speech and Language Processing（语言与语音研究中心） ； Human Language Technology Center for Excellence（语言技术卓越中心） 纠错

Comments NAACL 2025

DiscoGraMS: Enhancing Movie Screen-Play Summarization using Movie Character-Aware Discourse Graph

Maitreya Prafulla Chitale, Uday Bindal, Rajakrishnan Rajkumar, Rahul Mishra

机构 * IIIT Hyderabad（海得拉巴印度理工学院） 纠错

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

A Closer Look into Mixture-of-Experts in Large Language Models

Ka Man Lo, Zeyu Huang, Zihan Qiu, Zili Wang, Jie Fu

机构 * University of Macau（澳门大学） ； University of Edinburgh（爱丁堡大学） ； Tsinghua University（清华大学） ； INF Technology（INF技术） ； Shanghai AI Lab（上海人工智能实验室） 纠错

Comments NAACL 2025 Findings

HiURE: Hierarchical Exemplar Contrastive Learning for Unsupervised Relation Extraction

Shuliang Liu, Xuming Hu, Chenwei Zhang, Shu`ang Li, Lijie Wen, Philip S. Yu

机构 * Tsinghua University（清华大学） ； Amazon（亚马逊） ； University of Illinois at Chicago（伊利诺伊大学香槟分校） 纠错

Comments In NAACL 2022 as a long paper. Code and data available at https://github.com/THU-BPM/HiURE

Journal ref Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics

Mustango: Toward Controllable Text-to-Music Generation

Jan Melechovsky, Zixun Guo, Deepanway Ghosal, Navonil Majumder, Dorien Herremans, Soujanya Poria

Comments NAACL 2024

Journal ref Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL) (Volume 1: Long Papers)

Ask Optimal Questions: Aligning Large Language Models with Retriever's Preference in Conversation

Chanwoong Yoon, Gangwoo Kim, Byeongguk Jeon, Sungdong Kim, Yohan Jo, Jaewoo Kang

机构 * Korea University（韩国大学） ； KAIST AI（韩国科学技术院人工智能研究中心） ； Seoul National University（首尔国立大学） ； AIGEN Sciences（AIGEN科学） 纠错

Comments NAACL 2025 (findings)