NAACL

A Closer Look at Adversarial Suffix Learning for Jailbreaking LLMs: Augmented Adversarial Trigger Learning

深入研究对抗后缀学习用于劫持大语言模型：增强的对抗触发学习

Zhe Wang, Yanjun Qi

机构 * University of Virginia（弗吉尼亚大学） 纠错

AI总结 ATLA通过增强的对抗触发学习方法，高效生成劫持大语言模型的后缀并提取隐藏系统提示，实现高成功率和低查询消耗。

Comments the Association for Computational Linguistics: NAACL 2025

Journal ref https://aclanthology.org/2025.findings-naacl.394/

Dialetto, ma Quanto Dialetto? Transcribing and Evaluating Dialects on a Continuum

Ryan Soh-Eun Shim, Barbara Plank

机构 * MaiNLP, Center for Information and Language Processing, LMU Munich（MaiNLP语言信息处理中心，慕尼黑大学） ； Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心） 纠错

Comments Published in NAACL 2025 findings

EmoDynamiX: Emotional Support Dialogue Strategy Prediction by Modelling MiXed Emotions and Discourse Dynamics

Chenwei Wan, Matthieu Labeau, Chloé Clavel

机构 * LTCI, Télécom Paris, Institut Polytechnique de Paris（LTCI，Telecom Paris， Institut Polytechnique de Paris） ； Inria Paris（Inria巴黎） 纠错

Comments Accepted to NAACL 2025 main, long paper

Planetarium: A Rigorous Benchmark for Translating Text to Structured Planning Languages

Max Zuo, Francisco Piedrahita Velez, Xiaochen Li, Michael L. Littman, Stephen H. Bach

机构 * Brown University（布朗大学） 纠错

Comments NAACL Main Conference 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)

LLM-C3MOD: A Human-LLM Collaborative System for Cross-Cultural Hate Speech Moderation

Junyeong Park, Seogyeong Jeong, Seyoung Song, Yohan Lee, Alice Oh

Comments Accepted to NAACL 2025 Workshop - C3NLP (Workshop on Cross-Cultural Considerations in NLP)

MobA: Multifaceted Memory-Enhanced Adaptive Planning for Efficient Mobile Task Automation

Zichen Zhu, Hao Tang, Yansi Li, Dingye Liu, Hongshen Xu, Kunyao Lan, Danyang Zhang, Yixuan Jiang, Hao Zhou, Chenrun Wang, Situo Zhang, Liangtai Sun, Yixiao Wang, Yuheng Sun, Lu Chen, Kai Yu

机构 * Shanghai Jiao Tong University（上海交通大学） 纠错

Comments NAACL 2025 Demo Track [code] https://github.com/OpenDFM/MobA [dataset] https://huggingface.co/datasets/OpenDFM/MobA-MobBench

Unmask It! AI-Generated Product Review Detection in Dravidian Languages

Somsubhra De, Advait Vats

机构 * Indian Institute of Technology Madras（印度理工学院马德拉斯学院） 纠错

Comments 10 pages, 9 figures, Accepted to DravidianLangTech Workshop proceedings at NAACL 2025

Iterative Self-Tuning LLMs for Enhanced Jailbreaking Capabilities

Chung-En Sun, Xiaodong Liu, Weiwei Yang, Tsui-Wei Weng, Hao Cheng, Aidan San, Michel Galley, Jianfeng Gao

Comments Accepted to NAACL 2025 Main (Oral)

FUSE : A Ridge and Random Forest-Based Metric for Evaluating MT in Indigenous Languages

Rahul Raja, Arpita Vats

机构 * Carnegie Mellon University（卡内基梅隆大学） ； Stanford University（斯坦福大学） ； Boston University（波士顿大学） ； Santa Clara University（圣克拉拉大学） 纠错

Comments NAACL 2025 Workshop on NLP for Indigenous Languages of the Americas

Multilingual State Space Models for Structured Question Answering in Indic Languages

Arpita Vats, Rahul Raja, Mrinal Mathur, Vinija Jain, Aman Chadha

机构 * Santa Clara University（圣克拉拉大学） ； Carnegie Mellon University（卡内基梅隆大学） ； Georgia Institute of Technology（佐治亚理工学院） ； Stanford University（斯坦福大学） 纠错

Comments NAACL 2025 Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT)

FIRE: Fact-checking with Iterative Retrieval and Verification

Zhuohan Xie, Rui Xing, Yuxia Wang, Jiahui Geng, Hasan Iqbal, Dhruv Sahnan, Iryna Gurevych, Preslav Nakov

机构 * MBZUAI ； The University of Melbourne（墨尔本大学） 纠错

Comments 4 figures, 8 tables, accepted to Findings of NAACL

Towards Region-aware Bias Evaluation Metrics

Angana Borah, Aparna Garimella, Rada Mihalcea

机构 * University of Michigan（密歇根大学） ； Adobe Research（Adobe研究） 纠错

Comments Accepted to Cross-Cultural Considerations in NLP (C3NLP Workshop at NAACL 2025) -- Outstanding Paper Award

Rationale-Guided Retrieval Augmented Generation for Medical Question Answering

Jiwoong Sohn, Yein Park, Chanwoong Yoon, Sihyeon Park, Hyeon Hwang, Mujeen Sung, Hyunjae Kim, Jaewoo Kang

机构 * Korea University（韩国大学） ； Kyung Hee University（庆熙大学） ； AIGEN Sciences（AIGEN公司） 纠错

Comments Accepted to NAACL 2025 (Oral)

Neuro-symbolic Training for Reasoning over Spatial Language

Tanawan Premsri, Parisa Kordjamshidi

机构 * Department of Computer Science Michigan State University（计算机科学系密歇根州立大学） 纠错

Comments 9 pages, 4 figures, NAACL 2025 findings

Meta-Reasoning Improves Tool Use in Large Language Models

Lisa Alazraki, Marek Rei

机构 * Imperial College London（伦敦帝国学院） 纠错

Comments NAACL 2025 Findings

Line of Duty: Evaluating LLM Self-Knowledge via Consistency in Feasibility Boundaries

Sahil Kale, Vijaykant Nadadur

机构 * Knowledgeverse AI（知识verse人工智能） 纠错

Comments 14 pages, 8 figures, Accepted to the 5th TrustNLP Workshop at NAACL 2025

Journal ref Proceedings of the 5th Workshop on Trustworthy NLP (TrustNLP 2025), pages 127-140, 2025

Aggregation Artifacts in Subjective Tasks Collapse Large Language Models' Posteriors

Georgios Chochlakis, Alexandros Potamianos, Kristina Lerman, Shrikanth Narayanan

机构 * University of Southern California（南加州大学） ； National Technical University of Athens（雅典国立技术大学） 纠错

Comments 16 pages, 12 figures, 3 tables

Journal ref Proceedings of the 2025 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5513-5528, Albuquerque, New Mexico, April 2025

Automatic Input Rewriting Improves Translation with Large Language Models

Dayeon Ki, Marine Carpuat

机构 * University of Maryland（马里兰大学） 纠错

Comments NAACL 2025

Guiding Large Language Models to Post-Edit Machine Translation with Error Annotations

Dayeon Ki, Marine Carpuat

机构 * Computer Science University of Maryland（计算机科学大学马里兰大学） ； Computer Science, UMIACS University of Maryland（计算机科学，UMIACS大学马里兰大学） 纠错

Comments NAACL 2024 Findings

ErAConD : Error Annotated Conversational Dialog Dataset for Grammatical Error Correction

Xun Yuan, Derek Pham, Sam Davidson, Zhou Yu

Journal ref Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Playing with Voices: Tabletop Role-Playing Game Recordings as a Diarization Challenge

Lian Remme, Kevin Tang

机构 * Heinrich Heine University Düsseldorf（海因里希·海涅大学多特蒙德） 纠错

Comments 15 pages, 14 figures, published in NAACL Findings 2025

Journal ref Findings of the Association for Computational Linguistics: NAACL 2025

Analysis of LLM as a grammatical feature tagger for African American English

Rahul Porwal, Alice Rozet, Pryce Houck, Jotsna Gowda, Sarah Moeller, Kevin Tang

机构 * University of Florida（佛罗里达大学） ； Heinrich Heine University Düsseldorf（杜塞尔多夫海因里希-海涅大学） 纠错

Comments 13 pages, Accepted to "Findings of the Association for Computational Linguistics: NAACL 2025"

Journal ref Findings of the Association for Computational Linguistics: NAACL 2025 (2025) 7744-7756

What Did I Do Wrong? Quantifying LLMs' Sensitivity and Consistency to Prompt Engineering

Federico Errica, Giuseppe Siracusano, Davide Sanvito, Roberto Bifulco

机构 * NEC Italia（NEC意大利分公司） ； NEC Laboratories Europe（NEC欧洲实验室） 纠错

Comments Proceedings of the Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL 2025)

Error Reflection Prompting: Can Large Language Models Successfully Understand Errors?

Jason Li, Lauren Yraola, Kevin Zhu, Sean O'Brien

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

Comments Accepted to Insights @ NAACL 2025

Exploration of Plan-Guided Summarization for Narrative Texts: the Case of Small Language Models

Matt Grenander, Siddharth Varia, Paula Czarnowska, Yogarshi Vyas, Kishaloy Halder, Bonan Min

机构 * AWS AI Labs（AWS人工智能实验室） ； School of Informatics, University of Edinburgh（信息学院，爱丁堡大学） 纠错

Comments Accepted to the 7th Workshop on Narrative Understanding (WNU), co-located with NAACL 2025

Robust Bias Detection in MLMs and its Application to Human Trait Ratings

Ingroj Shrestha, Louis Tay, Padmini Srinivasan

机构 * University of Iowa（爱荷华大学） ； Purdue University（普渡大学） 纠错

Comments Findings of NAACL 2025

Journal ref Findings of the Association for Computational Linguistics NAACL 2025, pages 4842-4858 (2025)

Breaking Language Barriers: Equitable Performance in Multilingual Language Models

Tanay Nagar, Grigorii Khvatskii, Anna Sokol, Nitesh V. Chawla

机构 * University of Wisconsin–Madison（威斯康星大学麦迪逊分校） ； NSF Center for Computer Assisted Synthesis (CCAS), University of Notre Dame（国家科学基金会计算机辅助合成中心（CCAS）、诺特大学） ； University of Notre Dame（诺特大学） 纠错

Comments Accepted as a non-archival work-in-progress paper at the NAACL 2025 Student Research Workshop

Classic4Children: Adapting Chinese Literary Classics for Children with Large Language Model

Jiali Chen, Xusen Hei, Yuqi Xue, Zihan Wu, Jiayuan Xie, Yi Cai

机构 * Key Laboratory of Big Data and Intelligent Robot (South China University of Technology) Ministry of Education（大数据与智能机器人重点实验室（华南理工大学）教育部） ； School of Software Engineering, South China University of Technology（软件学院（华南理工大学）） ； The Hong Kong Polytechnic University（香港理工大学） 纠错

Comments Accepted at NAACL 2025 Findings

Modeling and Detecting Company Risks from News: A Case Study in Bloomberg News

Jiaxin Pei, Soumya Vadlamannati, Liang-Kang Huang, Daniel Preotiuc-Pietro, Xinyu Hua

机构 * University of Michigan（密歇根大学） ； Bloomberg（彭博） 纠错

Journal ref NAACL 2024: Human Language Technologies (Volume 6:Industry Track), pages 63 : 72

SynthDetoxM: Modern LLMs are Few-Shot Parallel Detoxification Data Annotators

Daniil Moskovskiy, Nikita Sushko, Sergey Pletenev, Elena Tutubalina, Alexander Panchenko

机构 * AIRI ； Skoltech（斯克里普挑战学院） ； Sber AI ； ISP RAS Research Center for Trusted AI（俄罗斯科学院可信人工智能研究中心） 纠错

Comments Accepted to NAACL 2025 Main Conference

Journal ref https://aclanthology.org/2025.naacl-long.294/