NAACL

Understanding LLMs' Fluid Intelligence Deficiency: An Analysis of the ARC Task

Junjie Wu, Mo Yu, Lemao Liu, Dit-Yan Yeung, Jie Zhou

Comments 22 pages, 9 figures, accepted by NAACL 2025 main conference

Padding Tone: A Mechanistic Analysis of Padding Tokens in T2I Models

Michael Toker, Ido Galil, Hadas Orgad, Rinon Gal, Yoad Tewel, Gal Chechik, Yonatan Belinkov

Comments Published in: NAACL 2025. Project webpage: https://padding-tone.github.io/

SeqAR: Jailbreak LLMs with Sequential Auto-Generated Characters

Yan Yang, Zeguan Xiao, Xin Lu, Hongru Wang, Xuetao Wei, Hailiang Huang, Guanhua Chen, Yun Chen

Comments Accepted by NAACL 2025

MiLoRA: Harnessing Minor Singular Components for Parameter-Efficient LLM Finetuning

Hanqing Wang, Yixia Li, Shuo Wang, Guanhua Chen, Yun Chen

Comments This paper has been accepted at NAACL 2025. Code is available at: https://github.com/sufenlp/MiLoRA

An Effective Automated Speaking Assessment Approach to Mitigating Data Scarcity and Imbalanced Distribution

Tien-Hong Lo, Fu-An Chao, Tzu-I Wu, Yao-Ting Sung, Berlin Chen

Comments Accepted to NAACL 2024 Findings

SynGhost: Invisible and Universal Task-agnostic Backdoor Attack via Syntactic Transfer

Pengzhou Cheng, Wei Du, Zongru Wu, Fengwei Zhang, Libo Chen, Zhuosheng Zhang, Gongshen Liu

Comments 17 pages, 16 figures, 12 tables, accepted at NAACL 2025 Findings

Efficient Prompting for Continual Adaptation to Missing Modalities

Zirun Guo, Shulei Wang, Wang Lin, Weicai Yan, Yangyang Wu, Tao Jin

Comments Accepted to NAACL 2025 Main

LLM2: Let Large Language Models Harness System 2 Reasoning

Cheng Yang, Chufan Shi, Siheng Li, Bo Shui, Yujiu Yang, Wai Lam

Comments Accepted to NAACL 2025 Main Conference

MiCEval: Unveiling Multimodal Chain of Thought's Quality via Image Description and Reasoning Steps

Xiongtao Zhou, Jie He, Lanyu Chen, Jingyu Li, Haojing Chen, Víctor Gutiérrez-Basulto, Jeff Z. Pan, Hanjie Chen

Comments NAACL 2025

AssertionBench: A Benchmark to Evaluate Large-Language Models for Assertion Generation

Vaishnavi Pulavarthi, Deeksha Nandal, Soham Dan, Debjit Pal

Comments 8 Pages, 3 Figures, Published in NAACL 2025

Do Large Language Models Align with Core Mental Health Counseling Competencies?

Viet Cuong Nguyen, Mohammad Taher, Dongwan Hong, Vinicius Konkolics Possobom, Vibha Thirunellayi Gopalakrishnan, Ekta Raj, Zihang Li, Heather J. Soled, Michael L. Birnbaum, Srijan Kumar, Munmun De Choudhury

Comments 10 Pages, Accepted to Findings of NAACL 2025

ETHIC: Evaluating Large Language Models on Long-Context Tasks with High Information Coverage

Taewhoo Lee, Chanwoong Yoon, Kyochul Jang, Donghyeon Lee, Minju Song, Hyunjae Kim, Jaewoo Kang

Comments NAACL 2025

Probing-RAG: Self-Probing to Guide Language Models in Selective Document Retrieval

Ingeol Baek, Hwan Chang, Byeongjeong Kim, Jimin Lee, Hwanhee Lee

Comments NAACL 2025 Findings

Identifying and Mitigating Social Bias Knowledge in Language Models

Ruizhe Chen, Yichen Li, Jianfei Yang, Joey Tianyi Zhou, Jian Wu, Zuozhu Liu

Comments NAACL 2025 Findings. arXiv admin note: substantial text overlap with arXiv:2405.09341

Stronger Models are NOT Stronger Teachers for Instruction Tuning

Zhangchen Xu, Fengqing Jiang, Luyao Niu, Bill Yuchen Lin, Radha Poovendran

Comments This is paper is accepted at NAACL 2025

Active Few-Shot Learning for Text Classification

Saeed Ahmadnia, Arash Yousefi Jordehi, Mahsa Hosseini Khasheh Heyran, Seyed Abolghasem Mirroshandel, Owen Rambow, Cornelia Caragea

Comments Accepted to NAACL 2025 Main Conference; 18 pages, 8 figures, 13 tables including Appendix

MixLLM: Dynamic Routing in Mixed Large Language Models

Xinyuan Wang, Yanchi Liu, Wei Cheng, Xujiang Zhao, Zhengzhang Chen, Wenchao Yu, Yanjie Fu, Haifeng Chen

Comments 11 pages, 7 figures, accepted by NAACL 2025 main conference

Breaking Down Power Barriers in On-Device Streaming ASR: Insights and Solutions

Yang Li, Yuan Shangguan, Yuhao Wang, Liangzhen Lai, Ernie Chang, Changsheng Zhao, Yangyang Shi, Vikas Chandra

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

Guiding Through Complexity: What Makes Good Supervision for Hard Math Reasoning Tasks?

Xuan He, Da Yin, Nanyun Peng

Comments NAACL 2025 Main

How Good Are LLMs for Literary Translation, Really? Literary Translation Evaluation with Humans and LLMs

Ran Zhang, Wei Zhao, Steffen Eger

Comments NAACL Camera-Ready version

From Text to Emoji: How PEFT-Driven Personality Manipulation Unleashes the Emoji Potential in LLMs

Navya Jain, Zekun Wu, Cristian Munoz, Airlie Hilliard, Xin Guan, Adriano Koshiyama, Emre Kazim, Philip Treleaven

Comments Findings paper of NAACL 2025 and NeurIPS 2024 Workshop on Behavioral Machine Learning

Journal ref Findings paper of NAACL 2025 and NeurIPS 2024 Workshop on Behavioral Machine Learning

HyPA-RAG: A Hybrid Parameter Adaptive Retrieval-Augmented Generation System for AI Legal and Policy Applications

Rishi Kalra, Zekun Wu, Ayesha Gulley, Airlie Hilliard, Xin Guan, Adriano Koshiyama, Philip Treleaven

Comments NAACL 2025 Industry Track & EMNLP 2024 CustomNLP4U Workshop

Mutual Reinforcement of LLM Dialogue Synthesis and Summarization Capabilities for Few-Shot Dialogue Summarization

Yen-Ju Lu, Ting-Yao Hu, Hema Swetha Koppula, Hadi Pouransari, Jen-Hao Rick Chang, Yin Xia, Xiang Kong, Qi Zhu, Simon Wang, Oncel Tuzel, Raviteja Vemulapalli

Comments NAACL 2025 Findings

MonoTODia: Translating Monologue Requests to Task-Oriented Dialogues

Sebastian Steindl, Ulrich Schäfer, Bernd Ludwig

Comments Accepted at NAACL 2025 (Industry Track)

Reverse Modeling in Large Language Models

Sicheng Yu, Yuanchen Xu, Cunxiao Du, Yanying Zhou, Minghui Qiu, Qianru Sun, Hao Zhang, Jiawei Wu

Comments NAACL 2025 Camera-ready Version

WaterSeeker: Pioneering Efficient Detection of Watermarked Segments in Large Documents

Leyi Pan, Aiwei Liu, Yijian Lu, Zitian Gao, Yichen Di, Shiyu Huang, Lijie Wen, Irwin King, Philip S. Yu

Comments NAACL 2025 Findings; AAAI PDLM Workshop (Oral)

An Efficient Sign Language Translation Using Spatial Configuration and Motion Dynamics with LLMs

Eui Jun Hwang, Sukmin Cho, Junmyeong Lee, Jong C. Park

Comments Accepted to NAACL 2025 main

Concept Distillation from Strong to Weak Models via Hypotheses-to-Theories Prompting

Emmanuel Aboah Boateng, Cassiano O. Becker, Nabiha Asghar, Kabir Walia, Ashwin Srinivasan, Ehi Nosakhare, Soundar Srinivasan, Victor Dibia

Comments Accepted to NAACL 2025; 17 pages, 8 figures

LLMs Are Biased Towards Output Formats! Systematically Evaluating and Mitigating Output Format Bias of LLMs

Do Xuan Long, Hai Nguyen Ngoc, Tiviatis Sim, Hieu Dao, Shafiq Joty, Kenji Kawaguchi, Nancy F. Chen, Min-Yen Kan

Comments NAACL 2025 Main Conference

Take the essence and discard the dross: A Rethinking on Data Selection for Fine-Tuning Large Language Models

Ziche Liu, Rui Ke, Yajiao Liu, Feng Jiang, Haizhou Li

Comments Accepted by the NAACL 2025 main conference