NAACL

DAWN-ICL: Strategic Planning of Problem-solving Trajectories for Zero-Shot In-Context Learning

Xinyu Tang, Xiaolei Wang, Wayne Xin Zhao, Ji-Rong Wen

Comments NAACL 2025 Main Conference

Upsample or Upweight? Balanced Training on Heavily Imbalanced Datasets

Tianjian Li, Haoran Xu, Weiting Tan, Kenton Murray, Daniel Khashabi

Comments 19 pages, 9 figures, accepted to NAACL 2025 main conference

EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms

Siyu Yuan, Kaitao Song, Jiangjie Chen, Xu Tan, Dongsheng Li, Deqing Yang

Comments Accepted as a main conference paper at NAACL 2025

VoCoT: Unleashing Visually Grounded Multi-Step Reasoning in Large Multi-Modal Models

Zejun Li, Ruipu Luo, Jiwen Zhang, Minghui Qiu, Xuanjing Huang, Zhongyu Wei

Comments Accepted by NAACL 2025 main conference

SANDWiCH: Semantical Analysis of Neighbours for Disambiguating Words in Context ad Hoc

Daniel Guzman-Olivares, Lara Quijano-Sanchez, Federico Liberatore

Comments 15 pages, 2 figures, 7 tables, NAACL 2025

DETQUS: Decomposition-Enhanced Transformers for QUery-focused Summarization

Yasir Khan, Xinlei Wu, Sangpil Youm, Justin Ho, Aryaan Shaikh, Jairo Garciga, Rohan Sharma, Bonnie J. Dorr

Comments 12 pages, 2 figures, Accepted to NAACL 2025 main conference

Detecting Offensive Memes with Social Biases in Singapore Context Using Multimodal Large Language Models

Cao Yuxuan, Wu Jiayang, Alistair Cheong Liang Chuen, Bryan Shan Guanrong, Theodore Lee Chong Jen, Sherman Chann Zhi Shen

Comments Accepted at 3rd Workshop on Cross-Cultural Considerations in NLP (C3NLP), co-located with NAACL 2025. This is an extended version with some appendix moved to the main body

Reverse Thinking Makes LLMs Stronger Reasoners

Justin Chih-Yao Chen, Zifeng Wang, Hamid Palangi, Rujun Han, Sayna Ebrahimi, Long Le, Vincent Perot, Swaroop Mishra, Mohit Bansal, Chen-Yu Lee, Tomas Pfister

Comments Accepted to NAACL 2025

A Zero-Shot Open-Vocabulary Pipeline for Dialogue Understanding

Abdulfattah Safa, Gözde Gül Şahin

Comments Accepted to NAACL 2025

Revitalizing Saturated Benchmarks: A Weighted Metric Approach for Differentiating Large Language Model Performance

Bryan Etzine, Masoud Hashemi, Nishanth Madhusudhan, Sagar Davasam, Roshnee Sharma, Sathwik Tejaswi Madhusudhan, Vikas Yadav

Comments conference NAACL, TrustNLP Workshop

Journal ref TrustNLP workshop NAACL, 2025

DiVISe: Direct Visual-Input Speech Synthesis Preserving Speaker Characteristics And Intelligibility

Yifan Liu, Yu Fang, Zhouhan Lin

Comments to be published in NAACL 25

HieroLM: Egyptian Hieroglyph Recovery with Next Word Prediction Language Model

Xuheng Cai, Erica Zhang

Comments Accepted at LaTeCH-CLfL 2025 @ NAACL 2025

LVLM-Compress-Bench: Benchmarking the Broader Impact of Large Vision-Language Model Compression

Souvik Kundu, Anahita Bhiwandiwalla, Sungduk Yu, Phillip Howard, Tiep Le, Sharath Nittur Sridhar, David Cobbley, Hao Kang, Vasudev Lal

Comments This work has been accepted to NAACL 2025

SuperRAG: Beyond RAG with Layout-Aware Graph Modeling

Jeff Yang, Duy-Khanh Vu, Minh-Tien Nguyen, Xuan-Quang Nguyen, Linh Nguyen, Hung Le

Comments NAACL 2025, Industry Track

NLI under the Microscope: What Atomic Hypothesis Decomposition Reveals

Neha Srikanth, Rachel Rudinger

Comments Accepted to NAACL 2025

LLM-guided Plan and Retrieval: A Strategic Alignment for Interpretable User Satisfaction Estimation in Dialogue

Sangyeop Kim, Sohhyung Park, Jaewon Jung, Jinseok Kim, Sungzoon Cho

Comments Accepted by NAACL 2025

IFIR: A Comprehensive Benchmark for Evaluating Instruction-Following in Expert-Domain Information Retrieval

Tingyu Song, Guo Gan, Mingsheng Shang, Yilun Zhao

Comments NAACL 2025 Main

HEISIR: Hierarchical Expansion of Inverted Semantic Indexing for Training-free Retrieval of Conversational Data using LLMs

Sangyeop Kim, Hangyeul Lee, Yohan Lee

Comments Accepted by NAACL 2025 (Findings)

Stealthy Jailbreak Attacks on Large Language Models via Benign Data Mirroring

Honglin Mu, Han He, Yuxin Zhou, Yunlong Feng, Yang Xu, Libo Qin, Xiaoming Shi, Zeming Liu, Xudong Han, Qi Shi, Qingfu Zhu, Wanxiang Che

Comments Accepted by NAACL 2025

Markov Chain of Thought for Efficient Mathematical Reasoning

Wen Yang, Minpeng Liao, Kai Fan

Comments Camera ready version for NAACL 2025 Main

Personalize Your LLM: Fake it then Align it

Yijing Zhang, Dyah Adila, Changho Shin, Frederic Sala

Comments NAACL 2025 Findings

Adaptive Attacks Break Defenses Against Indirect Prompt Injection Attacks on LLM Agents

Qiusi Zhan, Richard Fang, Henil Shalin Panchal, Daniel Kang

Comments 17 pages, 5 figures, 6 tables (NAACL 2025 Findings)

Open Ko-LLM Leaderboard2: Bridging Foundational and Practical Evaluation for Korean LLMs

Hyeonwoo Kim, Dahyun Kim, Jihoo Kim, Sukyung Lee, Yungi Kim, Chanjun Park

Comments Accepted to NAACL 2025 Industry

Understanding LLM Development Through Longitudinal Study: Insights from the Open Ko-LLM Leaderboard

Chanjun Park, Hyeonwoo Kim

Comments Accepted to NAACL 2025 Industry

Few-shot Personalization of LLMs with Mis-aligned Responses

Jaehyung Kim, Yiming Yang

Comments NAACL 25 (main, long), 32 pages

In-Context Learning with Long-Context Models: An In-Depth Exploration

Amanda Bertsch, Maor Ivgi, Emily Xiao, Uri Alon, Jonathan Berant, Matthew R. Gormley, Graham Neubig

Comments 32 pages; NAACL 2025 camera-ready

Dataverse: Open-Source ETL (Extract, Transform, Load) Pipeline for Large Language Models

Hyunbyung Park, Sukyung Lee, Gyoungjin Gim, Yungi Kim, Dahyun Kim, Chanjun Park

Comments Accepted to NAACL 2025 Demo

Language Models Predict Empathy Gaps Between Social In-groups and Out-groups

Yu Hou, Hal Daumé, Rachel Rudinger

Comments NAACL 2025

Waste Not, Want Not; Recycled Gumbel Noise Improves Consistency in Natural Language Generation

Damien de Mijolla, Hannan Saddiq, Kim Moore

Comments Accepted to NAACL 2025 main conference; Presented at Neurips Safe Generative AI workshop

Zero-Shot Keyphrase Generation: Investigating Specialized Instructions and Multi-Sample Aggregation on Large Language Models

Jayanth Mohan, Jishnu Ray Chowdhury, Tomas Malik, Cornelia Caragea

Comments Accepted at NAACL 2025