📰 NAACL 2025 — accepted papers

NAACL 2025 is the 2025 edition of the Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), held in Albuquerque, United States, 29 April – 4 May 2025 (publisher: Association for Computational Linguistics). The ACL Anthology lists 903 papers of it in 6 tracks; our library holds 7 with our summaries. Below: the most cited papers, every accepted paper, and ours with their topics, authors and institutions.

Tracks

Long Papers637Short Papers81Industry Track80Student Research Workshop53Human Language Technologies (System Demonstrations44Tutorial Abstracts8

Most cited papers

By their OpenAlex citations; a paper with our summary links to its page here, the others to the original.

1. Knowledge Graph-Guided Retrieval Augmented GenerationXiangrong Zhu, Yuexiang Xie, Yi Liu et al. · Long Papers80 citations
2. Simulating Classroom Education with LLM-Empowered AgentsZheyuan Zhang, Daniel Zhang-Li, Jifan Yu et al. · Long Papers46 citations
3. ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language ModelsJinheon Baek, Sujay Kumar Jauhar, Silviu Cucerzan et al. · Long Papers38 citations
4. Rationale-Guided Retrieval Augmented Generation for Medical Question AnsweringJiwoong Sohn, Yein Park, Chanwoong Yoon et al. · Long Papers33 citations
5. What Did I Do Wrong? Quantifying LLMs' Sensitivity and Consistency to Prompt EngineeringFederico Errica, Davide Sanvito, Giuseppe Siracusano et al. · Long Papers27 citations
6. The Good, The Bad, and The Greedy: Evaluation of LLMs Should Not Ignore Non-DeterminismYifan Song, Guoyin Wang, Sujian Li et al. · Long Papers26 citations
7. Benchmarking Large Language Models on Answering and Explaining Challenging Medical QuestionsHanjie Chen, Zhouxiang Fang, Yash Singla et al. · Long Papers25 citations · our summary
8. AudioBench: A Universal Benchmark for Audio Large Language ModelsBin Wang, Xunlong Zou, Geyu Lin et al. · Long Papers21 citations · our summary
9. Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented GenerationSatyapriya Krishna, Kalpesh Krishna, Anhad Mohananey et al. · Long Papers21 citations
10. VERSA: A Versatile Evaluation Toolkit for Speech, Audio, and MusicJiatong Shi, Hye-jin Shim, Jinchuan Tian et al. · Human Language Technologies (System Demonstrations20 citations

All accepted papers (903)

The most cited first; 7 with our summary link to their page here, the others to the original.

1. Knowledge Graph-Guided Retrieval Augmented GenerationXiangrong Zhu, Yuexiang Xie, Yi Liu et al. · Long Papers80 citations
2. Simulating Classroom Education with LLM-Empowered AgentsZheyuan Zhang, Daniel Zhang-Li, Jifan Yu et al. · Long Papers46 citations
3. ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language ModelsJinheon Baek, Sujay Kumar Jauhar, Silviu Cucerzan et al. · Long Papers38 citations
4. Rationale-Guided Retrieval Augmented Generation for Medical Question AnsweringJiwoong Sohn, Yein Park, Chanwoong Yoon et al. · Long Papers33 citations
5. What Did I Do Wrong? Quantifying LLMs' Sensitivity and Consistency to Prompt EngineeringFederico Errica, Davide Sanvito, Giuseppe Siracusano et al. · Long Papers27 citations
6. The Good, The Bad, and The Greedy: Evaluation of LLMs Should Not Ignore Non-DeterminismYifan Song, Guoyin Wang, Sujian Li et al. · Long Papers26 citations
7. Benchmarking Large Language Models on Answering and Explaining Challenging Medical QuestionsHanjie Chen, Zhouxiang Fang, Yash Singla et al. · Long Papers25 citations · our summary
8. AudioBench: A Universal Benchmark for Audio Large Language ModelsBin Wang, Xunlong Zou, Geyu Lin et al. · Long Papers21 citations · our summary
9. Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented GenerationSatyapriya Krishna, Kalpesh Krishna, Anhad Mohananey et al. · Long Papers21 citations
10. VERSA: A Versatile Evaluation Toolkit for Speech, Audio, and MusicJiatong Shi, Hye-jin Shim, Jinchuan Tian et al. · Human Language Technologies (System Demonstrations20 citations
11. CodexGraph: Bridging Large Language Models and Code Repositories via Code Graph DatabasesXiangyan Liu, Bo Lan, Zhiyuan Hu et al. · Long Papers19 citations
12. EASYTOOL: Enhancing LLM-based Agents with Concise Tool InstructionSiyu Yuan, Kaitao Song, Jiangjie Chen et al. · Long Papers19 citations
13. xLAM: A Family of Large Action Models to Empower AI Agent SystemsJianguo Zhang, Tian Lan, Ming Zhu et al. · Long Papers19 citations · our summary
14. Fact-Aware Multimodal Retrieval Augmentation for Accurate Medical Radiology Report GenerationLiwen Sun, James Jialun Zhao, Wenjing Han et al. · Long Papers18 citations
15. An Efficient Gloss-Free Sign Language Translation Using Spatial Configurations and Motion Dynamics with LLMsEui Jun Hwang, Sukmin Cho, Junmyeong Lee et al. · Long Papers17 citations
16. Design2Code: Benchmarking Multimodal Code Generation for Automated Front-End EngineeringChenglei Si, Yanzhe Zhang, Ryan Li et al. · Long Papers17 citations
17. Hello Again! LLM-powered Personalized Agent for Long-term DialogueHao Li, Chenghao Yang, An Zhang et al. · Long Papers17 citations
18. VisDoM: Multi-Document QA with Visually Rich Elements Using Multimodal Retrieval-Augmented GenerationManan Suri, Puneet Mathur, Franck Dernoncourt et al. · Long Papers16 citations
19. Towards Sustainable NLP: Insights from Benchmarking Inference Energy in Large Language ModelsSoham Poddar, Paramita Koley, Janardan Misra et al. · Long Papers15 citations
20. AEGIS2.0: A Diverse AI Safety Dataset and Risks Taxonomy for Alignment of LLM GuardrailsShaona Ghosh, Prasoon Varshney, Makesh Narsimhan Sreedhar et al. · Long Papers14 citations
21. Is Translation All You Need? A Study on Solving Multilingual Tasks with Large Language ModelsChaoqun Liu, Wenxuan Zhang, Yiran Zhao et al. · Long Papers14 citations
22. SeaLLMs 3: Open Foundation and Chat Multilingual Large Language Models for Southeast Asian LanguagesWenxuan Zhang, Hou Pong Chan, Yiran Zhao et al. · Human Language Technologies (System Demonstrations14 citations
23. Logic-of-Thought: Injecting Logic into Contexts for Full Reasoning in Large Language ModelsTongxuan Liu, Wenjiang Xu, Weizhe Huang et al. · Long Papers13 citations
24. MCQG-SRefine: Multiple Choice Question Generation and Evaluation with Iterative Self-Critique, Correction, and Comparison FeedbackZonghai Yao, Aditya Parashar, Huixue Zhou et al. · Long Papers13 citations
25. SimRAG: Self-Improving Retrieval-Augmented Generation for Adapting Large Language Models to Specialized DomainsRan Xu, Hui Liu, Sreyashi Nag et al. · Long Papers13 citations

See all 903 papers in NAACL 2025 — accepted papers →

📄 Papers with our summary in our library (7)

The most cited first (OpenAlex citations plus our library's).

1. In-Context Learning with Long-Context Models: An In-Depth ExplorationAmanda Bertsch, Maor Ivgi, Emily Xiao, et al.2025 · 75 citations
2. Benchmarking Large Language Models on Answering and Explaining Challenging Medical QuestionsHanjie Chen, Zhouxiang Fang, Yash Singla, et al.2025 · 75 citations
3. AudioBench: A Universal Benchmark for Audio Large Language ModelsBin Wang, Xunlong Zou, Geyu Lin, et al.2025 · 75 citations
4. KMMLU: Measuring Massive Multitask Language Understanding in KoreanGuijin Son, Hanwool Lee, Sungdong Kim, et al.2025 · 72 citations
5. IrokoBench: A New Benchmark for African Languages in the Age of Large Language ModelsDavid Ifeoluwa Adelani, Jessica Ojo, Israel Abebe Azime, et al.2025 · 69 citations
6. xLAM: A Family of Large Action Models to Empower AI Agent SystemsJianguo Zhang, Tian Lan, Ming Zhu, et al.2025 · 67 citations
7. A Survey of QUD Models for Discourse ProcessingYingxue Fu2025 · 3 citations

🧭 Top topics

Topics of its works in our library, with the number of works on each.

🧠 Language models & pretraining (3)📏 Evaluation & benchmarks (2)🧵 Discourse analysis (1)🎙️ Speech & spoken language (1) English (1)

📚 Fields

🎭 Arts and Humanities (7)🖥️ Computer Science (7)🩺 Medicine (1)

🧑‍🔬 Top authors

Authors with a page who published here most often: their works here, and the citations of those works.

🏛️ Top institutions

Institutions on the bylines of its works here, by the number of works.

🔬Canadian Institute for Advanced ResearchToronto · Canada1 work here🏛️Agency for Science, Technology and ResearchSingapore · Singapore1 work here🏢MicrosoftRedmond · United States1 work here🎓Johns Hopkins UniversityBaltimore · United States1 work here🎓Haramaya UniversityDire Dawa · Ethiopia1 work here🎓Korea Advanced Institute of Science and TechnologyDaejeon · South Korea1 work here🎓Tel Aviv UniversityTel Aviv · Israel1 work here🎓University of St AndrewsSt Andrews · United Kingdom1 work here🎓Princeton UniversityPrinceton · United States1 work here🔬Institute for Infocomm ResearchSingapore · Singapore1 work here🎓Ontario Tech UniversityOshawa · Canada1 work here🏢NAVER CloudSeongnam-si · South Korea1 work here

Place and dates from the event's site or the ACL Anthology; works and citations from OpenAlex and our library.

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/venues/naacl/2025/