📰 ACL 2025 — accepted papers

ACL 2025 is the 2025 edition of the Annual Meeting of the Association for Computational Linguistics (ACL), held in Vienna, Austria, 27 July – 1 August 2025 (publisher: Association for Computational Linguistics). The ACL Anthology lists 1,966 papers of it in 6 tracks; our library holds 24 with our summaries. Below: its awards, the most cited papers, every accepted paper, and ours with their topics, authors and institutions.

Tracks

Long Papers1,602Industry Track109Short Papers97Student Research Workshop86System Demonstrations64Tutorial Abstracts8

Awards

As the ACL Anthology records them.

1. Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse AttentionJingyang Yuan, Huazuo Gao, Damai Dai et al. · Long Papers · 🏆 Best Paper87 citations
2. Byte Latent Transformer: Patches Scale Better Than TokensArtidoro Pagnoni, Ramakanth Pasunuru, Pedro Rodriguez et al. · Long Papers · 🏆 Outstanding Paper17 citations
3. AfriMed-QA: A Pan-African, Multi-Specialty, Medical Question-Answering Benchmark DatasetCharles Nimo, Tobi Olatunji, Abraham Toluwase Owodunni et al. · Long Papers · 🏆 Best Social Impact Paper13 citations
4. HALoGEN: Fantastic LLM Hallucinations and Where to Find ThemAbhilasha Ravichander, Shrusti Ghela, David Wadden et al. · Long Papers · 🏆 Outstanding Paper12 citations
5. The AI Gap: How Socioeconomic Status Affects Language Technology InteractionsElisa Bassignana, Amanda Cercas Curry, Dirk Hovy · Long Papers · 🏆 Best Social Impact Paper12 citations
6. All That Glitters is Not Novel: Plagiarism in AI Generated ResearchTarun Gupta, Danish Pruthi · Long Papers · 🏆 Outstanding Paper9 citations
7. BRIGHTER: BRIdging the Gap in Human-Annotated Textual Emotion Recognition Datasets for 28 LanguagesShamsuddeen Hassan Muhammad, Nedjma Ousidhoum, Idris Abdulmumin et al. · Long Papers · 🏆 Best Resource Paper8 citations
8. LLMs know their vulnerabilities: Uncover Safety Gaps through Natural Distribution ShiftsQibing Ren, Hao Li, Dongrui Liu et al. · Long Papers · 🏆 Outstanding Paper6 citations
9. OLMoTrace: Tracing Language Model Outputs Back to Trillions of Training TokensJiacheng Liu, Taylor Blanton, Yanai Elazar et al. · System Demonstrations · 🏆 Best Demo6 citations
10. Towards the Law of Capacity Gap in Distilling Language ModelsChen Zhang, Qiuchi Li, Dawei Song et al. · Long Papers · 🏆 Outstanding Paper5 citations
11. A Theory of Response Sampling in LLMs: Part Descriptive and Part PrescriptiveSarath Sivaprasad, Pramod Kaushik, Sahar Abdelnabi et al. · Long Papers · 🏆 Best Paper3 citations
12. Bridging the Language Gaps in Large Language Models with Inference-Time Cross-Lingual InterventionWeixuan Wang, Minghao Wu, Barry Haddow et al. · Long Papers · 🏆 Outstanding Paper3 citations
13. Fairness through Difference Awareness: Measuring $\textitDesired$ Group Discrimination in LLMsAngelina Wang, Michelle Phan, Daniel E. Ho et al. · Long Papers · 🏆 Best Paper3 citations
14. HateDay: Insights from a Global Hate Speech Dataset Representative of a Day on TwitterManuel Tonneau, Diyi Liu, Niyati Malhotra et al. · Long Papers · 🏆 Outstanding Paper3 citations
15. Language Models Resist Alignment: Evidence From Data CompressionJiaming Ji, Kaile Wang, Tianyi Alex Qiu et al. · Long Papers · 🏆 Best Paper3 citations
16. Toward Automatic Discovery of a Canine Phonetic AlphabetTheron S. Wang, Xingyuan Li, Hridayesh Lekhak et al. · Long Papers · 🏆 Outstanding Paper3 citations
17. Beyond N-Grams: Rethinking Evaluation Metrics and Strategies for Multilingual Abstractive SummarizationItai Mondshine, Tzuf Paz-Argaman, Reut Tsarfaty · Long Papers · 🏆 Outstanding Paper2 citations
18. IndicSynth: A Large-Scale Multilingual Synthetic Speech Dataset for Low-Resource Indian LanguagesDivya V Sharma, Vijval Ekbote, Anubha Gupta · Long Papers · 🏆 Outstanding Paper2 citations
19. MaCP: Minimal yet Mighty Adaptation via Hierarchical Cosine ProjectionYixian Shen, Qi Bi, Jia-hong Huang et al. · Long Papers · 🏆 Best Theme Paper2 citations
20. Meta-rater: A Multi-dimensional Data Selection Method for Pre-training Language ModelsXinlin Zhuang, Jiahui Peng, Ren Ma et al. · Long Papers · 🏆 Best Theme Paper2 citations
21. Palm: A Culturally Inclusive and Linguistically Diverse Dataset for Arabic LLMsFakhraddin Alwajih, Abdellah El Mekki, Samar Mohamed Magdy et al. · Long Papers · 🏆 Best Resource Paper2 citations
22. Rethinking the Role of Prompting Strategies in LLM Test-Time Scaling: A Perspective of Probability TheoryYexiang Liu, Zekun Li, Zhi Fang et al. · Long Papers · 🏆 Outstanding Paper2 citations
23. Revisiting Compositional Generalization Capability of Large Language Models Considering Instruction Following AbilityYusuke Sakai, Hidetaka Kamigaito, Taro Watanabe · Long Papers · 🏆 Outstanding Paper2 citations
24. Turning Trash into Treasure: Accelerating Inference of Large Language Models with Token RecyclingXianzhen Luo, Yixuan Wang, Qingfu Zhu et al. · Long Papers · 🏆 Outstanding Paper2 citations
25. A New Formulation of Zipf's Meaning-Frequency Law through Contextual DiversityRyo Nagata, Kumiko Tanaka-Ishii · Long Papers · 🏆 Outstanding Paper1 citation
26. Between Circuits and Chomsky: Pre-pretraining on Formal Languages Imparts Linguistic BiasesMichael Y. Hu, Jackson Petty, Chuan Shi et al. · Long Papers · 🏆 Outstanding Paper1 citation
27. LaTIM: Measuring Latent Token-to-Token Interactions in Mamba ModelsHugo Pitorro, Marcos Vinicius Treviso · Long Papers · 🏆 Outstanding Paper1 citation
28. Mapping 1,000+ Language Models via the Log-Likelihood VectorMomose Oyama, Hiroaki Yamagiwa, Yusuke Takase et al. · Long Papers · 🏆 Outstanding Paper1 citation
29. MiniLongBench: The Low-cost Long Context Understanding Benchmark for Large Language ModelsZhongzhan Huang, Guoming Ling, Shanshan Zhong et al. · Long Papers · 🏆 Outstanding Paper1 citation
30. Pre$^3$: Enabling Deterministic Pushdown Automata for Faster Structured LLM GenerationJunyi Chen, Shihao Bai, Zaijun Wang et al. · Long Papers · 🏆 Outstanding Paper1 citation
31. SubLIME: Subset Selection via Rank Correlation Prediction for Data-Efficient LLM EvaluationGayathri Saranathan, Cong Xu, Mahammad Parwez Alam et al. · Long Papers · 🏆 Best Theme Paper1 citation
32. Are Rules Meant to be Broken? Understanding Multilingual Moral Reasoning as a Computational Pipeline with UniMoralShivani Kumar, David Jurgens · Long Papers · 🏆 Best Resource Paper
33. Capability Salience Vector: Fine-grained Alignment of Loss and Capabilities for Downstream Task Scaling LawQiming Ge, Shuhao Xing, Songyang Gao et al. · Long Papers · 🏆 Outstanding Paper
34. From Real to Synthetic: Synthesizing Millions of Diversified and Complicated User Instructions with Attributed GroundingChiwei Zhu, Benfeng Xu, Xiaorui Wang et al. · Long Papers · 🏆 Outstanding Paper
35. I0T: Embedding Standardization Method Towards Zero Modality GapNa Min An, Eunki Kim, James Thorne et al. · Long Papers · 🏆 Outstanding Paper
36. Llama See, Llama Do: A Mechanistic Perspective on Contextual Entrainment and Distraction in LLMsJingcheng Niu, Xingdi Yuan, Tong Wang et al. · Long Papers · 🏆 Outstanding Paper
37. PARME: Parallel Corpora for Low-Resourced Middle Eastern LanguagesSina Ahmadi, Rico Sennrich, Erfan Karami et al. · Long Papers · 🏆 Outstanding Paper
38. Past Meets Present: Creating Historical Analogy with Large Language ModelsNianqi Li, Siyu Yuan, Jiangjie Chen et al. · Long Papers · 🏆 Outstanding Paper
39. Typology-Guided Adaptation in Multilingual ModelsNdapa Nakashole · Long Papers · 🏆 Outstanding Paper

Most cited papers

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

1. Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and InferenceBenjamin Warner, Antoine Chaffin, Benjamin Clavié et al. · Long Papers201 citations
2. F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow MatchingYushen Chen, Zhikang Niu, Ziyang Ma et al. · Long Papers88 citations · our summary
3. Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse AttentionJingyang Yuan, Huazuo Gao, Damai Dai et al. · Long Papers · 🏆 Best Paper87 citations
4. Medical Graph RAG: Evidence-based Medical Large Language Model via Graph Retrieval-Augmented GenerationJunde Wu, Jiayuan Zhu, Yunli Qi et al. · Long Papers79 citations
5. Knowledge Graph Retrieval-Augmented Generation for LLM-based RecommendationShijie Wang, Wenqi Fan, Yue Feng et al. · Long Papers57 citations
6. MAIN-RAG: Multi-Agent Filtering Retrieval-Augmented GenerationChia-Yuan Chang, Zhimeng Jiang, Vineeth Rakesh et al. · Long Papers39 citations
7. HalluLens: LLM Hallucination BenchmarkYejin Bang, Ziwei Ji, Alan Schelten et al. · Long Papers38 citations
8. KG-Agent: An Efficient Autonomous Agent Framework for Complex Reasoning over Knowledge GraphJinhao Jiang, Kun Zhou, Wayne Xin Zhao et al. · Long Papers36 citations
9. LLMs instead of Human Judges? A Large Scale Empirical Study across 20 NLP Evaluation TasksAnna Bavaresco, Raffaella Bernardi, Leonardo Bertolazzi et al. · Short Papers36 citations
10. Recent Advances in Speech Language Models: A SurveyWenqian Cui, Dianzhi Yu, Xiaoqi Jiao et al. · Long Papers36 citations

All accepted papers (1,966)

The most cited first; 24 with our summary link to their page here, the others to the original.

1. Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and InferenceBenjamin Warner, Antoine Chaffin, Benjamin Clavié et al. · Long Papers201 citations
2. F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow MatchingYushen Chen, Zhikang Niu, Ziyang Ma et al. · Long Papers88 citations · our summary
3. Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse AttentionJingyang Yuan, Huazuo Gao, Damai Dai et al. · Long Papers · 🏆 Best Paper87 citations
4. Medical Graph RAG: Evidence-based Medical Large Language Model via Graph Retrieval-Augmented GenerationJunde Wu, Jiayuan Zhu, Yunli Qi et al. · Long Papers79 citations
5. Knowledge Graph Retrieval-Augmented Generation for LLM-based RecommendationShijie Wang, Wenqi Fan, Yue Feng et al. · Long Papers57 citations
6. MAIN-RAG: Multi-Agent Filtering Retrieval-Augmented GenerationChia-Yuan Chang, Zhimeng Jiang, Vineeth Rakesh et al. · Long Papers39 citations
7. HalluLens: LLM Hallucination BenchmarkYejin Bang, Ziwei Ji, Alan Schelten et al. · Long Papers38 citations
8. KG-Agent: An Efficient Autonomous Agent Framework for Complex Reasoning over Knowledge GraphJinhao Jiang, Kun Zhou, Wayne Xin Zhao et al. · Long Papers36 citations
9. LLMs instead of Human Judges? A Large Scale Empirical Study across 20 NLP Evaluation TasksAnna Bavaresco, Raffaella Bernardi, Leonardo Bertolazzi et al. · Short Papers36 citations
10. Recent Advances in Speech Language Models: A SurveyWenqian Cui, Dianzhi Yu, Xiaoqi Jiao et al. · Long Papers36 citations
11. EfficientQAT: Efficient Quantization-Aware Training for Large Language ModelsMengzhao Chen, Wenqi Shao, Peng Xu et al. · Long Papers35 citations · our summary
12. MultiAgentBench : Evaluating the Collaboration and Competition of LLM agentsKunlun Zhu, Hongyi Du, Zhaochen Hong et al. · Long Papers35 citations
13. PlanGenLLMs: A Modern Survey of LLM Planning CapabilitiesHui Wei, Zihao Zhang, Shenghua He et al. · Long Papers34 citations
14. Energy Considerations of Large Language Model Inference and Efficiency OptimizationsJared Fernandez, Clara Na, Vashisth Tiwari et al. · Long Papers31 citations
15. Agentic Reasoning: A Streamlined Framework for Enhancing LLM Reasoning with Agentic ToolsJunde Wu, Jiayuan Zhu, Yuyuan Liu et al. · Long Papers30 citations
16. mPLUG-DocOwl2: High-resolution Compressing for OCR-free Multi-page Document UnderstandingAnwen Hu, Haiyang Xu, Liang Zhang et al. · Long Papers29 citations
17. MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding BenchmarkXiang Yue, Tianyu Zheng, Yuansheng Ni et al. · Long Papers26 citations
18. LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context MultitasksYushi Bai, Shangqing Tu, Jiajie Zhang et al. · Long Papers25 citations
19. Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language ModelsFei Wang, Xingchen Wan, Ruoxi Sun et al. · Long Papers24 citations
20. JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMsJunjie Chu, Yugeng Liu, Ziqing Yang et al. · Long Papers24 citations
21. SeaKR: Self-aware Knowledge Retrieval for Adaptive Retrieval Augmented GenerationZijun Yao, Weijian Qi, Liangming Pan et al. · Long Papers23 citations
22. The Alternative Annotator Test for LLM-as-a-Judge: How to Statistically Justify Replacing Human Annotators with LLMsNitay Calderon, Roi Reichart, Rotem Dror · Long Papers23 citations
23. Benchmarking LLMs and LLM-based Agents in Practical Vulnerability Detection for Code RepositoriesAlperen Yildiz, Sin G Teo, Yiling Lou et al. · Long Papers21 citations
24. Demystifying Small Language Models for Edge DeploymentZhenyan Lu, Xiang Li, Dongqi Cai et al. · Long Papers21 citations
25. Unveiling Privacy Risks in LLM Agent MemoryBo Wang, Weiyi He, Shenglai Zeng et al. · Long Papers21 citations

See all 1,966 papers in ACL 2025 — accepted papers →

📄 Papers with our summary in our library (24)

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

1. Global MMLU: Understanding and Addressing Cultural and Linguistic Biases in Multilingual EvaluationAnnual Meeting of the Association for Computational Linguistics (ACL)Shivalika Singh, Angelika Romanou, Clémentine Fourrier, et al.2025 · 179 citations
2. F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow MatchingAnnual Meeting of the Association for Computational Linguistics (ACL)Yushen Chen, Zhikang Niu, Ziyang Ma, et al.2025 · 152 citations
3. ProcessBench: Identifying Process Errors in Mathematical ReasoningAnnual Meeting of the Association for Computational Linguistics (ACL)Chujie Zheng, Zhenru Zhang, Beichen Zhang, et al.2025 · 116 citations
4. How to Train Long-Context Language Models (Effectively)Annual Meeting of the Association for Computational Linguistics (ACL)Tianyu Gao, Alexander Wettig, Howard Yen, et al.2025 · 84 citations
5. EfficientQAT: Efficient Quantization-Aware Training for Large Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)Mengzhao Chen, Wenqi Shao, Peng Xu, et al.2025 · 82 citations
6. OpenCoder: The Open Cookbook for Top-Tier Code Large Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)Siming Huang, Tianhao Cheng, Jason Klein Liu, et al.2025 · 81 citations
7. PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human PreferenceAnnual Meeting of the Association for Computational Linguistics (ACL)Jiaming Ji, Donghai Hong, Borong Zhang, et al.2025 · 81 citations
8. WebWalker: Benchmarking LLMs in Web TraversalAnnual Meeting of the Association for Computational Linguistics (ACL)Jialong Wu, Wenbiao Yin, Yong Jiang, et al.2025 · 70 citations
9. CoT-Valve: Length-Compressible Chain-of-Thought TuningAnnual Meeting of the Association for Computational Linguistics (ACL)Xinyin Ma, Guangnian Wan, Runpeng Yu, et al.2025 · 64 citations
10. LegalAgentBench: Evaluating LLM Agents in Legal DomainAnnual Meeting of the Association for Computational Linguistics (ACL)Haitao Li, Junjie Chen, Jingli Yang, et al.2025 · 60 citations
11. Pragmatics in the Era of Large Language Models: A Survey on Datasets, Evaluation, Opportunities and ChallengesAnnual Meeting of the Association for Computational Linguistics (ACL)Bolei Ma, Yuting Li, Wei Zhou, et al.2025 · 49 citations
12. M-MAD: Multidimensional Multi-Agent Debate for Advanced Machine Translation EvaluationAnnual Meeting of the Association for Computational Linguistics (ACL)Zhaopeng Feng, Jiayuan Su, Jiamei Zheng, et al.2025 · 24 citations
13. An Expanded Massive Multilingual Dataset for High-Performance Language Technologies (HPLT)Annual Meeting of the Association for Computational Linguistics (ACL)Laurie Burchell, Ona de Gibert, Nikolay Arefyev, et al.2025 · 23 citations
14. METAL: A Multi-Agent Framework for Chart Generation with Test-Time ScalingAnnual Meeting of the Association for Computational Linguistics (ACL)Bingxuan Li, Yiwei Wang, Jiuxiang Gu, et al.2025 · 15 citations
15. Ontology-Guided Reverse Thinking Makes Large Language Models Stronger on Knowledge Graph Question AnsweringAnnual Meeting of the Association for Computational Linguistics (ACL)Runxuan Liu, Bei Luo, Jiaqi Li, et al.2025 · 15 citations
16. The Impact of Token Granularity on the Predictive Power of Language Model SurprisalAnnual Meeting of the Association for Computational Linguistics (ACL)Byung-Doh Oh, William Schuler2025 · 12 citations
17. from Benign import Toxic: Jailbreaking the Language Model via Adversarial MetaphorsAnnual Meeting of the Association for Computational Linguistics (ACL)Yu Yan, Sheng Sun, Zenghao Duan, et al.2025 · 12 citations
18. GrammaMT: Improving Machine Translation with Grammar-Informed In-Context LearningAnnual Meeting of the Association for Computational Linguistics (ACL)Rita Ramos, Everlyn Asiko Chimoto, Maartje Ter Hoeve, et al.2025 · 11 citations
19. Developmentally-plausible Working Memory Shapes a Critical Period for Language AcquisitionAnnual Meeting of the Association for Computational Linguistics (ACL)Masato Mita, Ryo Yoshida, Yohei Oseki2025 · 9 citations
20. Do LLMs Understand Dialogues? A Case Study on Dialogue ActsAyesha Qamar, Jonathan Tong, Ruihong Huang2025 · 6 citations
21. Targeted Syntactic Evaluation for Grammatical Error CorrectionAomi Koyama, Masato Mita, Su-Youn Yoon, et al.2025 · 3 citations
22. Modeling the Evolution of English Noun Compounds with Feature-Rich Diachronic Compositionality PredictionFilip Miletić, Sabine Schulte im Walde2025 · 3 citations
23. Cross-Genre Learning for Old English Poetry POS TaggingIrene Miani, Sara Stymne, Gregory R. Darwin2025 · 2 citations
24. The UD-NewsCrawl Treebank: Reflections and Challenges from a Large-scale Tagalog Syntactic Annotation ProjectAnnual Meeting of the Association for Computational Linguistics (ACL)Angelina Aspra Aquino, Lester James Validad Miranda, Elsie Marie T. Or2025

🧭 Top topics

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

🧠Language models & pretraining (9)English (3)🔁Machine translation (2)🌍Multilingual & cross-lingual NLP (2)📏Evaluation & benchmarks (2)🧮Reasoning (2)🧒Psycholinguistics & language acquisition (2)🛡️Bias, fairness & safety (2)⏳Historical linguistics & language change (2)💬Speech act theory (1)🌐Universal Dependencies (1)🗂️Treebanks (1)🔤Part-of-speech tagging (1)❓Question answering (1)🗨️Dialogue systems (1)

📚 Fields

🎭Arts and Humanities (23)🖥️Computer Science (23)🤝Social Sciences (3)🧠Neuroscience (2)💭Psychology (2)⚙️Engineering (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.

🎓Harbin Institute of TechnologyHarbin · China2 works here🎓University of StuttgartStuttgart · Germany1 work here🎓University of Notre DameNotre Dame · United States1 work here🔬Canadian Institute for Advanced ResearchToronto · Canada1 work here🎓Uppsala UniversityUppsala · Sweden1 work here🎓University of Science and Technology of ChinaHefei · China1 work here🏢Adobe SystemsSan Jose · United States1 work here🏢AmazonSeattle · United States1 work here🎓University of HelsinkiHelsinki · Finland1 work here🏢IBMArmonk · United States1 work here🎓Central South UniversityChangsha · China1 work here🎓University of LisbonLisbon · Portugal1 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/acl/2025/