FollowBench: A Multi-level Fine-grained Constraints Following Benchmark for Large Language Models
Open accessAbstract
Yuxin Jiang, Yufei Wang, Xingshan Zeng, Wanjun Zhong, Liangyou Li, Fei Mi, Lifeng Shang, Xin Jiang, Qun Liu, Wei Wang. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
FollowBench constraints are not verifiable and are evaluated using LLM-as-judges.
“These constraints are not verifiable and are evaluated using LLM-as-judges.”
From Generalizing Verifiable Instruction Following (2025) · cites this paper as [12]
The Introduction and §3.2 say FollowBench uses LLM judges for open-ended instructions, for which rule-based assessment is extremely challenging. But they also say closed-ended instructions are assessed with rule-based programs, so the claim overgeneralizes when it says FollowBench constraints are not verifiable and are evaluated using LLM judges. (LLM, conf=0.90)
Experimental — accuracy not yet measuredFollowBench looks at how models deal with an iteratively increasing amount of constraints, covering situation, style, and format constraints.
“FollowBench [12] looks at how models deal with an iteratively increasing amount of constraints, covering situation, style, and format constraints.”
From Generalizing Verifiable Instruction Following (2025) · cites this paper as [12]
Most evaluations of instruction following focus solely on synthetic data.
“Despite this, most evaluations focus solely on synthetic data.”
From LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraints (2024) · cites this paper as Jiang et al., 2024
The Introduction identifies gaps in prior instruction-following evaluations—limited attention to fine-grained constraints and varying difficulty—but does not say most use only synthetic data. Section 2.1 discusses automatically generated data for instruction tuning, not the data used by most evaluations. Searches for synthetic evaluation data found no passage establishing the claim. (LLM, conf=0.72)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
No references could be resolved yet.
Research works printed but not linked: 46
- arXiv.org submitters. 2023. arxiv dataset. · DOI
- Stephen Bach, Victor Sanh, Zheng Xin Yong, Albert Webson, Colin Raffel, Nihal V. Nayak, Abheesht Sharma, Taewoon Kim, M Saiful Bari, Thibault Fevry, Zaid Alyafeai, Manan Dey, Andrea Santilli, Zhiqing Sun, Srulik Ben-david, Canwen Xu, Gun- jan Chhablani, Han Wang, Jason Fries, Maged Al- shaibani, Shanya Sharma, Urmish Thakker, Khalid Almubarak, Xiangru Tang, Dragomir Radev, Mike Tian-jian Jiang, and Alexander Rush. 2022. Prompt- Source: An integrated development environment and repository for natural language prompts. In Proceed- ings of the 60th Annual Meeting of the Association for Computational Linguistics: System Demonstra- tions, pages 93-104, Dublin, Ireland. Association for Computational Linguistics. · DOI · Paper page
- Jinze Bai, Shuai Bai, Yunfei Chu, Zeyu Cui, Kai Dang, Xiaodong Deng, Yang Fan, Wenbin Ge, Yu Han, Fei Huang, Binyuan Hui, Luo Ji, Mei Li, Junyang Lin, Runji Lin, Dayiheng Liu, Gao Liu, Chengqiang Lu, Keming Lu, Jianxin Ma, Rui Men, Xingzhang Ren, Xuancheng Ren, Chuanqi Tan, Sinan Tan, Jianhong Tu, Peng Wang, Shijie Wang, Wei Wang, Sheng- guang Wu, Benfeng Xu, Jin Xu, An Yang, Hao Yang, Jian Yang, Shusheng Yang, Yang Yao, Bowen Yu, Hongyi Yuan, Zheng Yuan, Jianwei Zhang, Xingx- uan Zhang, Yichang Zhang, Zhenru Zhang, Chang Zhou, Jingren Zhou, Xiaohuan Zhou, and Tianhang Zhu. 2023. Qwen technical report. arXiv preprint arXiv:2309.16609. · arXiv
- Yuntao Bai, Andy Jones, Kamal Ndousse, Amanda Askell, Anna Chen, Nova DasSarma, Dawn Drain, Stanislav Fort, Deep Ganguli, Tom Henighan, et al. 2022. Training a helpful and harmless assistant with reinforcement learning from human feedback. arXiv preprint arXiv:2204.05862. · arXiv
- Baichuan. 2023. Baichuan 2: Open large-scale lan- guage models. arXiv preprint arXiv:2309.10305. · arXiv
- Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel Ziegler, Jeffrey Wu, Clemens Winter, Chris Hesse, Mark Chen, Eric Sigler, Ma- teusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language models are few-shot learners. In Ad- vances in Neural Information Processing Systems, volume 33, pages 1877-1901.
- Mauro Cettolo, Christian Girardi, and Marcello Fed- erico. 2012. Wit3: Web inventory of transcribed and translated talks. In Proceedings of the Conference of European Association for Machine Translation (EAMT), pages 261-268.
- Yupeng Chang, Xu Wang, Jindong Wang, Yuan Wu, Kaijie Zhu, Hao Chen, Linyi Yang, Xiaoyuan Yi, Cunxiang Wang, Yidong Wang, et al. 2023. A sur- vey on evaluation of large language models. arXiv preprint arXiv:2307.03109. · arXiv
- Howard Chen, Huihan Li, Danqi Chen, and Karthik Narasimhan. 2022. Controllable text genera- tion with language constraints. arXiv preprint arXiv:2212.10466. · arXiv
- Mark Chen, Jerry Tworek, Heewoo Jun, Qiming Yuan, Henrique Ponde de Oliveira Pinto, Jared Ka- plan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, Alex Ray, Raul Puri, Gretchen Krueger, Michael Petrov, Heidy Khlaaf, Girish Sas- try, Pamela Mishkin, Brooke Chan, Scott Gray, Nick Ryder, Mikhail Pavlov, Alethea Power, Lukasz Kaiser, Mohammad Bavarian, Clemens Winter, Philippe Tillet, Felipe Petroski Such, Dave Cum- mings, Matthias Plappert, Fotios Chantzis, Eliza- beth Barnes, Ariel Herbert-Voss, William Hebgen Guss, Alex Nichol, Alex Paino, Nikolas Tezak, Jie Tang, Igor Babuschkin, Suchir Balaji, Shantanu Jain, William Saunders, Christopher Hesse, Andrew N. Carr, Jan Leike, Josh Achiam, Vedant Misra, Evan Morikawa, Alec Radford, Matthew Knight, Miles Brundage, Mira Murati, Katie Mayer, Peter Welinder, Bob McGrew, Dario Amodei, Sam McCandlish, Ilya Sutskever, and Wojciech Zaremba. 2021. Evaluating large language models trained on code.
- Pengyu Cheng and Ruineng Li. 2022. Replacing language model for style transfer. arXiv preprint arXiv:2211.07343. · arXiv
- Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian, Mark Chen, Heewoo Jun, Lukasz Kaiser, Matthias Plappert, Jerry Tworek, Jacob Hilton, Reiichiro Nakano, et al. 2021. Training verifiers to solve math word problems. arXiv preprint arXiv:2110.14168. · arXiv
- Zhengxiao Du, Yujie Qian, Xiao Liu, Ming Ding, Jiezhong Qiu, Zhilin Yang, and Jie Tang. 2022. Glm: General language model pretraining with autoregres- sive blank infilling. In Proceedings of the 60th An- nual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 320-335.
- Angela Fan, Mike Lewis, and Yann Dauphin. 2018. Hierarchical neural story generation. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 889-898, Melbourne, Australia. Association for Computational Linguistics. · DOI · Paper page
- Fabrizio Gilardi, Meysam Alizadeh, and Maël Kubli. 2023. Chatgpt outperforms crowd-workers for text- annotation tasks. arXiv preprint arXiv:2303.15056. · arXiv
- Bogdan Gliwa, Iwona Mochol, Maciej Biesek, and Alek- sander Wawer. 2019. SAMSum corpus: A human- annotated dialogue dataset for abstractive summa- rization. In Proceedings of the 2nd Workshop on New Frontiers in Summarization, pages 70-79, Hong Kong, China. Association for Computational Linguis- tics. · DOI · Paper page
- David Graff, Junbo Kong, Ke Chen, and Kazuaki Maeda. 2003. English gigaword. Linguistic Data Consor- tium, Philadelphia, 4(1):34.
- Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Stein- hardt. 2021. Measuring massive multitask language understanding. Proceedings of the International Con- ference on Learning Representations (ICLR).
- F Huang, H Kwak, and J An. 2023. Is chatgpt better than human annotators? potential and limitations of chatgpt in explaining implicit hate speech. arxiv.
- Yuxin Jiang, Chunkit Chan, Mingyang Chen, and Wei Wang. 2023. Lion: Adversarial distillation of propri- etary large language models. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023, Singapore, De- cember 6-10, 2023, pages 3134-3154. Association for Computational Linguistics. · DOI
- Yuxin Jiang, Yufei Wang, Chuhan Wu, Wanjun Zhong, Xingshan Zeng, Jiahui Gao, Liangyou Li, Xin Jiang, Lifeng Shang, Ruiming Tang, Qun Liu, and Wei Wang. 2024. Learning to edit: Aligning llms with knowledge editing. CoRR, abs/2402.11905. · DOI
- Sumith Kulal, Panupong Pasupat, Kartik Chandra, Mina Lee, Oded Padon, Alex Aiken, and Percy S Liang. 2019. Spoc: Search-based pseudocode to code. Ad- vances in Neural Information Processing Systems, 32.
- Wai-Chung Kwan, Xingshan Zeng, Yuxin Jiang, Yufei Wang, Liangyou Li, Lifeng Shang, Xin Jiang, Qun Liu, and Kam-Fai Wong. 2024. Mt-eval: A multi- turn capabilities evaluation benchmark for large lan- guage models. CoRR, abs/2401.16745. · DOI
- Sha Li, Heng Ji, and Jiawei Han. 2021. Document-level event argument extraction by conditional generation. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computa- tional Linguistics: Human Language Technologies, NAACL-HLT 2021, Online, June 6-11, 2021, pages 894-908. Association for Computational Linguistics. · DOI
- Pierre Lison and Jörg Tiedemann. 2016. OpenSub- titles2016: Extracting large parallel corpora from movie and TV subtitles. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 923-929, Portorož, Slovenia. European Language Resources Association (ELRA).
- Xiao Liu, Hao Yu, Hanchen Zhang, Yifan Xu, Xuanyu Lei, Hanyu Lai, Yu Gu, Hangliang Ding, Kaiwen Men, Kejuan Yang, et al. 2023. Agentbench: Evaluat- ing llms as agents. arXiv preprint arXiv:2308.03688. · arXiv
- George A. Miller. 1992. WordNet: A lexical database for English. In Speech and Natural Language: Pro- ceedings of a Workshop Held at Harriman, New York, February 23-26, 1992.
- Swaroop Mishra, Daniel Khashabi, Chitta Baral, and Hannaneh Hajishirzi. 2022. Cross-task generaliza- tion via natural language crowdsourcing instructions. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3470-3487, Dublin, Ireland. Association for Computational Linguistics. · DOI · Paper page
- Nasrin Mostafazadeh, Nathanael Chambers, Xiaodong He, Devi Parikh, Dhruv Batra, Lucy Vanderwende, Pushmeet Kohli, and James Allen. 2016. A corpus and cloze evaluation for deeper understanding of commonsense stories. In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 839-849, San Diego, California. Association for Computational Linguis- tics. · DOI · Paper page
- Ramesh Nallapati, Bowen Zhou, Caglar Gulcehre, Bing Xiang, et al. 2016. Abstractive text summarization using sequence-to-sequence rnns and beyond. arXiv preprint arXiv:1602.06023. · arXiv
- Shashi Narayan, Shay B. Cohen, and Mirella Lapata. 2018. Don't give me the details, just the summary! topic-aware convolutional neural networks for ex- treme summarization. In Proceedings of the 2018 Conference on Empirical Methods in Natural Lan- guage Processing, pages 1797-1807, Brussels, Bel- gium. Association for Computational Linguistics. · DOI · Paper page
- Jekaterina Novikova, Ondřej Dušek, and Verena Rieser. 2017. The E2E dataset: New challenges for end- to-end generation. In Proceedings of the 18th An- nual SIGdial Meeting on Discourse and Dialogue, pages 201-206, Saarbrücken, Germany. Association for Computational Linguistics. · DOI
- OpenAI. 2023. GPT-4 technical report. CoRR, abs/2303.08774. · arXiv
- Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et al. 2022. Training language models to follow instruc- tions with human feedback. Advances in Neural Information Processing Systems, 35:27730-27744.
- Victor Sanh, Albert Webson, Colin Raffel, Stephen H Bach, Lintang Sutawika, Zaid Alyafeai, Antoine Chaffin, Arnaud Stiegler, Teven Le Scao, Arun Raja, et al. 2021. Multitask prompted training en- ables zero-shot task generalization. arXiv preprint arXiv:2110.08207. · arXiv
- Murray Shanahan, Kyle McDonell, and Laria Reynolds. 2023. Role-play with large language models. arXiv preprint arXiv:2305.16367. · arXiv
- Eric Michael Smith, Diana Gonzalez-Rico, Emily Dinan, and Y-Lan Boureau. 2020. Control- ling style in generated dialogue. arXiv preprint arXiv:2009.10855. · arXiv
- Mirac Suzgun, Nathan Scales, Nathanael Schärli, Se- bastian Gehrmann, Yi Tay, Hyung Won Chung, Aakanksha Chowdhery, Quoc V Le, Ed H Chi, Denny Zhou, , and Jason Wei. 2022. Challenging big-bench tasks and whether chain-of-thought can solve them. arXiv preprint arXiv:2210.09261. · arXiv
- Xiangru Tang, Yiming Zong, Yilun Zhao, Arman Cohan, and Mark Gerstein. 2023. Struc-bench: Are large language models really good at generating complex structured data? arXiv preprint arXiv:2309.08963. · arXiv
- Jörg Tiedemann. 2012. Parallel data, tools and inter- faces in opus. In Lrec, volume 2012, pages 2214- 2218.
- Erik F. Tjong Kim Sang and Fien De Meulder. 2003. Introduction to the CoNLL-2003 shared task: Language-independent named entity recognition. In Proceedings of the Seventh Conference on Natural Language Learning at HLT-NAACL 2003, pages 142- 147.
- Alicia Tsai, Shereen Oraby, Vittorio Perera, Jiun-Yu Kao, Yuheng Du, Anjali Narayan-Chen, Tagyoung Chung, and Dilek Hakkani-Tur. 2021. Style control for schema-guided natural language generation. In Proceedings of the 3rd Workshop on Natural Lan- guage Processing for Conversational AI, pages 228- 242, Online. Association for Computational Linguis- tics. · DOI
- Denny Vrandečić and Markus Krötzsch. 2014. Wiki- data: a free collaborative knowledgebase. Communi- cations of the ACM, 57(10):78-85.
- Yizhong Wang, Yeganeh Kordi, Swaroop Mishra, Alisa Liu, Noah A. Smith, Daniel Khashabi, and Hannaneh Hajishirzi. 2023a. Self-instruct: Aligning language models with self-generated instructions. In Proceed- ings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 13484-13508, Toronto, Canada. Association for Computational Linguistics. · DOI · Paper page
- Yufei Wang, Wanjun Zhong, Liangyou Li, Fei Mi, Xing- shan Zeng, Wenyong Huang, Lifeng Shang, Xin Jiang, and Qun Liu. 2023b. Aligning large lan- guage models with human: A survey. arXiv preprint arXiv:2307.12966. · arXiv
- Zekun Wang, Ge Zhang, Kexin Yang, Ning Shi, Wangchunshu Zhou, Shaochun Hao, Guangzheng Xiong, Yizhi Li, Mong Yuan Sim, Xiuying Chen, et al. 2023c. Interactive natural language processing. arXiv preprint arXiv:2305.13246. · arXiv
Cited by
Sorted by citations
Generalizing Verifiable Instruction Following
Pyatkin, V., Malik, S., Graf, V., Ivison, H., Huang, S., Dasigi, P., Lambert, N., & Hajishirzi, H. (2025) · arXiv · doi:10.48550/arxiv.2507.02833 · Cited by 4 · see citing works
Palmeira Ferraz, T., Mehta, K., Lin, Y.-H., Chang, H.-S., Oraby, S., Liu, S., Subramanian, V., Chung, T., Bansal, M., & Peng, N. (2024) · Findings of the Association for Computational Linguistics: EMNLP 2024 · doi:10.18653/v1/2024.findings-emnlp.458 · Cited by 3 · see citing works
OctoBench: Benchmarking Scaffold-Aware Instruction Following in Repository-Grounded Agentic Coding
Ding, D., Liu, S., Yang, E., Lin, J., Chen, Z., Dou, S., Guo, H., Cheng, W., Zhao, P., Xiao, C., et al. (2026) · arXiv · doi:10.48550/arxiv.2601.10343
- Authors
- Jiang, Y., Wang, Y., Zeng, X., Zhong, W., Li, L., Mi, F., Shang, L., Jiang, X., Liu, Q., & Wang, W.
- Affiliations
- The Hong Kong University of Science and Technology (Guangzhou) (CN)
- Hong Kong University of Science and Technology (HK)
- Venue
- Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Published
- 2024
- Pages
- 4667-4688
- ISSN
- 0736-587X (ISSN-L)
- OpenAlex
- W4402672064
- Cited by
- 55
- References
- 0
- Citations by year
- 2026: 26 · 2025: 24 · 2024: 5
- FWCI
- 13.25
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Proceedings of the conference - Association for Computational Linguistics. Meeting (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- Rare & Special e-Zone (The Hong Kong University of Science and Technology) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Hong Kong University of Science and Technology (2023A03J0013)
- Guangzhou Municipal Science and Technology Project (2023A03J0013, 2023A03J0003)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
- Keywords
- large language models
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
