CoChat
Sign Up
Cited by 5Topic ModelingNatural Language Processing TechniquesMultimodal Machine Learning Applications

The DOI matches its Crossref record; 4 of the 4 references it cites were found in a registry or an index.

Verifiable Format Control for Large Language Model Generations

Open access
Wang, Zhaoyang, Jiang, Jinqi, Zhou, Huichi, Zheng, Wenhao, Zhang, Xuchao, Bansal, Chetan, Yao, Huaxiu·2025·Findings of the Association for Computational Linguistics: NAACL 2025
DOI 10.18653/v1/2025.findings-naacl.194
Open this paper in CoChat — free accountOpen PDF

Abstract

Recent Large Language Models (LLMs) have demonstrated satisfying general instruction following ability.However, small LLMs with about 7B parameters still struggle fine-grained format following (e.g., JSON format), which seriously hinder the advancements of their applications.Most existing methods focus on benchmarking general instruction following while overlook how to improve the specific format following ability for small LLMs.Besides, these methods often rely on evaluations based on advanced LLMs (e.g., GPT-4), which can introduce the intrinsic bias of LLMs and be costly due to the API calls.In this paper, we first curate a fully verifiable format following dataset VFF.In contrast to existing works often adopting external LLMs for instruction-following validations, every sample of VFF can be easily validated with a Python function.Further, we propose to leverage this verifiable feature to synthesize massive data for progressively training small LLMs, in order to improve their format following abilities.Experimental results highlight the prevalent limitations in the format following capabilities of 7B level open-source LLMs and demonstrate the effectiveness of our method in enhancing this essential ability.Write a poem. Question Answer within [[VAR1]] words.

Overview

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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.18653/v1/2025.findings-naacl.194

Cites

4 of 4 references verified0 citation errors · 0 not checkable

Statistics

Verification

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.

A few free checks a day · papers already verified open instantly · results are public

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?

  • To the best of our knowledge, the only other work that generates automatically verifiable training and test data is VFF.

    “To the best of our knowledge, the only other work that generates automatically verifiable training and test data is VFF [30]”

    From Generalizing Verifiable Instruction Following (2025) · cites this paper as [30]

  • VFF showed how their data improves IF performance using SFT and DPO training.

    “showing how their data improves IF performance using SFT and DPO training.”

    From Generalizing Verifiable Instruction Following (2025) · cites this paper as [30]

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Flagged first, then by citations

Research works printed but not linked: 41

  1. Yuntao Bai, Andy Jones, Kamal Ndousse, Amanda Askell, Anna Chen, Nova DasSarma, Dawn Drain, Stanislav Fort, Deep Ganguli, Tom Henighan, Nicholas Joseph, Saurav Kadavath, Jackson Kernion, Tom Conerly, Sheer El-Showk, Nelson Elhage, Zac Hatfield-Dodds, Danny Hernandez, Tristan Hume, Scott Johnston, Shauna Kravec, Liane Lovitt, Neel Nanda, Catherine Olsson, Dario Amodei, Tom Brown, Jack Clark, Sam McCandlish, Chris Olah, Ben Mann, and Jared Kaplan. 2022. Training a Helpful and Harmless Assistant with Reinforce- ment Learning from Human Feedback. arXiv, abs/2204.05862. · arXiv
  2. Yejin Bang, Samuel Cahyawijaya, Nayeon Lee, Wen- liang Dai, Dan Su, Bryan Wilie, Holy Lovenia, Ziwei Ji, Tiezheng Yu, Willy Chung, et al. 2023. A multi- task, multilingual, multimodal evaluation of chatgpt on reasoning, hallucination, and interactivity. arXiv preprint arXiv:2302.04023. · arXiv
  3. Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared 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 M. Ziegler, Jeffrey Wu, Clemens Winter, Christopher Hesse, Mark Chen, Eric Sigler, Mateusz 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 Conference on Neural Information Processing Sys- tems (NeurIPS).
  4. Sébastien Bubeck, Varun Chandrasekaran, Ronen El- dan, Johannes Gehrke, Eric Horvitz, Ece Kamar, Peter Lee, Yin Tat Lee, Yuanzhi Li, Scott Lund- berg, et al. 2023. Sparks of artificial general intelli- gence: Early experiments with gpt-4. arXiv preprint arXiv:2303.12712. · arXiv
  5. Chi-Min Chan, Weize Chen, Yusheng Su, Jianxuan Yu, Wei Xue, Shanghang Zhang, Jie Fu, and Zhiyuan Liu. 2023. Chateval: Towards better llm-based eval- uators through multi-agent debate. arXiv preprint arXiv:2308.07201. · arXiv
  6. Cheng-Han Chiang and Hung-yi Lee. 2023. Can large language models be an alternative to human evalua- tions? In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Vol- ume 1: Long Papers), pages 15607-15631, Toronto, Canada. Association for Computational Linguistics. · DOI · Paper page
  7. Hanze Dong, Wei Xiong, Deepanshu Goyal, Rui Pan, Shizhe Diao, Jipeng Zhang, Kashun Shum, and T. Zhang. 2023. Raft: Reward rAnked Fine- Tuning for Generative Foundation Model Align- ment. Transactions on Machine Learning Research, abs/2304.06767. · arXiv
  8. Yixin Dong, Charlie F Ruan, Yaxing Cai, Ruihang Lai, Ziyi Xu, Yilong Zhao, and Tianqi Chen. 2024. Xgrammar: Flexible and efficient structured genera- tion engine for large language models. arXiv preprint arXiv:2411.15100. · arXiv
  9. Kawin Ethayarajh, Winnie Xu, Niklas Muennighoff, Dan Jurafsky, and Douwe Kiela. 2024. Kto: Model alignment as prospect theoretic optimization. arXiv preprint arXiv:2402.01306. · arXiv
  10. Jinlan Fu, See-Kiong Ng, Zhengbao Jiang, and Pengfei Liu. 2023. Gptscore: Evaluate as you desire. arXiv, abs/2302.04166. · arXiv
  11. Zhibin Gou, Zhihong Shao, Yeyun Gong, yelong shen, Yujiu Yang, Nan Duan, and Weizhu Chen. 2024. CRITIC: Large language models can self-correct with tool-interactive critiquing. In The Twelfth Inter- national Conference on Learning Representations.
  12. Qianyu He, Jie Zeng, Qianxi He, Jiaqing Liang, and Yanghua Xiao. 2024. From complex to simple: En- hancing multi-constraint complex instruction follow- ing ability of large language models. arXiv preprint arXiv:2404.15846. · arXiv
  13. Jiwoo Hong, Noah Lee, and James Thorne. 2024. Orpo: Monolithic preference optimization without reference model. arXiv preprint arXiv:2403.07691, 2(4):5. · arXiv
  14. Jiaxin Huang, Shixiang Gu, Le Hou, Yuexin Wu, Xuezhi Wang, Hongkun Yu, and Jiawei Han. 2023. Large language models can self-improve. In Proceedings of the 2023 Conference on Empirical Methods in Nat- ural Language Processing, pages 1051-1068, Singa- pore. Association for Computational Linguistics. · DOI · Paper page
  15. Neel Jain, Khalid Saifullah, Yuxin Wen, John Kirchen- bauer, Manli Shu, Aniruddha Saha, Micah Goldblum, Jonas Geiping, and Tom Goldstein. 2023. Bring your own data! self-supervised evaluation for large lan- guage models. arXiv preprint arXiv:2306.13651. · arXiv
  16. Yuxin Jiang, Yufei Wang, Xingshan Zeng, Wanjun Zhong, Liangyou Li, Fei Mi, Lifeng Shang, Xin Jiang, Qun Liu, and Wei Wang. 2023b. Follow- bench: A multi-level fine-grained constraints follow- ing benchmark for large language models. arXiv preprint arXiv:2310.20410. · arXiv
  17. Zaifan Jiang, Xing Huang, and Chao Wei. 2023c. Pref- erence as reward, maximum preference optimiza- tion with importance sampling. arXiv preprint arXiv:2312.16430. · arXiv
  18. Yen-Ting Lin and Yun-Nung Chen. 2023. LLM-eval: Unified multi-dimensional automatic evaluation for open-domain conversations with large language mod- els. In Proceedings of the 5th Workshop on NLP for Conversational AI (NLP4ConvAI 2023), pages 47- 58, Toronto, Canada. Association for Computational Linguistics. · DOI
  19. Yang Liu, Dan Iter, Yichong Xu, Shuohang Wang, Ruochen Xu, and Chenguang Zhu. 2023a. G-eval: Nlg evaluation using gpt-4 with better human align- ment (2023). URL http://arxiv. org/abs/2303.16634.
  20. Yuxuan Liu, Tianchi Yang, Shaohan Huang, Zihan Zhang, Haizhen Huang, Furu Wei, Weiwei Deng, Feng Sun, and Qi Zhang. 2023b. Calibrating llm- based evaluator. arXiv, abs/2309.13308. · arXiv
  21. Shayne Longpre, Le Hou, Tu Vu, Albert Webson, Hyung Won Chung, Yi Tay, Denny Zhou, Quoc V Le, Barret Zoph, Jason Wei, et al. 2023. The flan collection: Designing data and methods for effective instruction tuning. In International Conference on Machine Learning, pages 22631-22648.
  22. PMLR.
  23. Jingkun Ma, Runzhe Zhan, Derek F Wong, and Lidia S Chao. 2024. Activate integrated controllable genera- tion with soft prompt. In CCF International Confer- ence on Natural Language Processing and Chinese Computing, pages 239-251. Springer.
  24. Yu Meng, Mengzhou Xia, and Danqi Chen. 2024. Simpo: Simple preference optimization with a reference-free reward. arXiv preprint arXiv:2405.14734. · arXiv
  25. Swaroop Mishra, Daniel Khashabi, Chitta Baral, and Hannaneh Hajishirzi. 2021. Cross-task generaliza- tion via natural language crowdsourcing instructions. arXiv preprint arXiv:2104.08773. · arXiv
  26. OpenAI. 2023. Gpt-4 technical report. arXiv, abs/2303.08774. · arXiv
  27. 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 in- formation processing systems, 35:27730-27744.
  28. Yiwei Qin, Kaiqiang Song, Yebowen Hu, Wenlin Yao, Sangwoo Cho, Xiaoyang Wang, Xuansheng Wu, Fei Liu, Pengfei Liu, and Dong Yu. 2024. Infobench: Evaluating instruction following ability in large lan- guage models. arXiv.
  29. Haoran Sun, Lixin Liu, Junjie Li, Fengyu Wang, Bao- hua Dong, Ran Lin, and Ruohui Huang. 2024. Conifer: Improving complex constrained instruction- following ability of large language models. arxiv preprint arXiv:2404.02823. · arXiv
  30. Hugo Touvron, Louis Martin, Kevin Stone, Peter Al- bert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, Dan Bikel, Lukas Blecher, Cristian Canton Ferrer, et al. 2023a. Llama 2: Open foundation and fine-tuned chat models. arXiv, abs/2307.09288. · arXiv
  31. Hugo Touvron, Louis Martin, Kevin Stone, Peter Al- bert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, et al. 2023b. Llama 2: Open founda- tion and fine-tuned chat models. arXiv preprint arXiv:2307.09288. · arXiv
  32. Yidong Wang, Zhuohao Yu, Zhengran Zeng, Linyi Yang, Cunxiang Wang, Hao Chen, Chaoya Jiang, Rui Xie, Jindong Wang, Xing Xie, et al. 2023a. Pandalm: An automatic evaluation benchmark for llm instruction tuning optimization. arXiv preprint arXiv:2306.05087. · arXiv
  33. Yizhong Wang, Yeganeh Kordi, Swaroop Mishra, Alisa Liu, Noah A. Smith, Daniel Khashabi, and Hannaneh Hajishirzi. 2023b. 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
  34. Zhaoyang Wang, Shaohan Huang, Yuxuan Liu, Jiahai Wang, Minghui Song, Zihan Zhang, Haizhen Huang, Furu Wei, Weiwei Deng, Feng Sun, and Qi Zhang. 2023c. Democratizing reasoning ability: Tailored learning from large language model. In Proceed- ings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 1948-1966, Singapore. Association for Computational Linguis- tics. · DOI
  35. Congying Xia, Chen Xing, Jiangshu Du, Xinyi Yang, Yihao Feng, Ran Xu, Wenpeng Yin, and Caim- ing Xiong. 2024. Fofo: A benchmark to evaluate llms' format-following capability. arXiv preprint arXiv:2402.18667. · arXiv
  36. Can Xu, Qingfeng Sun, Kai Zheng, Xiubo Geng, Pu Zhao, Jiazhan Feng, Chongyang Tao, Qingwei Lin, and Daxin Jiang. 2023. Wizardlm: Empowering large pre-trained language models to follow complex instructions. In The Twelfth International Conference on Learning Representations.
  37. Li Yizhi, Ge Zhang, Xingwei Qu, Jiali Li, Zhaoqun Li, Zekun Wang, Hao Li, Ruibin Yuan, Yi Ma, Kai Zhang, Wangchunshu Zhou, Yiming Liang, Lei Zhang, Lei Ma, Jiajun Zhang, Zuowen Li, Stephen W. Huang, Chenghua Lin, Wenhu Chen, and Jie Fu. 2024. Cif-Bench: A Chinese Instruction-Following Benchmark for Evaluating the Generalizability of Large Language Models. arXiv.
  38. Shengyu Zhang, Linfeng Dong, Xiaoya Li, Sen Zhang, Xiaofei Sun, Shuhe Wang, Jiwei Li, Runyi Hu, Tian- wei Zhang, Fei Wu, et al. 2023. Instruction tuning for large language models: A survey. arXiv preprint arXiv:2308.10792. · arXiv
  39. Yaowei Zheng, Richong Zhang, Junhao Zhang, Yanhan Ye, Zheyan Luo, and Yongqiang Ma. 2024. Llamafac- tory: Unified efficient fine-tuning of 100+ language models. arXiv preprint arXiv:2403.13372. · arXiv
  40. Chunting Zhou, Pengfei Liu, Puxin Xu, Srini Iyer, Jiao Sun, Yuning Mao, Xuezhe Ma, Avia Efrat, Ping Yu, L. Yu, Susan Zhang, Gargi Ghosh, M. Lewis, Luke Zettlemoyer, and Omer Levy. 2023a. Lima: Less Is More for Alignment. In Thirty-seventh Conference on Neural Information Processing Systems, volume abs/2305.11206. · arXiv
  41. Jeffrey Zhou, Tianjian Lu, Swaroop Mishra, Siddhartha Brahma, Sujoy Basu, Yi Luan, Denny Zhou, and Le Hou. 2023b. Instruction-Following Evaluation for Large Language Models. arXiv, abs/2311.07911. · arXiv

Cited by

Sorted by citations

Metadata

Authors
Wang, Z., Jiang, J., Zhou, H., Zheng, W., Zhang, X., Bansal, C., & Yao, H.
Affiliations
  • University of North Carolina at Chapel Hill (US)
  • Imperial College London (GB)
  • Microsoft (United States) (US)
ORCID
Venue
Findings of the Association for Computational Linguistics: NAACL 2025
Publisher
Association for Computational Linguistics
Published
2025
Pages
3499-3513
DOI
10.18653/v1/2025.findings-naacl.194
OpenAlex
W4411113123
Cited by
5
References
4
Citations by year
2026: 4 · 2025: 1
FWCI
3.51
Type
conference paper
Language
en
Open access
Licence
cc-by
Locations
  • Findings of the Association for Computational Linguistics: NAACL (publishedVersion, cc-by)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
  • Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
Keywords
large language models, synthetic data generation, instruction following, open-source LLMs, data curation

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