Elamur Research⌕
☰
home / papers / 2025 / MuSC: Improving Complex Instruction Following with Multi-granularity Self-Contrastive Training

MuSC: Improving Complex Instruction Following with Multi-granularity Self-Contrastive Training

Paper · 2025 · Hui Huang, Jiaheng Liu, Yancheng He et al.

Summary

Large language models often fail on instructions that combine many constraints, frequently dropping some of them. Earlier methods for building complex-instruction training data mostly distill from a stronger proprietary model such as GPT-4, which is costly and hard to scale. MuSC (Multi-granularity Self-Contrastive Training) is a self-alignment framework in which the model improves itself with no external model or human labels. At the coarse level, it splits each complex instruction into atomic constraints, randomly removes a portion of them, and reassembles the remainder into a weaker instruction. The response to the full instruction serves as the preferred sample, and the response to the reduced one serves as the dispreferred sample. At the fine level, a token-aware variant of DPO weights individual tokens using the model's calibrated confidence, which concentrates learning on the tokens that break constraints. On open-source models, MuSC improves both complex and general instruction-following benchmarks and outperforms prior self-alignment methods such as Self-Reward. This makes it a cheap, scalable route to stronger instruction following.

Key points

  • The preference data pipeline has four steps: instruction decomposition, constraint dropout (removing α% of the constraints), instruction recombination, and response generation. It works on existing complex queries as well as on Self-Instruct-generated ones.
  • Experiments cover Llama-3-8B-Instruct, Qwen-2-7B-Instruct and the Qwen2.5-Instruct family from 1.5B to 32B. Evaluation uses CFBench, AlpacaEval2 and other benchmarks, mainly judged by a GPT-4-based LLM-as-a-Judge.
  • Results on Qwen2.5-Instruct with MuSC:
    • CFBench PSR rises from 0.28 to 0.41 at 1.5B and from 0.70 to 0.75 at 32B.
    • AlpacaEval2 LC rises from 27.44 to 30.64 at 3B.
  • The framework is not tied to DPO. It also yields gains with SimPO and IPO.
  • On MMLU, GSM8K and HumanEval, the coarse-only version loses a small amount of general ability. Adding the token-level supervision reduces this alignment tax and also makes training converge faster.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓Harbin Institute of TechnologyHarbin · China158 works · 28,841 citations🎓Beijing University of Posts and TelecommunicationsBeijing · China57 works · 32,843 citations🎓Nanjing UniversityNanjing · China74 works · 7,814 citations

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 works

Cite

Cite as Hui Huang, Jiaheng Liu, Yancheng He, Shilong Li, Bing Xu, Conghui Zhu, Muyun Yang and Tiejun Zhao. 2025. MuSC: Improving Complex Instruction Following with Multi-granularity Self-Contrastive Training. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2025.acl-long.523

@inproceedings{huang2025musc,
  title = {{MuSC: Improving Complex Instruction Following with Multi-granularity Self-Contrastive Training}},
  author = {Hui Huang, Jiaheng Liu, Yancheng He, Shilong Li, Bing Xu, Conghui Zhu, Muyun Yang and Tiejun Zhao},
  booktitle = {Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2025},
  doi = {10.18653/v1/2025.acl-long.523},
  url = {https://doi.org/10.18653/v1/2025.acl-long.523}
}

References

65 references, 26 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Mohammad Gheshlaghi Azar, Zhaohan Daniel Guo, Bilal Piot, Remi Munos, Mark Rowland, Michal Valko, and Daniele Calandriello. 2024. A general theoretical paradigm to understand learning from human preferences. In International Conference on Artificial Intelligence and Statistics, pages 4447–4455. PMLR…
  2. Meng Cao, Lei Shu, Lei Yu, Yun Zhu, Nevan Wichers, Yinxiao Liu, and Lei Meng. 2024. Beyond sparse rewards: Enhancing reinforcement learning with language model critique in text generation. Preprint, arXiv:2401.07382. — [arXiv:2401.07382](https://arxiv.org/abs/2401.07382) find
  3. Changyu Chen, Zichen Liu, Chao Du, Tianyu Pang, Qian Liu, Arunesh Sinha, Pradeep Varakantham, and Min Lin. 2024a. Bootstrapping language models with dpo implicit rewards. arXiv preprint arXiv:2406.09760. — [arXiv:2406.09760](https://arxiv.org/abs/2406.09760) find
  4. Mark Chen, Jerry Tworek, Heewoo Jun, Qiming Yuan, Henrique Ponde de Oliveira Pinto, Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, Alex Ray, Raul Puri, Gretchen Krueger, Michael Petrov, Heidy Khlaaf, Girish Sastry, Pamela Mishkin, Brooke Chan, Scott Gray, Nick Ryder, Mikhai… — Evaluating Large Language Models Trained on Code
  5. Yongrui Chen, Haiyun Jiang, Xinting Huang, Shuming Shi, and Guilin Qi. 2024b. Dog-instruct: Towards premium instruction-tuning data via text-grounded instruction wrapping. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Lang… find
  6. Wei-Lin Chiang, Zhuohan Li, Zi Lin, Ying Sheng, Zhanghao Wu, Hao Zhang, Lianmin Zheng, Siyuan Zhuang, Yonghao Zhuang, Joseph E. Gonzalez, Ion Stoica, and Eric P. Xing. 2023. Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality. find
  7. Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian, Mark Chen, Heewoo Jun, Lukasz Kaiser, Matthias Plappert, Jerry Tworek, Jacob Hilton, Reiichiro Nakano, Christopher Hesse, and John Schulman. 2021. Training verifiers to solve math word problems. Preprint, arXiv:2110.14168.
  8. Guanting Dong, Keming Lu, Chengpeng Li, Tingyu Xia, Bowen Yu, Chang Zhou, and Jingren Zhou. 2024. Self-play with execution feedback: Improving instruction-following capabilities of large language models. arXiv preprint arXiv:2406.13542. find
  9. Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, et al. 2024. The llama 3 herd of models. arXiv preprint arXiv:2407.21783.
  10. Yann Dubois, Balázs Galambosi, Percy Liang, and Tatsunori B Hashimoto. 2024. Length-controlled alpacaeval: A simple way to debias automatic evaluators. arXiv preprint arXiv:2404.04475. find
  11. AbdelRahim Elmadany, ElMoatez Billah Nagoudi, and Muhammad Abdul-Mageed. 2023. ORCA: A challenging benchmark for Arabic language understanding. In Findings of the Association for Computational Linguistics: ACL 2023, pages 9559–9586, Toronto, Canada. Association for Computational Linguistics.
  12. Marina Fomicheva, Shuo Sun, Lisa Yankovskaya, Frédéric Blain, Francisco Guzmán, Mark Fishel, Nikolaos Aletras, Vishrav Chaudhary, and Lucia Specia. 2020. Unsupervised quality estimation for neural machine translation. Transactions of the Association for Computational Linguistics, 8:539–555.
  13. Jiahui Geng, Fengyu Cai, Yuxia Wang, Heinz Koeppl, Preslav Nakov, and Iryna Gurevych. 2024. A survey of confidence estimation and calibration in large language models. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language… find
  14. Shangmin Guo, Biao Zhang, Tianlin Liu, Tianqi Liu, Misha Khalman, Felipe Llinares, Alexandre Rame, Thomas Mesnard, Yao Zhao, Bilal Piot, Johan Ferret, and Mathieu Blondel. 2024. Direct language model alignment from online ai feedback. Preprint, arXiv:2402.04792. — [arXiv:2402.04792](https://arxiv.org/abs/2402.04792) find
  15. Qianyu He, Jie Zeng, Qianxi He, Jiaqing Liang, and Yanghua Xiao. 2024a. From complex to simple: Enhancing multi-constraint complex instruction following ability of large language models. Preprint, arXiv:2404.15846. find
  16. Qianyu He, Jie Zeng, Wenhao Huang, Lina Chen, Jin Xiao, Qianxi He, Xunzhe Zhou, Jiaqing Liang, and Yanghua Xiao. 2024b. Can large language models understand real-world complex instructions? In Proceedings of the AAAI Conference on Artificial Intelligence, volume 38, pages 18188–18196. find
  17. Yancheng He, Shilong Li, Jiaheng Liu, Yingshui Tan, Weixun Wang, Hui Huang, Xingyuan Bu, Hangyu Guo, Chengwei Hu, Boren Zheng, et al. 2024c. Chinese simpleqa: A chinese factuality evaluation for large language models. arXiv preprint arXiv:2411.07140.
  18. Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt. 2021. Measuring massive multitask language understanding. In International Conference on Learning Representations.
  19. Hamish Ivison, Yizhong Wang, Jiacheng Liu, Zeqiu Wu, Valentina Pyatkin, Nathan Lambert, Noah A. Smith, Yejin Choi, and Hannaneh Hajishirzi. 2024. Unpacking dpo and ppo: Disentangling best practices for learning from preference feedback. Preprint, arXiv:2406.09279.
  20. Yuxin Jiang, Bo Huang, Yufei Wang, Xingshan Zeng, Liangyou Li, Yasheng Wang, Xin Jiang, Lifeng Shang, Ruiming Tang, and Wei Wang. 2024a. Bridging and modeling correlations in pairwise data for direct preference optimization. Preprint, arXiv:2408.07471. — [arXiv:2408.07471](https://arxiv.org/abs/2408.07471) find
  21. Yuxin Jiang, Yufei Wang, Xingshan Zeng, Wanjun Zhong, Liangyou Li, Fei Mi, Lifeng Shang, Xin Jiang, Qun Liu, and Wei Wang. 2024b. Follow-Bench: A multi-level fine-grained constraints following benchmark for large language models. In Proceedings of the 62nd Annual Meeting of the Association for Compu… find
  22. Siyu Lai, Hui Huang, Dong Jing, Yufeng Chen, Jinan Xu, and Jian Liu. 2021. Saliency-based multi-view mixed language training for zero-shot cross-lingual classification. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 599–610, Punta Cana, Dominican Republic. Associatio… find
  23. Sergey Levine. 2018. Reinforcement learning and control as probabilistic inference: Tutorial and review. ArXiv, abs/1805.00909. — [arXiv:1805.00909](https://arxiv.org/abs/1805.00909) find
  24. Shilong Li, Yancheng He, Hui Huang, Xingyuan Bu, Jiaheng Liu, Hangyu Guo, Weixun Wang, Jihao Gu, Wenbo Su, and Bo Zheng. 2024. 2d-dpo: Scaling direct preference optimization with 2-dimensional supervision. Preprint, arXiv:2410.19720. find
  25. Wing Lian, Bleys Goodson, Eugene Pentland, Austin Cook, Chanvichet Vong, and "Teknium". 2023. Openorca: An open dataset of gpt augmented flan reasoning traces. https://https://huggingface.co/Open-Orca/OpenOrca. find
  26. Yiming Liang, Ge Zhang, Xingwei Qu, Tianyu Zheng, Jiawei Guo, Xinrun Du, Zhenzhu Yang, Jiaheng Liu, Chenghua Lin, Lei Ma, Wenhao Huang, and Jiajun Zhang. 2024. I-sheep: Self-alignment of llm from scratch through an iterative self-enhancement paradigm. Preprint, arXiv:2408.08072. — [arXiv:2408.08072](https://arxiv.org/abs/2408.08072) find
  27. Hunter Lightman, Vineet Kosaraju, Yura Burda, Harri Edwards, Bowen Baker, Teddy Lee, Jan Leike, John Schulman, Ilya Sutskever, and Karl Cobbe. 2023. Let’s verify step by step. arXiv preprint arXiv:2305.20050.
  28. Aiwei Liu, Haoping Bai, Zhiyun Lu, Xiang Kong, Xiaoming Wang, Jiulong Shan, Meng Cao, and Lijie Wen. 2024. Direct large language model alignment through self-rewarding contrastive prompt distillation. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume… find
  29. Jiaheng Liu, Dawei Zhu, Zhiqi Bai, Yancheng He, Huanxuan Liao, Haoran Que, Zekun Wang, Chenchen Zhang, Ge Zhang, Jiebin Zhang, et al. 2025. A comprehensive survey on long context language modeling. arXiv preprint arXiv:2503.17407.
  30. Shayne Longpre, Le Hou, Tu Vu, Albert Webson, Hyung Won Chung, Yi Tay, Denny Zhou, Quoc V. Le, Barret Zoph, Jason Wei, and Adam Roberts. 2023. The flan collection: Designing data and methods for effective instruction tuning. Preprint, arXiv:2301.13688.
  31. Renze Lou, Kai Zhang, Jian Xie, Yuxuan Sun, Janice Ahn, Hanzi Xu, Yu Su, and Wenpeng Yin. 2023. Muffin: Curating multi-faceted instructions for improving instruction following. In The Twelfth International Conference on Learning Representations. find
  32. Renze Lou, Kai Zhang, and Wenpeng Yin. 2024. Large language model instruction following: A survey of progresses and challenges. Computational Linguistics, pages 1–10.
  33. Yu Meng, Mengzhou Xia, and Danqi Chen. 2024. Simpo: Simple preference optimization with a reference-free reward. In Advances in Neural Information Processing Systems (NeurIPS). find
  34. OpenAI, Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, Red Avila, Igor Babuschkin, Suchir Balaji, Valerie Balcom, Paul Baltescu, Haiming Bao, Mohammad Bavarian, Jeff Belgum, Irwan Bello, Ja… — GPT-4 Technical Report
  35. Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Gray, John Schulman, Jacob Hilton, Fraser Kelton, Luke Miller, Maddie Simens, Amanda Askell, Peter Welinder, Paul Christiano, Jan Leike, and Ryan Lowe. 2022. Trai… — Training language models to follow instructions with human feedback
  36. Thomas Palmeira Ferraz, Kartik Mehta, Yu-Hsiang Lin, Haw-Shiuan Chang, Shereen Oraby, Sijia Liu, Vivek Subramanian, Tagyoung Chung, Mohit Bansal, and Nanyun Peng. 2024. LLM self-correction with De-CRIM: Decompose, critique, and refine for enhanced following of instructions with multiple constraints.… find
  37. Xianghe Pang, Shuo Tang, Rui Ye, Yuxin Xiong, Bolun Zhang, Yanfeng Wang, and Siheng Chen. 2024. Self-alignment of large language models via monopolylogue-based social scene simulation. arXiv preprint arXiv:2402.05699. — [arXiv:2402.05699](https://arxiv.org/abs/2402.05699) find
  38. 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 language models.
  39. Rafael Rafailov, Joey Hejna, Ryan Park, and Chelsea Finn. 2024a. From r to q ∗ : Your language model is secretly a q-function. Preprint, arXiv:2404.12358. find
  40. Rafael Rafailov, Archit Sharma, Eric Mitchell, Stefano Ermon, Christopher D. Manning, and Chelsea Finn. 2024b. Direct preference optimization: Your language model is secretly a reward model. Preprint, arXiv:2305.18290.
  41. Swarnadeep Saha, Omer Levy, Asli Celikyilmaz, Mohit Bansal, Jason Weston, and Xian Li. 2024. Branch-solve-merge improves large language model evaluation and generation. Preprint, arXiv:2310.15123. find
  42. John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal policy optimization algorithms. Preprint, arXiv:1707.06347. find
  43. Haoran Sun, Lixin Liu, Junjie Li, Fengyu Wang, Baohua Dong, Ran Lin, and Ruohui Huang. 2024a. Conifer: Improving complex constrained instruction-following ability of large language models. arxiv preprint arXiv:2404.02823.
  44. Yuchong Sun, Che Liu, Kun Zhou, Jinwen Huang, Ruihua Song, Wayne Xin Zhao, Fuzheng Zhang, Di Zhang, and Kun Gai. 2024b. Parrot: Enhancing multi-turn instruction following for large language models. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1:… find
  45. Junya Takayama and Yuki Arase. 2019. Relevant and informative response generation using pointwise mutual information. In Proceedings of the First Workshop on NLP for Conversational AI, pages 133–138, Florence, Italy. Association for Computational Linguistics. find
  46. Rohan Taori, Ishaan Gulrajani, Tianyi Zhang, Yann Dubois, Xuechen Li, Carlos Guestrin, Percy Liang, and Tatsunori B. Hashimoto. 2023. Stanford alpaca: An instruction-following llama model. https://github.com/tatsu-lab/stanford_alpaca. ↗
  47. Yizhong Wang, Hamish Ivison, Pradeep Dasigi, Jack Hessel, Tushar Khot, Khyathi Chandu, David Wadden, Kelsey MacMillan, Noah A Smith, Iz Beltagy, and Hannaneh Hajishirzi. 2023. How far can camels go? exploring the state of instruction tuning on open resources. In Advances in Neural Information Proces…
  48. Yizhong Wang, Yeganeh Kordi, Swaroop Mishra, Alisa Liu, Noah A. Smith, Daniel Khashabi, and Hannaneh Hajishirzi. 2022. Self-instruct: Aligning language model with self generated instructions. find
  49. Zhichao Wang, Bin Bi, Shiva Kumar Pentyala, Kiran Ramnath, Sougata Chaudhuri, Shubham Mehrotra, Zixu, Zhu, Xiang-Bo Mao, Sitaram Asur, Na, and Cheng. 2024. A comprehensive survey of llm alignment techniques: Rlhf, rlaif, ppo, dpo and more. Preprint, arXiv:2407.16216. — [arXiv:2407.16216](https://arxiv.org/abs/2407.16216) find
  50. Bosi Wen, Pei Ke, Xiaotao Gu, Lindong Wu, Hao Huang, Jinfeng Zhou, Wenchuang Li, Binxin Hu, Wendy Gao, Jiaxin Xu, Yiming Liu, Jie Tang, Hongning Wang, and Minlie Huang. 2024. Benchmarking complex instruction-following with multiple constraints composition. Preprint, arXiv:2407.03978. — [arXiv:2407.03978](https://arxiv.org/abs/2407.03978) find
  51. Siwei Wu, Zhongyuan Peng, Xinrun Du, Tuney Zheng, Minghao Liu, Jialong Wu, Jiachen Ma, Yizhi Li, Jian Yang, Wangchunshu Zhou, et al. 2024a. A comparative study on reasoning patterns of openai’s o1 model. arXiv preprint arXiv:2410.13639. — [arXiv:2410.13639](https://arxiv.org/abs/2410.13639) find
  52. Tianhao Wu, Weizhe Yuan, Olga Golovneva, Jing Xu, Yuandong Tian, Jiantao Jiao, Jason Weston, and Sainbayar Sukhbaatar. 2024b. Meta-rewarding language models: Self-improving alignment with llm-as-a-meta-judge. Preprint, arXiv:2407.19594.
  53. Zeqiu Wu, Yushi Hu, Weijia Shi, Nouha Dziri, Alane Suhr, Prithviraj Ammanabrolu, Noah A. Smith, Mari Ostendorf, and Hannaneh Hajishirzi. 2023. Fine-grained human feedback gives better rewards for language model training. In Thirty-seventh Conference on Neural Information Processing Systems.
  54. Can Xu, Qingfeng Sun, Kai Zheng, Xiubo Geng, Pu Zhao, Jiazhan Feng, Chongyang Tao, Qingwei Lin, and Daxin Jiang. 2024. WizardLM: Empowering large pre-trained language models to follow complex instructions. In The Twelfth International Conference on Learning Representations.
  55. An Yang, Baosong Yang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Zhou, Chengpeng Li, Chengyuan Li, Dayiheng Liu, Fei Huang, et al. 2024a. Qwen2 technical report. arXiv preprint arXiv:2407.10671. find
  56. Da Yin, Xiao Liu, Fan Yin, Ming Zhong, Hritik Bansal, Jiawei Han, and Kai-Wei Chang. 2023. Dynosaur: A dynamic growth paradigm for instruction-tuning data curation. arXiv preprint arXiv:2305.14327. find
  57. Weizhe Yuan, Richard Yuanzhe Pang, Kyunghyun Cho, Xian Li, Sainbayar Sukhbaatar, Jing Xu, and Jason Weston. 2024. Self-rewarding language models. Preprint, arXiv:2401.10020. find
  58. Alexander Zhang, Marcus Dong, Jiaheng Liu, Wei Zhang, Yejie Wang, Jian Yang, Ge Zhang, Tianyu Liu, Zhongyuan Peng, Yingshui Tan, et al. 2025. Codecriticbench: A holistic code critique benchmark for large language models. arXiv preprint arXiv:2502.16614. — [arXiv:2502.16614](https://arxiv.org/abs/2502.16614) find
  59. Ruize Zhang, Zelai Xu, Chengdong Ma, Chao Yu, Wei-Wei Tu, Shiyu Huang, Deheng Ye, Wenbo Ding, Yaodong Yang, and Yu Wang. 2024a. A survey on self-play methods in reinforcement learning. Preprint, arXiv:2408.01072. — [arXiv:2408.01072](https://arxiv.org/abs/2408.01072) find
  60. Tao Zhang, Yanjun Shen, Wenjing Luo, Yan Zhang, Hao Liang, Tao Zhang, Fan Yang, Mingan Lin, Yujing Qiao, Weipeng Chen, Bin Cui, Wentao Zhang, and Zenan Zhou. 2024b. Cfbench: A comprehensive constraints-following benchmark for llms. Preprint, arXiv:2408.01122.
  61. Wayne Xin Zhao, Kun Zhou, Junyi Li, Tianyi Tang, Xiaolei Wang, Yupeng Hou, Yingqian Min, Beichen Zhang, Junjie Zhang, Zican Dong, Yifan Du, Chen Yang, Yushuo Chen, Zhipeng Chen, Jinhao Jiang, Ruiyang Ren, Yifan Li, Xinyu Tang, Zikang Liu, Peiyu Liu, Jian-Yun Nie, and Ji-Rong Wen. 2024. A survey of l…
  62. Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric Xing, et al. 2023. Judging llm-as-a-judge with mt-bench and chatbot arena. Advances in Neural Information Processing Systems, 36:46595–46623.
  63. Yaowei Zheng, Richong Zhang, Junhao Zhang, Yanhan Ye, Zheyan Luo, Zhangchi Feng, and Yongqiang Ma. 2024. Llamafactory: Unified efficient fine-tuning of 100+ language models. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations),…
  64. Brian D. Ziebart. 2010. Modeling purposeful adaptive behavior with the principle of maximum causal entropy. find
  65. Zhen Yang, Ming Ding, Tinglin Huang, Yukuo Cen, Junshuai Song, Bin Xu, Yuxiao Dong, and Jie Tang. 2024b. Does negative sampling matter? a review with insights into its theory and applications. Preprint, arXiv:2402.17238. — [arXiv:2402.17238](https://arxiv.org/abs/2402.17238) find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/huang-2025-musc-improving-complex-instruction-following/