📄 Preference Optimization for Reasoning with Pseudo Feedback

Paper · 2024 · Fangkai Jiao, Geyang Guo, Xingxing Zhang et al.

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

🏢MicrosoftRedmond · United States325 works · 142,931 citations🎓Georgia Institute of TechnologyAtlanta · United States133 works · 24,497 citations🏢SalesforceSan Francisco · United States56 works · 17,867 citations🎓Nanyang Technological UniversitySingapore · Singapore156 works · 25,644 citations

🧭 Fields, topics and concepts

Cite

Cite as Fangkai Jiao, Geyang Guo, Xingxing Zhang, Nancy F. Chen, Shafiq Joty and Furu Wei. 2024. Preference Optimization for Reasoning with Pseudo Feedback. arXiv:2411.16345.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.48550/arxiv.2411.16345 · arXiv 2411.16345

@misc{jiao2024preference,
  title = {{Preference Optimization for Reasoning with Pseudo Feedback}},
  author = {Fangkai Jiao, Geyang Guo, Xingxing Zhang, Nancy F. Chen, Shafiq Joty and Furu Wei},
  year = {2024},
  doi = {10.48550/arxiv.2411.16345},
  eprint = {2411.16345},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2411.16345}
}

References

72 references, 40 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. Gpt-4 technical report. arXiv preprint arXiv:2303.08774, 2023.
2. Sina Alemohammad, Josue Casco-Rodriguez, Lorenzo Luzi, Ahmed Imtiaz Humayun, Hossein Babaei, Daniel LeJeune, Ali Siahkoohi, and Richard G Baraniuk. Self-consuming generative models go mad. arXiv preprint arXiv:2307.01850, 2023. — [arXiv:2307.01850](https://arxiv.org/abs/2307.01850) find
3. Jacob Austin, Augustus Odena, Maxwell Nye, Maarten Bosma, Henryk Michalewski, David Dohan, Ellen Jiang, Carrie Cai, Michael Terry, Quoc Le, et al. Program synthesis with large language models. arXiv preprint arXiv:2108.07732, 2021.
4. Edward Beeching, Shengyi Costa Huang, Albert Jiang, Jia Li, Benjamin Lipkin, Zihan Qina, Kashif Rasul, Ziju Shen, Roman Soletskyi, and Lewis Tunstall. Numinamath 72b cot. https://huggingface.co/AI-MO/NuminaMath-72B-CoT, 2024. ↗
5. Samuel R. Bowman, Jeeyoon Hyun, Ethan Perez, Edwin Chen, Craig Pettit, Scott Heiner, Kamile Lukosiute, Amanda Askell, Andy Jones, Anna Chen, Anna Goldie, Azalia Mirhoseini, Cameron McKinnon, Christopher Olah, Daniela Amodei, Dario Amodei, Dawn Drain, Dustin Li, Eli Tran-Johnson, Jackson Kernion, Jam… — Measuring Progress on Scalable Oversight for Large Language Models
6. Collin Burns, Pavel Izmailov, Jan Hendrik Kirchner, Bowen Baker, Leo Gao, Leopold Aschenbrenner, Yining Chen, Adrien Ecoffet, Manas Joglekar, Jan Leike, Ilya Sutskever, and Jeffrey Wu. Weak-to-strong generalization: Eliciting strong capabilities with weak supervision. In Forty-first International Co…
7. Xin Chan, Xiaoyang Wang, Dian Yu, Haitao Mi, and Dong Yu. Scaling synthetic data creation with 1,000,000,000 personas. CoRR, abs/2406.20094, 2024.
8. Changyu Chen, Zichen Liu, Chao Du, Tianyu Pang, Qian Liu, Arunesh Sinha, Pradeep Varakantham, and Min Lin. Bootstrapping language models with DPO implicit rewards. CoRR, abs/2406.09760, 2024a. — [arXiv:2406.09760](https://arxiv.org/abs/2406.09760) find
9. 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
10. Mark Chen, Jerry Tworek, Heewoo Jun, Qiming Yuan, Henrique Ponde De Oliveira Pinto, Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, et al. Evaluating large language models trained on code. arXiv preprint arXiv:2107.03374, 2021b.
11. Wenhu Chen, Xueguang Ma, Xinyi Wang, and William W Cohen. Program of thoughts prompting: Disentangling computation from reasoning for numerical reasoning tasks. arXiv preprint arXiv:2211.12588, 2022. find
12. Zixiang Chen, Yihe Deng, Huizhuo Yuan, Kaixuan Ji, and Quanquan Gu. Self-play fine-tuning converts weak language models to strong language models. arXiv preprint arXiv:2401.01335, 2024b. find
13. 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. Training verifiers to solve math word problems. arXiv preprint arXiv:2110.14168, 2021a.
14. Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian, Mark Chen, Heewoo Jun, Lukasz Kaiser, Matthias Plappert, Jerry Tworek, Jacob Hilton, Reiichiro Nakano, et al. Training verifiers to solve math word problems. arXiv preprint arXiv:2110.14168, 2021b.
15. DeepSeek-AI, Qihao Zhu, Daya Guo, Zhihong Shao, Dejian Yang, Peiyi Wang, Runxin Xu, Y. Wu, Yukun Li, Huazuo Gao, Shirong Ma, Wangding Zeng, Xiao Bi, Zihui Gu, Hanwei Xu, Damai Dai, Kai Dong, Liyue Zhang, Yishi Piao, Zhibin Gou, Zhenda Xie, Zhewen Hao, Bingxuan Wang, Junxiao Song, Deli Chen, Xin Xie,… — DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence
16. Mucong Ding, Souradip Chakraborty, Vibhu Agrawal, Zora Che, Alec Koppel, Mengdi Wang, Amrit Bedi, and Furong Huang. Sail: Self-improving efficient online alignment of large language models. arXiv preprint arXiv:2406.15567, 2024. — [arXiv:2406.15567](https://arxiv.org/abs/2406.15567) find
17. Hanze Dong, Wei Xiong, Deepanshu Goyal, Yihan Zhang, Winnie Chow, Rui Pan, Shizhe Diao, Jipeng Zhang, Kashun Shum, and Tong Zhang. RAFT: reward ranked finetuning for generative foundation model alignment. TMLR, 2023, 2023.
18. Shihan Dou, Yan Liu, Haoxiang Jia, Limao Xiong, Enyu Zhou, Wei Shen, Junjie Shan, Caishuang Huang, Xiao Wang, Xiaoran Fan, Zhiheng Xi, Yuhao Zhou, Tao Ji, Rui Zheng, Qi Zhang, Xuanjing Huang, and Tao Gui. Stepcoder: Improve code generation with reinforcement learning from compiler feedback. CoRR, ab… — [arXiv:2402.01391](https://arxiv.org/abs/2402.01391) find
19. Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, Anirudh Goyal, Anthony Hartshorn, Aobo Yang, Archi Mitra, Archie Sravankumar, Artem Korenev, Arthur Hinsvark, Arun Rao, Aston Zhang, Aurélien Rodriguez… — The Llama 3 Herd of Models
20. Alex Gu, Baptiste Rozière, Hugh James Leather, Armando Solar-Lezama, Gabriel Synnaeve, and Sida Wang. Cruxeval: A benchmark for code reasoning, understanding and execution. In Forty-first International Conference on Machine Learning, ICML. OpenReview.net, 2024.
21. Daya Guo, Qihao Zhu, Dejian Yang, Zhenda Xie, Kai Dong, Wentao Zhang, Guanting Chen, Xiao Bi, Y. Wu, Y. K. Li, Fuli Luo, Yingfei Xiong, and Wenfeng Liang. Deepseek-coder: When the large language model meets programming - the rise of code intelligence. CoRR, abs/2401.14196, 2024. find
22. Joy He-Yueya, Gabriel Poesia, Rose E Wang, and Noah D Goodman. Solving math word problems by combining language models with symbolic solvers. arXiv preprint arXiv:2304.09102, 2023. find
23. Dan Hendrycks, Steven Basart, Saurav Kadavath, Mantas Mazeika, Akul Arora, Ethan Guo, Collin Burns, Samir Puranik, Horace He, Dawn Song, and Jacob Steinhardt. Measuring coding challenge competence with APPS. In Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks…
24. Dan Hendrycks, Collin Burns, Saurav Kadavath, Akul Arora, Steven Basart, Eric Tang, Dawn Song, and Jacob Steinhardt. Measuring mathematical problem solving with the MATH dataset. In Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks, 2021b.
25. Jiaxin Huang, Shixiang Shane Gu, Le Hou, Yuexin Wu, Xuezhi Wang, Hongkun Yu, and Jiawei Han. Large language models can self-improve. arXiv preprint arXiv:2210.11610, 2022.
26. Binyuan Hui, Jian Yang, Zeyu Cui, Jiaxi Yang, Dayiheng Liu, Lei Zhang, Tianyu Liu, Jiajun Zhang, Bowen Yu, Kai Dang, et al. Qwen2. 5-coder technical report. arXiv preprint arXiv:2409.12186, 2024.
27. Naman Jain, King Han, Alex Gu, Wen-Ding Li, Fanjia Yan, Tianjun Zhang, Sida Wang, Armando Solar-Lezama, Koushik Sen, and Ion Stoica. Livecodebench: Holistic and contamination free evaluation of large language models for code. CoRR, abs/2403.07974, 2024.
28. Fangkai Jiao, Chengwei Qin, Zhengyuan Liu, Nancy F. Chen, and Shafiq Joty. Learning planning-based reasoning by trajectories collection and process reward synthesizing. arXiv preprint arXiv:2402.00658, 2024.
29. Akbir Khan, John Hughes, Dan Valentine, Laura Ruis, Kshitij Sachan, Ansh Radhakrishnan, Edward Grefenstette, Samuel R. Bowman, Tim Rocktäschel, and Ethan Perez. Debating with more persuasive LLMs leads to more truthful answers. In Ruslan Salakhutdinov, Zico Kolter, Katherine Heller, Adrian Weller,… find
30. Mohammad Abdullah Matin Khan, M. Saiful Bari, Xuan Do Long, Weishi Wang, Md. Rizwan Parvez, and Shafiq Joty. Xcodeeval: An execution-based large scale multilingual multitask benchmark for code understanding, generation, translation and retrieval. In Proceedings of the 62nd Annual Meeting of the Asso…
31. Jan Hendrik Kirchner, Yining Chen, Harri Edwards, Jan Leike, Nat McAleese, and Yuri Burda. Prover-verifier games improve legibility of llm outputs. arXiv preprint arXiv:2407.13692, 2024. — [arXiv:2407.13692](https://arxiv.org/abs/2407.13692) find
32. Xin Lai, Zhuotao Tian, Yukang Chen, Senqiao Yang, Xiangru Peng, and Jiaya Jia. Step-dpo: Stepwise preference optimization for long-chain reasoning of llms. CoRR, abs/2406.18629, 2024.
33. Hung Le, Yue Wang, Akhilesh Deepak Gotmare, Silvio Savarese, and Steven Chu-Hong Hoi. Coderl: Mastering code generation through pretrained models and deep reinforcement learning. In Sanmi Koyejo, S. Mohamed, A. Agarwal, Danielle Belgrave, K. Cho, and A. Oh (eds.), Advances in Neural Information Proc…
34. Raymond Li, Loubna Ben Allal, Yangtian Zi, Niklas Muennighoff, Denis Kocetkov, Chenghao Mou, Marc Marone, Christopher Akiki, Jia Li, Jenny Chim, Qian Liu, Evgenii Zheltonozhskii, Terry Yue Zhuo, Thomas Wang, Olivier Dehaene, Mishig Davaadorj, Joel Lamy-Poirier, João Monteiro, Oleh Shliazhko, Nicola… find
35. Yifei Li, Zeqi Lin, Shizhuo Zhang, Qiang Fu, Bei Chen, Jian-Guang Lou, and Weizhu Chen. On the advance of making language models better reasoners. arXiv preprint arXiv:2206.02336, 2022a. — [arXiv:2206.02336](https://arxiv.org/abs/2206.02336) find
36. Yifei Li, Zeqi Lin, Shizhuo Zhang, Qiang Fu, Bei Chen, Jian-Guang Lou, and Weizhu Chen. Making language models better reasoners with step-aware verifier. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 5315– 5333. Association fo…
37. Yujia Li, David H. Choi, Junyoung Chung, Nate Kushman, Julian Schrittwieser, Rémi Leblond, Tom Eccles, James Keeling, Felix Gimeno, Agustin Dal Lago, Thomas Hubert, Peter Choy, Cyprien de Masson d’Autume, Igor Babuschkin, Xinyun Chen, Po-Sen Huang, Johannes Welbl, Sven Gowal, Alexey Cherepanov, Jam… — Competition-Level Code Generation with AlphaCode
38. Hunter Lightman, Vineet Kosaraju, Yuri Burda, Harrison Edwards, Bowen Baker, Teddy Lee, Jan Leike, John Schulman, Ilya Sutskever, and Karl Cobbe. Let’s verify step by step. In The Twelfth International Conference on Learning Representations. OpenReview.net, 2024. — Let's Verify Step by Step
39. Jiate Liu, Yiqin Zhu, Kaiwen Xiao, Qiang Fu, Xiao Han, Wei Yang, and Deheng Ye. RLTF: reinforcement learning from unit test feedback. Trans. Mach. Learn. Res., 2023, 2023. URL https://openreview.net/forum?id=hjYmsV6nXZ. ↗
40. Haipeng Luo, Qingfeng Sun, Can Xu, Pu Zhao, Jianguang Lou, Chongyang Tao, Xiubo Geng, Qingwei Lin, Shifeng Chen, and Dongmei Zhang. Wizardmath: Empowering mathematical reasoning for large language models via reinforced evol-instruct. arXiv preprint arXiv:2308.09583, 2023.
41. Mistral AI Team. Codestral. Codestral-22B-v0.1, 2024a. https://huggingface.co/mistralai/ ↗
42. Mistral AI Team. Mathstral. Mathstral-7B-v0.1, 2024b. https://huggingface.co/mistralai/ ↗
43. Arindam Mitra, Hamed Khanpour, Corby Rosset, and Ahmed Awadallah. Orca-math: Unlocking the potential of slms in grade school math. arXiv preprint arXiv:2402.14830, 2024.
44. Erik Nijkamp, Hiroaki Hayashi, Caiming Xiong, Silvio Savarese, and Yingbo Zhou. Codegen2: Lessons for training llms on programming and natural languages. ICLR, 2023a. find
45. Erik Nijkamp, Bo Pang, Hiroaki Hayashi, Lifu Tu, Huan Wang, Yingbo Zhou, Silvio Savarese, and Caiming Xiong. Codegen: An open large language model for code with multi-turn program synthesis. ICLR, 2023b. find
46. Qwen Team. Code with codeqwen1.5, April 2024. URL https://qwenlm.github.io/ blog/codeqwen1.5/. ↗
47. Rafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D. Manning, Stefano Ermon, and Chelsea Finn. Direct preference optimization: Your language model is secretly a reward model. In Advances in Neural Information Processing Systems, 2023.
48. Baptiste Roziere, Jonas Gehring, Fabian Gloeckle, Sten Sootla, Itai Gat, Xiaoqing Ellen Tan, Yossi Adi, Jingyu Liu, Romain Sauvestre, Tal Remez, et al. Code llama: Open foundation models for code. arXiv preprint arXiv:2308.12950, 2023.
49. John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. Proximal policy optimization algorithms. CoRR, abs/1707.06347, 2017. find
50. Ilia Shumailov, Zakhar Shumaylov, Yiren Zhao, Yarin Gal, Nicolas Papernot, and Ross Anderson. The curse of recursion: Training on generated data makes models forget. arXiv preprint arXiv:2305.17493, 2023.
51. Charlie Snell, Jaehoon Lee, Kelvin Xu, and Aviral Kumar. Scaling LLM test-time compute optimally can be more effective than scaling model parameters. CoRR, abs/2408.03314, 2024.
52. Zhengyang Tang, Xingxing Zhang, Benyou Wang, and Furu Wei. Mathscale: Scaling instruction tuning for mathematical reasoning. arXiv preprint arXiv:2403.02884, 2024. find
53. Zhengwei Tao, Ting-En Lin, Xiancai Chen, Hangyu Li, Yuchuan Wu, Yongbin Li, Zhi Jin, Fei Huang, Dacheng Tao, and Jingren Zhou. A survey on self-evolution of large language models. arXiv preprint arXiv:2404.14387, 2024. — [arXiv:2404.14387](https://arxiv.org/abs/2404.14387) find
54. Rohan Taori, Ishaan Gulrajani, Tianyi Zhang, Yann Dubois, Xuechen Li, Carlos Guestrin, Percy Liang, and Tatsunori B. Hashimoto. Stanford alpaca: An instruction-following llama model. https://github.com/tatsu-lab/stanford_alpaca, 2023. ↗
55. Jonathan Uesato, Nate Kushman, Ramana Kumar, H. Francis Song, Noah Y. Siegel, Lisa Wang, Antonia Creswell, Geoffrey Irving, and Irina Higgins. Solving math word problems with process-and outcome-based feedback. arXiv preprint arXiv:2211.14275, 2022.
56. Peiyi Wang, Lei Li, Zhihong Shao, Runxin Xu, Damai Dai, Yifei Li, Deli Chen, Yu Wu, and Zhifang Sui. Math-shepherd: Verify and reinforce llms step-by-step without human annotations. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics, pp. 9426–9439. Association…
57. Tianduo Wang, Shichen Li, and Wei Lu. Self-training with direct preference optimization improves chain-of-thought reasoning, 2024b. find
58. Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc Le, Ed Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. Self-consistency improves chain of thought reasoning in language models. arXiv preprint arXiv:2203.11171, 2022.
59. Yizhong Wang, Yeganeh Kordi, Swaroop Mishra, Alisa Liu, Noah A. Smith, Daniel Khashabi, and Hannaneh Hajishirzi. Self-instruct: Aligning language models with self-generated instructions. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics, pp. 13484–13508. Asso… find
60. Ziqi Wang, Le Hou, Tianjian Lu, Yuexin Wu, Yunxuan Li, Hongkun Yu, and Heng Ji. Enable language models to implicitly learn self-improvement from data. arXiv preprint arXiv:2310.00898, 2023b. — [arXiv:2310.00898](https://arxiv.org/abs/2310.00898) find
61. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al. Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems, 35:24824–24837, 2022.
62. Yuxiang Wei, Zhe Wang, Jiawei Liu, Yifeng Ding, and Lingming Zhang. Magicoder: Empowering code generation with oss-instruct. In International Conference on Machine Learning. PMLR, 2024. find
63. Yixuan Weng, Minjun Zhu, Shizhu He, Kang Liu, and Jun Zhao. Large language models are reasoners with self-verification. arXiv preprint arXiv:2212.09561, 2, 2022.
64. Martin Weyssow, Aton Kamanda, and Houari A. Sahraoui. Codeultrafeedback: An llm-as-a-judge dataset for aligning large language models to coding preferences. CoRR, abs/2403.09032, 2024. — [arXiv:2403.09032](https://arxiv.org/abs/2403.09032) find
65. Wei Xiong, Hanze Dong, Chenlu Ye, Ziqi Wang, Han Zhong, Heng Ji, Nan Jiang, and Tong Zhang. Iterative preference learning from human feedback: Bridging theory and practice for RLHF under kl-constraint. In Forty-first International Conference on Machine Learning. OpenReview.net, 2024. find
66. An Yang, Baosong Yang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Zhou, Chengpeng Li, Chengyuan Li, Dayiheng Liu, Fei Huang, et al. Qwen2 technical report. arXiv preprint arXiv:2407.10671, 2024a. find
67. An Yang, Beichen Zhang, Binyuan Hui, Bofei Gao, Bowen Yu, Chengpeng Li, Dayiheng Liu, Jianhong Tu, Jingren Zhou, Junyang Lin, Keming Lu, Mingfeng Xue, Runji Lin, Tianyu Liu, Xingzhang Ren, and Zhenru Zhang. Qwen2.5-math technical report: Toward mathematical expert model via self-improvement. CoRR, a…
68. Yuqing Yang, Yan Ma, and Pengfei Liu. arXiv:2407.13647, 2024c. — [arXiv:2407.13647](https://arxiv.org/abs/2407.13647) find
69. Weak-to-strong reasoning. arXiv preprint Longhui Yu, Weisen Jiang, Han Shi, Jincheng Yu, Zhengying Liu, Yu Zhang, James T Kwok, Zhenguo Li, Adrian Weller, and Weiyang Liu. Metamath: Bootstrap your own mathematical questions for large language models. arXiv preprint arXiv:2309.12284, 2023.
70. Weizhe Yuan, Richard Yuanzhe Pang, Kyunghyun Cho, Sainbayar Sukhbaatar, Jing Xu, and Jason Weston. Self-rewarding language models. arXiv preprint arXiv:2401.10020, 2024. find
71. Xiang Yue, Xingwei Qu, Ge Zhang, Yao Fu, Wenhao Huang, Huan Sun, Yu Su, and Wenhu Chen. Mammoth: Building math generalist models through hybrid instruction tuning. arXiv preprint arXiv:2309.05653, 2023.
72. Eric Zelikman, Yuhuai Wu, Jesse Mu, and Noah Goodman. Star: Bootstrapping reasoning with reasoning. Advances in Neural Information Processing Systems, 35:15476–15488, 2022.

Updated 31 October 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/jiao-2024-preference-optimization-reasoning-pseudo-feedback/