Elamur Research⌕
☰
home / papers / 2024 / AutoPSV: Automated Process-Supervised Verifier

AutoPSV: Automated Process-Supervised Verifier

Paper · 2024 · Jianqiao Lu, Zhiyang Dou, Hongru Wang et al.

Summary

Process-supervised verifiers judge each reasoning step of an LLM solution, which makes them better at reranking answers than outcome-only verifiers. Their weakness is the cost of step labels, which come either from skilled human annotators or from heavy Monte Carlo tree search (MCTS) sampling. AutoPSV avoids both.

The method first trains an outcome-supervised verifier (OSV) with an MSE loss: every prefix of a solution is regressed onto whether the final answer was correct. The trained OSV then scores each step with its estimated chance of reaching a correct answer. Steps where this score drops sharply relative to the previous step are labelled as errors. These automatic labels then train a process-supervised verifier.

Because labelling needs no reference answer, AutoPSV can also use unlabeled questions. Across five mathematics and commonsense reasoning datasets, the verifiers improve best-of-N answer selection over self-consistency. They match or beat MCTS-based labelling at a small fraction of the annotation compute. This matters wherever gold solutions and compute are scarce.

Key points

  • Prompting alone is not enough. Off-the-shelf LLM selectors (Mistral-Instruct, Mixtral-Instruct, Llama2-chat, Qwen; 7B to 72B) were asked to pick the correct answer among five Mixtral-Instruct candidates on GSM8K. Across five prompting strategies, none exceeded about 70% accuracy. For comparison, Mixtral-Instruct alone scores 62.55% Pass@1 and 82.31% Pass@5.

  • Much cheaper labelling. Annotation cost was measured in processed tokens on GSM8K (7,473 questions) and MATH (7,498 questions). AutoPSV costs far less than MCTS labelling because it needs no repeated sampling per step.

  • Gains from unlabeled data. The authors added 7,000 unlabeled math problems generated with WizardLM's Evol-Instruct. With these extra questions, GSM8K selection accuracy rose for every response generator:

    Response generatorOSV onlyMCTS labellingAutoPSV (GSM8K + WizardLM)
    Mistral-Instruct61.1860.8263.11
    Mixtral-Instruct74.9175.1078.15
    Qwen84.9184.8586.77

    Neither OSV-only training nor MCTS can make use of such data.

  • Self-consistency baseline. The corresponding self-consistency scores are 50.03, 69.06 and 81.27, all below the verifier-based results above.

  • Label quality check. A PSV retrained only on OSV-generated step labels stays close to the OSV it learned from (e.g., 71.39 vs. 74.07 for Mixtral-Instruct). This suggests the automatic labels preserve the OSV's signal. Code is at github.com/rookie-joe/AutoPSV (NeurIPS 2024).

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

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksComputational Theory and Mathematics · 252 worksSoftware · 92 works

Cite

Cite as Jianqiao Lu, Zhiyang Dou, Hongru Wang, Zeyu Cao, Jianbo Dai, Yingjia Wan and Zhijiang Guo. 2024. AutoPSV: Automated Process-Supervised Verifier. arXiv:2405.16802.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.48550/arxiv.2405.16802 · arXiv 2405.16802

@misc{lu2024autopsv,
  title = {{AutoPSV: Automated Process-Supervised Verifier}},
  author = {Jianqiao Lu, Zhiyang Dou, Hongru Wang, Zeyu Cao, Jianbo Dai, Yingjia Wan and Zhijiang Guo},
  year = {2024},
  doi = {10.48550/arxiv.2405.16802},
  eprint = {2405.16802},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2405.16802}
}

References

63 references, 35 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. OpenAI. GPT-4 technical report. CoRR, abs/2303.08774, 2023.
  2. Mistral AI. Au large, 2023. find
  3. Anthropic. Introducing the next generation of claude, 2023. find
  4. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed H. Chi, Quoc V. Le, and Denny Zhou. Chain-of-thought prompting elicits reasoning in large language models. In Sanmi Koyejo, S. Mohamed, A. Agarwal, Danielle Belgrave, K. Cho, and A. Oh, editors, Advances in Neural Info…
  5. Yao Fu, Hao Peng, Ashish Sabharwal, Peter Clark, and Tushar Khot. Complexity-based prompting for multi-step reasoning. In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenReview.net, 2023.
  6. Shunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran, Tom Griffiths, Yuan Cao, and Karthik Narasimhan. Tree of thoughts: Deliberate problem solving with large language models. In Alice Oh, Tristan Naumann, Amir Globerson, Kate Saenko, Moritz Hardt, and Sergey Levine, editors, Advances in Neural Informat… find
  7. Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc V. Le, Ed H. Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. Self-consistency improves chain of thought reasoning in language models. In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023.…
  8. Xi Ye and Greg Durrett. The unreliability of explanations in few-shot prompting for textual reasoning. In Sanmi Koyejo, S. Mohamed, A. Agarwal, Danielle Belgrave, K. Cho, and A. Oh, editors, Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Syst…
  9. Yongchao Zhou, Andrei Ioan Muresanu, Ziwen Han, Keiran Paster, Silviu Pitis, Harris Chan, and Jimmy Ba. Large language models are human-level prompt engineers. In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenReview.net, 2023.
  10. Hyung Won Chung, Le Hou, Shayne Longpre, Barret Zoph, Yi Tay, William Fedus, Eric Li, Xuezhi Wang, Mostafa Dehghani, Siddhartha Brahma, Albert Webson, Shixiang Shane Gu, Zhuyun Dai, Mirac Suzgun, Xinyun Chen, Aakanksha Chowdhery, Sharan Narang, Gaurav Mishra, Adams Yu, Vincent Y. Zhao, Yanping Huang… find
  11. Subhabrata Mukherjee, Arindam Mitra, Ganesh Jawahar, Sahaj Agarwal, Hamid Palangi, and Ahmed Awadallah. Orca: Progressive learning from complex explanation traces of GPT-4. CoRR, abs/2306.02707, 2023.
  12. Suriya Gunasekar, Yi Zhang, Jyoti Aneja, Caio César Teodoro Mendes, Allie Del Giorno, Sivakanth Gopi, Mojan Javaheripi, Piero Kauffmann, Gustavo de Rosa, Olli Saarikivi, Adil Salim, Shital Shah, Harkirat Singh Behl, Xin Wang, Sébastien Bubeck, Ronen Eldan, Adam Tauman Kalai, Yin Tat Lee, and Yuanzhi… find
  13. 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. CoRR, abs/2308.09583, 2023.
  14. 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. CoRR, abs/2211.14275, 2022.
  15. Hunter Lightman, Vineet Kosaraju, Yura Burda, Harrison Edwards, Bowen Baker, Teddy Lee, Jan Leike, John Schulman, Ilya Sutskever, and Karl Cobbe. Let’s verify step by step. CoRR, abs/2305.20050, 2023.
  16. Peiyi Wang, Lei Li, Zhihong Shao, R. X. Xu, Damai Dai, Yifei Li, Deli Chen, Y. Wu, and Zhifang Sui. Math-shepherd: Verify and reinforce llms step-by-step without human annotations. CoRR, abs/2312.08935, 2023.
  17. Zihan Wang, Yunxuan Li, Yuexin Wu, Liangchen Luo, Le Hou, Hongkun Yu, and Jingbo Shang. Multi-step problem solving through a verifier: An empirical analysis on model-induced process supervision. CoRR, abs/2402.02658, 2024. find
  18. 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 Anna Rogers, Jordan L. Boyd-Graber, and Naoaki Okazaki, editors, Proceedings of the 61st Annual Meeting of the Association for Computational Li…
  19. Zeqiu Wu, Yushi Hu, Weijia Shi, Nouha Dziri, Alane Suhr, Prithviraj Ammanabrolu, Noah A. Smith, Mari Ostendorf, and Hannaneh Hajishirzi. Fine-grained human feedback gives better rewards for language model training. In Alice Oh, Tristan Naumann, Amir Globerson, Kate Saenko, Moritz Hardt, and Sergey L…
  20. 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. CoRR, abs/2110.14168, 2021.
  21. Fei Yu, Anningzhe Gao, and Benyou Wang. Outcome-supervised verifiers for planning in thematical reasoning. CoRR, abs/2311.09724, 2023. find
  22. Qianli Ma, Haotian Zhou, Tingkai Liu, Jianbo Yuan, Pengfei Liu, Yang You, and Hongxia Yang. Let’s reward step by step: Step-level reward model as the navigators for reasoning. CoRR, abs/2310.10080, 2023. find
  23. Rémi Coulom. Efficient selectivity and backup operators in monte-carlo tree search. In H. Jaap van den Herik, Paolo Ciancarini, and H. H. L. M. Donkers, editors, Computers and Games, 5th International Conference, CG 2006, Turin, Italy, May 29-31, 2006. Revised Papers, volume 4630 of Lecture Notes in… find
  24. David Silver, Aja Huang, Chris J. Maddison, Arthur Guez, Laurent Sifre, George van den Driessche, Julian Schrittwieser, Ioannis Antonoglou, Vedavyas Panneershelvam, Marc Lanctot, Sander Dieleman, Dominik Grewe, John Nham, Nal Kalchbrenner, Ilya Sutskever, Timothy P. Lillicrap, Madeleine Leach, Koray… find
  25. 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,… — Language Models are Few-Shot Learners
  26. Jing Xiong, Zixuan Li, Chuanyang Zheng, Zhijiang Guo, Yichun Yin, Enze Xie, Zhicheng Yang, Qingxing Cao, Haiming Wang, Xiongwei Han, Jing Tang, Chengming Li, and Xiaodan Liang. Dq-lore: Dual queries with low rank approximation re-ranking for in-context learning. In The Twelfth International Conferen…
  27. Takeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa. Large language models are zero-shot reasoners. In Sanmi Koyejo, S. Mohamed, A. Agarwal, Danielle Belgrave, K. Cho, and A. Oh, editors, Advances in Neural Information Processing Systems 35: Annual Conference on Neural…
  28. Michihiro Yasunaga, Xinyun Chen, Yujia Li, Panupong Pasupat, Jure Leskovec, Percy Liang, Ed H. Chi, and Denny Zhou. Large language models as analogical reasoners. CoRR, abs/2310.01714, 2023. find
  29. Jianqiao Lu, Wanjun Zhong, Yufei Wang, Zhijiang Guo, Qi Zhu, Wenyong Huang, Yanlin Wang, Fei Mi, Baojun Wang, Yasheng Wang, Lifeng Shang, Xin Jiang, and Qun Liu. YODA: teacher-student progressive learning for language models. CoRR, abs/2401.15670, 2024. — [arXiv:2401.15670](https://arxiv.org/abs/2401.15670) find
  30. Albert Q. Jiang, Alexandre Sablayrolles, Antoine Roux, Arthur Mensch, Blanche Savary, Chris Bamford, Devendra Singh Chaplot, Diego de Las Casas, Emma Bou Hanna, Florian Bressand, Gianna Lengyel, Guillaume Bour, Guillaume Lample, Lélio Renard Lavaud, Lucile Saulnier, Marie-Anne Lachaux, Pierre Stock,… find
  31. Albert Q. Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de Las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, Lélio Renard Lavaud, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Thibaut Lavril, Thomas Wang, Timothée Lacroix,… find
  32. Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, Dan Bikel, Lukas Blecher, Cristian Canton-Ferrer, Moya Chen, Guillem Cucurull, David Esiobu, Jude Fernandes, Jeremy Fu, Wenyin Fu, Brian Fuller,… — Llama 2: Open Foundation and Fine-Tuned Chat Models
  33. 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, P… — Qwen Technical Report
  34. Yichen Zhu, Minjie Zhu, Ning Liu, Zhicai Ou, Xiaofeng Mou, and Jian Tang. Llava-phi: Efficient multi-modal assistant with small language model. CoRR, abs/2401.02330, 2024. — [arXiv:2401.02330](https://arxiv.org/abs/2401.02330) find
  35. 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. CoRR, abs/2103.03874, 2021.
  36. Rowan Zellers, Ari Holtzman, Yonatan Bisk, Ali Farhadi, and Yejin Choi. Hellaswag: Can a machine really finish your sentence? In Anna Korhonen, David R. Traum, and Lluís Màrquez, editors, Proceedings of the 57th Conference of the Association for Computational Linguistics, ACL 2019, Florence, Italy,… find
  37. Keisuke Sakaguchi, Ronan Le Bras, Chandra Bhagavatula, and Yejin Choi. Winogrande: An adversarial winograd schema challenge at scale. In The Thirty-Fourth AAAI Conference on Artificial Intelligence, AAAI 2020, The Thirty-Second Innovative Applications of Artificial Intelligence Conference, IAAI 2020… find
  38. Joe Stacey, Pasquale Minervini, Haim Dubossarsky, Sebastian Riedel, and Tim Rocktäschel. Avoiding the hypothesis-only bias in natural language inference via ensemble adversarial training. In Bonnie Webber, Trevor Cohn, Yulan He, and Yang Liu, editors, Proceedings of the 2020 Conference on Empirical…
  39. Leo Gao, Jonathan Tow, Baber Abbasi, Stella Biderman, Sid Black, Anthony DiPofi, Charles Foster, Laurence Golding, Jeffrey Hsu, Alain Le Noac’h, Haonan Li, Kyle McDonell, Niklas Muennighoff, Chris Ociepa, Jason Phang, Laria Reynolds, Hailey Schoelkopf, Aviya Skowron, Lintang Sutawika, Eric Tang, Ani… find
  40. Mark Chen, Jerry Tworek, Heewoo Jun, Qiming Yuan, Henrique Pondé de Oliveira Pinto, Jared Kaplan, Harrison 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, Mik… — Evaluating Large Language Models Trained on Code
  41. Can Xu, Qingfeng Sun, Kai Zheng, Xiubo Geng, Pu Zhao, Jiazhan Feng, Chongyang Tao, Qingwei Lin, and Daxin Jiang. Wizardlm: Empowering large pre-trained language models to follow complex instructions. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May…
  42. Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll L. Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, John Schulman, Jacob Hilton, Fraser Kelton, Luke Miller, Maddie Simens, Amanda Askell, Peter Welinder, Paul F. Christiano, Jan Leike, and Ryan Lowe. Train… — Training language models to follow instructions with human feedback
  43. Yuntao Bai, Saurav Kadavath, Sandipan Kundu, Amanda Askell, Jackson Kernion, Andy Jones, Anna Chen, Anna Goldie, Azalia Mirhoseini, Cameron McKinnon, Carol Chen, Catherine Olsson, Christopher Olah, Danny Hernandez, Dawn Drain, Deep Ganguli, Dustin Li, Eli Tran-Johnson, Ethan Perez, Jamie Kerr, Jared… — Constitutional AI: Harmlessness from AI Feedback
  44. Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, Dan Bikel, Lukas Blecher, Cristian Canton-Ferrer, Moya Chen, Guillem Cucurull, David Esiobu, Jude Fernandes, Jeremy Fu, Wenyin Fu, Brian Fuller,… — Llama 2: Open Foundation and Fine-Tuned Chat Models
  45. Liangming Pan, Michael Saxon, Wenda Xu, Deepak Nathani, Xinyi Wang, and William Yang Wang. Automatically correcting large language models: Surveying the landscape of diverse self-correction strategies. CoRR, abs/2308.03188, 2023. find
  46. Patrick Fernandes, Aman Madaan, Emmy Liu, António Farinhas, Pedro Henrique Martins, Amanda Bertsch, José G. C. de Souza, Shuyan Zhou, Tongshuang Wu, Graham Neubig, and André F. T. Martins. Bridging the gap: A survey on integrating (human) feedback for natural language generation. CoRR, abs/2305.0095…
  47. Kevin Yang, Yuandong Tian, Nanyun Peng, and Dan Klein. Re3: Generating longer stories with recursive reprompting and revision. CoRR, abs/2210.06774, 2022. find
  48. Jianqiao Lu, Zhengying Liu, Yingjia Wan, Yinya Huang, Haiming Wang, Zhicheng Yang, Jing Tang, and Zhijiang Guo. Process-driven autoformalization in lean 4. CoRR, abs/2406.01940, 2024. find
  49. Zhibin Gou, Zhihong Shao, Yeyun Gong, Yelong Shen, Yujiu Yang, Nan Duan, and Weizhu Chen. CRITIC: large language models can self-correct with tool-interactive critiquing. CoRR, abs/2305.11738, 2023.
  50. Dong Huang, Jianbo Dai, Han Weng, Puzhen Wu, Yuhao Qing, Jie M. Zhang, Heming Cui, and Zhijiang Guo. SOAP: enhancing efficiency of generated code via self-optimization. CoRR, abs/2405.15189, 2024. — [arXiv:2405.15189](https://arxiv.org/abs/2405.15189) find
  51. Luyu Gao, Zhuyun Dai, Panupong Pasupat, Anthony Chen, Arun Tejasvi Chaganty, Yicheng Fan, Vincent Y. Zhao, Ni Lao, Hongrae Lee, Da-Cheng Juan, and Kelvin Guu. RARR: researching and revising what language models say, using language models. In Anna Rogers, Jordan L. Boyd-Graber, and Naoaki Okazaki, ed…
  52. Wenhao Yu, Zhihan Zhang, Zhenwen Liang, Meng Jiang, and Ashish Sabharwal. Improving language models via plug-and-play retrieval feedback. CoRR, abs/2305.14002, 2023.
  53. Jaehun Jung, Lianhui Qin, Sean Welleck, Faeze Brahman, Chandra Bhagavatula, Ronan Le Bras, and Yejin Choi. Maieutic prompting: Logically consistent reasoning with recursive explanations. In Yoav Goldberg, Zornitsa Kozareva, and Yue Zhang, editors, Proceedings of the 2022 Conference on Empirical Meth…
  54. Sean Welleck, Ximing Lu, Peter West, Faeze Brahman, Tianxiao Shen, Daniel Khashabi, and Yejin Choi. Generating sequences by learning to self-correct. In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenReview.net, 2023.
  55. Yuxuan Yao, Han Wu, Zhijiang Guo, Biyan Zhou, Jiahui Gao, Sichun Luo, Hanxu Hou, Xiaojin Fu, and Linqi Song. Learning from correctness without prompting makes LLM efficient reasoner. CoRR, abs/2403.19094, 2024. — [arXiv:2403.19094](https://arxiv.org/abs/2403.19094) find
  56. Aman Madaan, Niket Tandon, Prakhar Gupta, Skyler Hallinan, Luyu Gao, Sarah Wiegreffe, Uri Alon, Nouha Dziri, Shrimai Prabhumoye, Yiming Yang, Sean Welleck, Bodhisattwa Prasad Majumder, Shashank Gupta, Amir Yazdanbakhsh, and Peter Clark. Self-refine: Iterative refinement with self-feedback. CoRR, abs… find
  57. Noah Shinn, Federico Cassano, Ashwin Gopinath, Karthik Narasimhan, and Shunyu Yao. Reflexion: language agents with verbal reinforcement learning. In Alice Oh, Tristan Naumann, Amir Globerson, Kate Saenko, Moritz Hardt, and Sergey Levine, editors, Advances in Neural Information Processing Systems 36:…
  58. Alec Helbling, Mansi Phute, Matthew Hull, and Duen Horng Chau. LLM self defense: By self examination, llms know they are being tricked. CoRR, abs/2308.07308, 2023. find
  59. Yuxi Xie, Kenji Kawaguchi, Yiran Zhao, James Xu Zhao, Min-Yen Kan, Junxian He, and Michael Qizhe Xie. Self-evaluation guided beam search for reasoning. In Alice Oh, Tristan Naumann, Amir Globerson, Kate Saenko, Moritz Hardt, and Sergey Levine, editors, Advances in Neural Information Processing Syste…
  60. Hao Yan, Saurabh Srivastava, Yintao Tai, Sida I. Wang, Wen-tau Yih, and Ziyu Yao. Learning to simulate natural language feedback for interactive semantic parsing. In Anna Rogers, Jordan L. Boyd-Graber, and Naoaki Okazaki, editors, Proceedings of the 61st Annual Meeting of the Association for Computa… find
  61. Seonghyeon Ye, Yongrae Jo, Doyoung Kim, Sungdong Kim, Hyeonbin Hwang, and Minjoon Seo. Selfee: Iterative self-revising llm empowered by self-feedback generation. Blog post, May 2023. find
  62. Jie Huang, Xinyun Chen, Swaroop Mishra, Huaixiu Steven Zheng, Adams Wei Yu, Xinying Song, and Denny Zhou. Large language models cannot self-correct reasoning yet. CoRR, abs/2310.01798, 2023.
  63. Jianqiao Lu, Wanjun Zhong, Wenyong Huang, Yufei Wang, Fei Mi, Baojun Wang, Weichao Wang, Lifeng Shang, and Qun Liu. SELF: language-driven self-evolution for large language model. CoRR, abs/2310.00533, 2023. — [arXiv:2310.00533](https://arxiv.org/abs/2310.00533) find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/lu-2024-autopsv-automated-process-supervised-verifier/