Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback

Item #:

079017-1154

Details

DOI: https://doi.org/10.52202/079017-1154
Author(s): Yejin Choi, Hannaneh Hajishirzi, Hamish Ivison, Nathan Lambert, Jiacheng Liu, Valentina Pyatkin, Noah Smith, Yizhong Wang, Zeqiu Wu
Pages: 36602-36633 (32 pages)
Format: PDF Paper Download
Conference: Advances in Neural Information Processing Systems 37
Date/Location: Held 10-15 December 2024, Vancouver, Canada.
Series: Advances in Neural Information Processing Systems 37
Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)

DOI: https://doi.org/10.52202/079017-1154
Author(s): Yejin Choi, Hannaneh Hajishirzi, Hamish Ivison, Nathan Lambert, Jiacheng Liu, Valentina Pyatkin, Noah Smith, Yizhong Wang, Zeqiu Wu
Pages: 36602-36633 (32 pages)
Format: PDF Paper Download
Conference: Advances in Neural Information Processing Systems 37
Date/Location: Held 10-15 December 2024, Vancouver, Canada.
Series: Advances in Neural Information Processing Systems 37
Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)