InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling

Item #:

079017-4270

Details

DOI: https://doi.org/10.52202/079017-4270
Author(s): Rong Bao, Liang Ding, Yuchun Miao, Dacheng Tao, Lefei Zhang, Sen Zhang
Pages: 134387-134429 (43 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/10.52202/079017-4270
Author(s): Rong Bao, Liang Ding, Yuchun Miao, Dacheng Tao, Lefei Zhang, Sen Zhang
Pages: 134387-134429 (43 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)