Skip to main content
Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer
- Item #:
- 079017-4399
- UPC:
Details
-
DOI:
https://doi.org/10.52202/079017-4399
-
Author(s):
Jose Blanchet, Hongyi Guo, Boyi Liu, Zhihan Liu, Miao Lu, Zhaoran Wang, Yingxiang Yang, Shenao Zhang
-
Pages:
138663-138697 (35 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/10.52202/079017-4399
-
Author(s):
Jose Blanchet, Hongyi Guo, Boyi Liu, Zhihan Liu, Miao Lu, Zhaoran Wang, Yingxiang Yang, Shenao Zhang
-
Pages:
138663-138697 (35 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)