Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithms

Item #:

079017-4009

Details

DOI: https://doi.org/10.52202/079017-4009
Author(s): Yaswanth Chittepu, Chelsea Finn, Joey Hejna, W. Knox, Scott Niekum, Ryan Park, Rafael Rafailov, Harshit Sikchi
Pages: 126207-126242 (36 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/10.52202/079017-4009
Author(s): Yaswanth Chittepu, Chelsea Finn, Joey Hejna, W. Knox, Scott Niekum, Ryan Park, Rafael Rafailov, Harshit Sikchi
Pages: 126207-126242 (36 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)