"Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly ..."

Zhihan Liu et al. (2024)

Details and statistics

DOI: 10.48550/ARXIV.2405.16436

access: open

type: Informal or Other Publication

metadata version: 2024-06-18

a service of  Schloss Dagstuhl - Leibniz Center for Informatics