@article{provablymitigatingoveroptimizationinrlhf, title = {Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer}, author = {Zhihan Liu and Miao Lu and Shenao Zhang and Boyi Liu and Hongyi Guo and Yingxiang Yang and Jose Blanchet and Zhaoran Wang}, year = {2024}, eprint = {2405.16436}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2405.16436v3}, }