@article{rlhfworkflowfromrewardmodelingtoonline, title = {RLHF Workflow: From Reward Modeling to Online RLHF}, author = {Hanze Dong and Wei Xiong and Bo Pang and Haoxiang Wang and Han Zhao and Yingbo Zhou and Nan Jiang and Doyen Sahoo and Caiming Xiong and Tong Zhang}, year = {2024}, eprint = {2405.07863}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2405.07863v3}, }