@article{
dong2024rlhf,
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},
journal={Transactions on Machine Learning Research},
issn={2835-8856},
year={2024},
url={https://openreview.net/forum?id=a13aYUU9eU},
note={}
}