@article{gibbssamplingfromhumanfeedbackaprovable,
  title = {Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-Constraint},
  author = {Wei Xiong and Hanze Dong and Chenlu Ye and Ziqi Wang and Han Zhong and Heng Ji and Nan Jiang and Tong Zhang},
  year = {2023},
  eprint = {2312.11456},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2312.11456v4},
}