@article{simplifyrlhfasrewardweightedsfta,
  title = {Simplify RLHF as Reward-Weighted SFT: A Variational Method},
  author = {Yuhao Du and Zhuo Li and Pengyu Cheng and Zhihong Chen and Yuejiao Xie and Xiang Wan and Anningzhe Gao},
  year = {2025},
  eprint = {2502.11026},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2502.11026v1},
}