@article{rsdpoahybridrejectionsamplinganddirect,
  title = {RS-DPO: A Hybrid Rejection Sampling and Direct Preference Optimization Method for Alignment of Large Language Models},
  author = {Saeed Khaki and Jinjin Li and Lan Ma and Liu Yang and Prathap Ramachandra},
  year = {2024},
  eprint = {2402.10038},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2402.10038v2},
}