@article{unaunifyingalignmentsofrlhfppodpoand,
  title = {UNA: Unifying Alignments of RLHF/PPO, DPO and KTO by a Generalized Implicit Reward Function},
  author = {Zhichao Wang and Bin Bi and Can Huang and Shiva Kumar Pentyala and Zixu James Zhu and Sitaram Asur and Na Claire Cheng},
  year = {2024},
  eprint = {2408.15339},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2408.15339v2},
}