@article{selfaugmentedpreferenceoptimizationoff,
  title = {Self-Augmented Preference Optimization: Off-Policy Paradigms for Language Model Alignment},
  author = {Yueqin Yin and Zhendong Wang and Yujia Xie and Weizhu Chen and Mingyuan Zhou},
  year = {2024},
  eprint = {2405.20830},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2405.20830v1},
}