@article{rlcdreinforcementlearningfromcontrast,
  title = {RLCD: Reinforcement Learning from Contrastive Distillation for Language Model Alignment},
  author = {Kevin Yang and Dan Klein and Asli Celikyilmaz and Nanyun Peng and Yuandong Tian},
  year = {2023},
  eprint = {2307.12950},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2307.12950v3},
}