@misc{lee2023rlaif,
  title={RLAIF: Scaling Reinforcement Learning from Human Feedback with AI Feedback},
  author={Harrison Lee and Samrat Phatale and Hassan Mansoor and Kellie Lu and Thomas Mesnard and Colton Bishop and Victor Carbune and Abhinav Rastogi},
  year={2023},
  eprint={2309.00267},
  archivePrefix={arXiv},
  primaryClass={cs.CL},
  url={https://arxiv.org/abs/2309.00267}
}