@misc{zhu2023fine,
  title={Fine-Tuning Language Models with Advantage-Induced Policy Alignment},
  author={Banghua Zhu and Hiteshi Sharma and Felipe Vieira Frujeri and Shi Dong and Chenguang Zhu and Michael I. Jordan and Jiantao Jiao},
  year={2023},
  eprint={2306.02231},
  archivePrefix={arXiv},
  primaryClass={cs.CL},
  url={https://arxiv.org/abs/2306.02231}
}