@article{remaxasimpleeffectiveandefficientmethod,
  title = {ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models},
  author = {Ziniu Li and Tian Xu and Yushun Zhang and Zhihang Lin and Yang Yu and Ruoyu Sun and Zhi-Quan Luo},
  year = {2023},
  eprint = {2310.10505},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2310.10505v4},
}