@misc{rosset2024direct,
  title={Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences},
  author={Corby Rosset and Ching-An Cheng and Arindam Mitra and Michael Santacroce and Ahmed Awadallah and Tengyang Xie},
  year={2024},
  eprint={2404.03715},
  archivePrefix={arXiv},
  primaryClass={cs.LG},
  url={https://arxiv.org/abs/2404.03715}
}