@misc{chen2024self, title={Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models}, author={Zixiang Chen and Yihe Deng and Huizhuo Yuan and Kaixuan Ji and Quanquan Gu}, year={2024}, eprint={2401.01335}, archivePrefix={arXiv}, primaryClass={cs.LG}, url={https://arxiv.org/abs/2401.01335} }