@misc{yuan2024self, title={Self-Rewarding Language Models}, author={Weizhe Yuan and Richard Yuanzhe Pang and Kyunghyun Cho and Sainbayar Sukhbaatar and Jing Xu and Jason Weston}, year={2024}, eprint={2401.10020}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2401.10020} }