@misc{saunders2022self, title={Self-critiquing models for assisting human evaluators}, author={William Saunders and Catherine Yeh and Jeff Wu and Steven Bills and Long Ouyang and Jonathan Ward and Jan Leike}, year={2022}, eprint={2206.05802}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2206.05802} }