@misc{stiennon2020learning, title={Learning to summarize from human feedback}, author={Nisan Stiennon and Long Ouyang and Jeff Wu and Daniel M. Ziegler and Ryan Lowe and Chelsea Voss and Alec Radford and Dario Amodei and Paul Christiano}, year={2020}, eprint={2009.01325}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2009.01325} }