%0 Journal Article %1 lee2023rlaif %A Lee, Harrison %A Phatale, Samrat %A Mansoor, Hassan %A Lu, Kellie %A Mesnard, Thomas %A Bishop, Colton %A Carbune, Victor %A Rastogi, Abhinav %D 2023 %J arXiv preprint arXiv:2309.00267 %K rlaif %T Rlaif: Scaling reinforcement learning from human feedback with ai feedback

@article{lee2023rlaif, added-at = {2024-03-13T19:11:59.000+0100}, author = {Lee, Harrison and Phatale, Samrat and Mansoor, Hassan and Lu, Kellie and Mesnard, Thomas and Bishop, Colton and Carbune, Victor and Rastogi, Abhinav}, biburl = {https://www.bibsonomy.org/bibtex/2cb9e020c1fd1a065afbad7d93084ea1b/albinzehe}, interhash = {574ffe25d7bef8255e70eced4b1d7e66}, intrahash = {cb9e020c1fd1a065afbad7d93084ea1b}, journal = {arXiv preprint arXiv:2309.00267}, keywords = {rlaif}, timestamp = {2024-03-13T19:11:59.000+0100}, title = {Rlaif: Scaling reinforcement learning from human feedback with ai feedback}, year = 2023 }