%0 Journal Article %1 journals/corr/abs-1909-08593 %A Ziegler, Daniel M. %A Stiennon, Nisan %A Wu, Jeffrey %A Brown, Tom B. %A Radford, Alec %A Amodei, Dario %A Christiano, Paul %A Irving, Geoffrey %D 2019 %J CoRR %K ChatGPT OpenAI codefreeze llms reinforcement-learning %T Fine-Tuning Language Models from Human Preferences. %U https://arxiv.org/pdf/1909.08593 %V abs/1909.08593

@article{journals/corr/abs-1909-08593, added-at = {2024-01-07T20:53:56.000+0100}, author = {Ziegler, Daniel M. and Stiennon, Nisan and Wu, Jeffrey and Brown, Tom B. and Radford, Alec and Amodei, Dario and Christiano, Paul and Irving, Geoffrey}, biburl = {https://www.bibsonomy.org/bibtex/29841c201b6157f237a90ea4b27f1d85d/ghagerer}, ee = {http://arxiv.org/abs/1909.08593}, interhash = {c891749d0a098748db9eefb5ac27bd70}, intrahash = {9841c201b6157f237a90ea4b27f1d85d}, journal = {CoRR}, keywords = {ChatGPT OpenAI codefreeze llms reinforcement-learning}, timestamp = {2024-01-07T20:53:56.000+0100}, title = {Fine-Tuning Language Models from Human Preferences.}, url = {https://arxiv.org/pdf/1909.08593}, volume = {abs/1909.08593}, year = 2019 }