%0 Generic %1 rafailov2023direct %A Rafailov, Rafael %A Sharma, Archit %A Mitchell, Eric %A Ermon, Stefano %A Manning, Christopher D. %A Finn, Chelsea %D 2023 %K feedback nlp %T Direct Preference Optimization: Your Language Model is Secretly a Reward Model

@misc{rafailov2023direct, added-at = {2024-04-19T12:49:40.000+0200}, archiveprefix = {arXiv}, author = {Rafailov, Rafael and Sharma, Archit and Mitchell, Eric and Ermon, Stefano and Manning, Christopher D. and Finn, Chelsea}, biburl = {https://www.bibsonomy.org/bibtex/20e2dfe25ee07c86585f5c1f7a5be3d92/jonas.kaiser}, description = {[2305.18290] Direct Preference Optimization: Your Language Model is Secretly a Reward Model}, eprint = {2305.18290}, interhash = {5de55bbe56b91e84c7e7d39ba86548ab}, intrahash = {0e2dfe25ee07c86585f5c1f7a5be3d92}, keywords = {feedback nlp}, primaryclass = {cs.LG}, timestamp = {2024-04-19T12:49:40.000+0200}, title = {Direct Preference Optimization: Your Language Model is Secretly a Reward Model}, year = 2023 }