%0 Generic %1 hong2024orpo %A Hong, Jiwoo %A Lee, Noah %A Thorne, James %D 2024 %K llm nlp not-so-reinforcement-learning preference-optim %T ORPO: Monolithic Preference Optimization without Reference Model %U https://arxiv.org/abs/2403.07691

@misc{hong2024orpo, added-at = {2024-05-07T15:07:25.000+0200}, archiveprefix = {arXiv}, author = {Hong, Jiwoo and Lee, Noah and Thorne, James}, biburl = {https://www.bibsonomy.org/bibtex/2ce609b031f77d37f9a3ad15d0f7c3f66/antonvlasjuk}, eprint = {2403.07691}, interhash = {799e619703b8713ee0544dfeec4d1ce2}, intrahash = {ce609b031f77d37f9a3ad15d0f7c3f66}, keywords = {llm nlp not-so-reinforcement-learning preference-optim}, primaryclass = {cs.CL}, timestamp = {2024-05-07T15:07:25.000+0200}, title = {ORPO: Monolithic Preference Optimization without Reference Model}, url = {https://arxiv.org/abs/2403.07691}, year = 2024 }