Direct Preference Optimization: Your Language Model is Secretly a Reward Model

@Article{Rafailov2023DirectPO,
 author = {Rafael Rafailov and Archit Sharma and E. Mitchell and Stefano Ermon and Christopher D. Manning and Chelsea Finn},
 booktitle = {Neural Information Processing Systems},
 journal = {ArXiv},
 title = {Direct Preference Optimization: Your Language Model is Secretly a Reward Model},
 volume = {abs/2305.18290},
 year = {2023}
}