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

2024 article dpo_paper ○ Not yet verified

Authors

Rafael Rafailov, Archit Sharma, Eric Mitchell, Stefano Ermon, Christopher D. Manning, Chelsea Finn

BibTeX

Local Entry

@article{dpo_paper,
  title = {Direct Preference Optimization: Your Language Model is Secretly a Reward Model},
  author = {Rafael Rafailov and Archit Sharma and Eric Mitchell and Stefano Ermon and Christopher D. Manning and Chelsea Finn},
  year = {2024},
  url = {https://arxiv.org/abs/2305.18290},
  eprint = {2305.18290},
  archiveprefix = {arXiv}
}

From OPENALEX

@article{dpo_paper,
  title = {Direct Preference Optimization: Your Language Model is Secretly a Reward Model},
  author = {Rafael Rafailov and Archit Sharma and Eric Mitchell and Stefano Ermon and Christopher D. Manning and Chelsea Finn},
  year = {2023},
  journal = {arXiv (Cornell University)},
  doi = {10.48550/arxiv.2305.18290}
}