Direct preference optimization: Your language model is secretly a reward model

{
  "doi": null,
  "year": 2023,
  "title": "Direct preference optimization: Your language model is secretly a reward model",
  "venue": "Advances in Neural Information Processing Systems",
  "authors": [
    "Rafailov, R.",
    "Sharma, A.",
    "Mitchell, E.",
    "Manning, C. D.",
    "Ermon, S.",
    "Finn, C."
  ],
  "arxiv_id": null,
  "s2_paper_id": null,
  "ingest_status": "referenced-only"
}