{"work":{"id":"5d2e1082-e73f-4c1b-a18c-bf0ba1772c23","openalex_id":null,"doi":null,"arxiv_id":null,"raw_key":"raw:1f01b8cbfaa0b9d0c273e973","title":"Direct preference optimization: Your language model is secretly a reward model","authors":null,"authors_text":"Rafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D Manning, Stefano Ermon, and Chelsea Finn","year":2023,"venue":null,"abstract":null,"external_url":null,"cited_by_count":null,"metadata_source":"raw_reference","metadata_fetched_at":"2026-05-27T10:29:02.314340+00:00","pith_arxiv_id":null,"created_at":"2026-05-12T13:56:36.714865+00:00","updated_at":"2026-05-27T10:29:02.314340+00:00","title_quality_ok":true,"display_title":"Direct preference optimization: Your language model is secretly a reward model","render_title":"Direct preference optimization: Your language model is secretly a reward model"},"hub":{"state":{"work_id":"5d2e1082-e73f-4c1b-a18c-bf0ba1772c23","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":39,"external_cited_by_count":null,"distinct_field_count":6,"first_pith_cited_at":"2025-09-26T07:02:22+00:00","last_pith_cited_at":"2026-05-21T17:03:22+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-05-28T12:28:33.784320+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":8},{"context_role":"method","n":3}],"polarity_counts":[{"context_polarity":"background","n":8},{"context_polarity":"use_method","n":3}],"runs":{},"summary":{},"graph":{},"authors":[]}}