{"work":{"id":"d65a86ed-cf86-475e-9502-161e34d6a682","openalex_id":null,"doi":null,"arxiv_id":null,"raw_key":"raw:125e4bca36c95b47f3967053","title":"Direct preference optimization: Your language model is secretly a reward model.Advances in neural information processing systems, 36:53728–53741, 2023","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":"2026-05-25T23:57:14.680917+00:00","pith_arxiv_id":null,"created_at":"2026-05-11T14:08:37.641446+00:00","updated_at":"2026-06-05T21:23:00.469572+00:00","title_quality_ok":true,"display_title":"Direct preference optimization: Your language model is secretly a reward model.Advances in neural information processing systems, 36:53728–53741","render_title":"Direct preference optimization: Your language model is secretly a reward model.Advances in neural information processing systems, 36:53728–53741"},"hub":{"state":{"work_id":"d65a86ed-cf86-475e-9502-161e34d6a682","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":18,"external_cited_by_count":null,"distinct_field_count":5,"first_pith_cited_at":"2025-08-24T15:34:17+00:00","last_pith_cited_at":"2026-05-21T13:55:02+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":"2026-06-19T22:58:26.915104+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":4},{"context_role":"method","n":2}],"polarity_counts":[{"context_polarity":"background","n":4},{"context_polarity":"use_method","n":2}],"runs":{},"summary":{},"graph":{},"authors":[]}}