{"work":{"id":"3733ff2d-cd95-4776-9fa9-1b2328326749","openalex_id":null,"doi":null,"arxiv_id":null,"raw_key":"raw:4a6cc4513cfd9d773c8b6edf","title":"On-policy distillation of language models: Learning from self-generated mistakes","authors":null,"authors_text":"Rishabh Agarwal, Nino Vieillard, Yongchao Zhou, Piotr Stanczyk, Sabela Ramos Garea, Matthieu Geist, and Olivier Bachem","year":2024,"venue":null,"abstract":null,"external_url":null,"cited_by_count":null,"metadata_source":"raw_reference","metadata_fetched_at":"2026-05-26T11:52:15.381107+00:00","pith_arxiv_id":null,"created_at":"2026-05-12T19:01:47.887179+00:00","updated_at":"2026-06-05T21:23:00.469572+00:00","title_quality_ok":true,"display_title":"On-policy distillation of language models: Learning from self-generated mistakes","render_title":"On-policy distillation of language models: Learning from self-generated mistakes"},"hub":{"state":{"work_id":"3733ff2d-cd95-4776-9fa9-1b2328326749","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":17,"external_cited_by_count":null,"distinct_field_count":3,"first_pith_cited_at":"2026-05-07T12:13:15+00:00","last_pith_cited_at":"2026-05-21T16:18:41+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":"2026-06-30T06:09:30.840858+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":5},{"context_role":"method","n":2}],"polarity_counts":[{"context_polarity":"background","n":5},{"context_polarity":"use_method","n":2}],"runs":{},"summary":{},"graph":{},"authors":[]}}