{"work":{"id":"a7265aa9-5ce8-4a96-acfd-3f069003f21d","openalex_id":null,"doi":null,"arxiv_id":"2312.11456","raw_key":null,"title":"Iterative preference learning from human feedback: Bridging theory and practice for RLHF under KL-constraint.arXiv preprint arXiv:2312.11456,","authors":null,"authors_text":"54 [XDY+24] Wei Xiong, Hanze Dong, Chenlu Ye, Ziqi Wang, Han Zhong, Heng Ji, Nan Jiang, and Tong Zhang","year":2024,"venue":null,"abstract":null,"external_url":"https://arxiv.org/abs/2312.11456","cited_by_count":null,"metadata_source":"arxiv_reference","metadata_fetched_at":"2026-07-03T08:07:45.294768+00:00","pith_arxiv_id":null,"created_at":"2026-05-10T14:10:28.662157+00:00","updated_at":"2026-07-03T08:07:45.294768+00:00","title_quality_ok":true,"display_title":"Iterative preference learning from human feedback: Bridging theory and practice for rlhf under kl-constraint.arXiv preprint arXiv:2312.11456","render_title":"Iterative preference learning from human feedback: Bridging theory and practice for rlhf under kl-constraint.arXiv preprint arXiv:2312.11456"},"hub":{"state":{"work_id":"a7265aa9-5ce8-4a96-acfd-3f069003f21d","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":14,"external_cited_by_count":null,"distinct_field_count":5,"first_pith_cited_at":"2024-01-18T14:43:47+00:00","last_pith_cited_at":"2026-06-29T15:17:42+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":"2026-07-07T14:31:01.804685+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":2}],"polarity_counts":[{"context_polarity":"background","n":1},{"context_polarity":"unclear","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}