{"work":{"id":"759d28e6-9f1c-4043-a34b-2ddfd671d288","openalex_id":null,"doi":null,"arxiv_id":"2402.14762","raw_key":null,"title":"MT-Bench-101: A fine-grained benchmark for evaluating large language models in multi-turn dialogues, 2024","authors":null,"authors_text":"Ge Bai, Jie Liu, Xingyuan Bu, Yancheng He, Jiaheng Liu, Zhanhui Zhou, Zhuoran Lin, Wenbo Su, Tiezheng Ge, Bo Zheng, and Wanli Ouyang","year":2024,"venue":null,"abstract":null,"external_url":"https://arxiv.org/abs/2402.14762","cited_by_count":null,"metadata_source":"arxiv_reference","metadata_fetched_at":"2026-05-20T10:18:11.667759+00:00","pith_arxiv_id":null,"created_at":"2026-05-09T06:00:37.440657+00:00","updated_at":"2026-05-20T10:18:11.667759+00:00","title_quality_ok":true,"display_title":"Mt-bench-101: A fine-grained benchmark for evaluating large language models in multi-turn dialogues","render_title":"Mt-bench-101: A fine-grained benchmark for evaluating large language models in multi-turn dialogues"},"hub":{"state":{"work_id":"759d28e6-9f1c-4043-a34b-2ddfd671d288","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":11,"external_cited_by_count":null,"distinct_field_count":5,"first_pith_cited_at":"2025-07-29T02:05:51+00:00","last_pith_cited_at":"2026-05-18T20:37:14+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":"2026-05-28T04:38:13.175412+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"dataset","n":2},{"context_role":"background","n":1}],"polarity_counts":[{"context_polarity":"use_dataset","n":2},{"context_polarity":"background","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}