{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AIRPX2A7PGIMESTNLDSU7MGUUE","short_pith_number":"pith:AIRPX2A7","schema_version":"1.0","canonical_sha256":"0222fbe81f7990c24a6d58e54fb0d4a139d0adfb2e40011d33e48bdb8d8ae521","source":{"kind":"arxiv","id":"2402.14762","version":3},"attestation_state":"computed","paper":{"title":"MT-Bench-101: A Fine-Grained Benchmark for Evaluating Large Language Models in Multi-Turn Dialogues","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bo Zheng, Ge Bai, Jiaheng Liu, Jie Liu, Tiezheng Ge, Wanli Ouyang, Wenbo Su, Xingyuan Bu, Yancheng He, Zhanhui Zhou, Zhuoran Lin","submitted_at":"2024-02-22T18:21:59Z","abstract_excerpt":"The advent of Large Language Models (LLMs) has drastically enhanced dialogue systems. However, comprehensively evaluating the dialogue abilities of LLMs remains a challenge. Previous benchmarks have primarily focused on single-turn dialogues or provided coarse-grained and incomplete assessments of multi-turn dialogues, overlooking the complexity and fine-grained nuances of real-life dialogues. To address this issue, we introduce MT-Bench-101, specifically designed to evaluate the fine-grained abilities of LLMs in multi-turn dialogues. By conducting a detailed analysis of real multi-turn dialog"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2402.14762","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-22T18:21:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b302e60c132b53a1bb2dc33fb364f04c1f115c43bb341c7d51e31e83763c9f26","abstract_canon_sha256":"cfc337d5c7f973666902600275cd45c02125de61cc5903450015de5a736f7882"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:30:59.602195Z","signature_b64":"C5IajbdC6F/lJChKo5JNqsXppeuSGTswIorScYk+3YgzIei+51/FtUSHJ2S+ju/vHo1lJ693ZlOsiqItL+jQCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0222fbe81f7990c24a6d58e54fb0d4a139d0adfb2e40011d33e48bdb8d8ae521","last_reissued_at":"2026-07-05T09:30:59.601677Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:30:59.601677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MT-Bench-101: A Fine-Grained Benchmark for Evaluating Large Language Models in Multi-Turn Dialogues","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bo Zheng, Ge Bai, Jiaheng Liu, Jie Liu, Tiezheng Ge, Wanli Ouyang, Wenbo Su, Xingyuan Bu, Yancheng He, Zhanhui Zhou, Zhuoran Lin","submitted_at":"2024-02-22T18:21:59Z","abstract_excerpt":"The advent of Large Language Models (LLMs) has drastically enhanced dialogue systems. However, comprehensively evaluating the dialogue abilities of LLMs remains a challenge. Previous benchmarks have primarily focused on single-turn dialogues or provided coarse-grained and incomplete assessments of multi-turn dialogues, overlooking the complexity and fine-grained nuances of real-life dialogues. To address this issue, we introduce MT-Bench-101, specifically designed to evaluate the fine-grained abilities of LLMs in multi-turn dialogues. By conducting a detailed analysis of real multi-turn dialog"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.14762","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2402.14762/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2402.14762","created_at":"2026-07-05T09:30:59.601741+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.14762v3","created_at":"2026-07-05T09:30:59.601741+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.14762","created_at":"2026-07-05T09:30:59.601741+00:00"},{"alias_kind":"pith_short_12","alias_value":"AIRPX2A7PGIM","created_at":"2026-07-05T09:30:59.601741+00:00"},{"alias_kind":"pith_short_16","alias_value":"AIRPX2A7PGIMESTN","created_at":"2026-07-05T09:30:59.601741+00:00"},{"alias_kind":"pith_short_8","alias_value":"AIRPX2A7","created_at":"2026-07-05T09:30:59.601741+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09850","citing_title":"Mechanistic Analysis of Alignment Algorithms in Language Models","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04477","citing_title":"Data-dependent Exploration for Online Reinforcement Learning from Human Feedback","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19099","citing_title":"DecisionBench: A Benchmark for Emergent Delegation in Long-Horizon Agentic Workflows","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2507.21433","citing_title":"ReasonCache: Accelerating Large Reasoning Model Serving through KV Cache Sharing","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2509.07177","citing_title":"Towards EnergyGPT: A Large Language Model Specialized for the Energy Sector","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2509.17677","citing_title":"EngiBench: A Benchmark for Evaluating Large Language Models on Engineering Problem Solving","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2512.04695","citing_title":"TRINITY: An Evolved LLM Coordinator","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09557","citing_title":"SPEED-Bench: A Unified and Diverse Benchmark for Speculative Decoding","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16403","citing_title":"Computational Hermeneutics: Evaluating generative AI as a cultural technology","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04060","citing_title":"CoopGuard: Stateful Cooperative Agents Safeguarding LLMs Against Evolving Multi-Round Attacks","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11317","citing_title":"SOMA: Efficient Multi-turn LLM Serving via Small Language Model","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04477","citing_title":"Data-dependent Exploration for Online Reinforcement Learning from Human Feedback","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02083","citing_title":"EditPropBench: Measuring Factual Edit Propagation in Scientific Manuscripts","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AIRPX2A7PGIMESTNLDSU7MGUUE","json":"https://pith.science/pith/AIRPX2A7PGIMESTNLDSU7MGUUE.json","graph_json":"https://pith.science/api/pith-number/AIRPX2A7PGIMESTNLDSU7MGUUE/graph.json","events_json":"https://pith.science/api/pith-number/AIRPX2A7PGIMESTNLDSU7MGUUE/events.json","paper":"https://pith.science/paper/AIRPX2A7"},"agent_actions":{"view_html":"https://pith.science/pith/AIRPX2A7PGIMESTNLDSU7MGUUE","download_json":"https://pith.science/pith/AIRPX2A7PGIMESTNLDSU7MGUUE.json","view_paper":"https://pith.science/paper/AIRPX2A7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.14762&json=true","fetch_graph":"https://pith.science/api/pith-number/AIRPX2A7PGIMESTNLDSU7MGUUE/graph.json","fetch_events":"https://pith.science/api/pith-number/AIRPX2A7PGIMESTNLDSU7MGUUE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AIRPX2A7PGIMESTNLDSU7MGUUE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AIRPX2A7PGIMESTNLDSU7MGUUE/action/storage_attestation","attest_author":"https://pith.science/pith/AIRPX2A7PGIMESTNLDSU7MGUUE/action/author_attestation","sign_citation":"https://pith.science/pith/AIRPX2A7PGIMESTNLDSU7MGUUE/action/citation_signature","submit_replication":"https://pith.science/pith/AIRPX2A7PGIMESTNLDSU7MGUUE/action/replication_record"}},"created_at":"2026-07-05T09:30:59.601741+00:00","updated_at":"2026-07-05T09:30:59.601741+00:00"}