{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ED2YINHNT7F2UTKBUSXZVQO4WX","short_pith_number":"pith:ED2YINHN","schema_version":"1.0","canonical_sha256":"20f58434ed9fcbaa4d41a4af9ac1dcb5f3c40f89d047fadb658a9b0c3f0b363b","source":{"kind":"arxiv","id":"2401.16745","version":1},"attestation_state":"computed","paper":{"title":"MT-Eval: A Multi-Turn Capabilities Evaluation Benchmark for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kam-Fai Wong, Liangyou Li, Lifeng Shang, Qun Liu, Wai-Chung Kwan, Xingshan Zeng, Xin Jiang, Yufei Wang, Yuxin Jiang","submitted_at":"2024-01-30T04:50:28Z","abstract_excerpt":"Large language models (LLMs) are increasingly relied upon for complex multi-turn conversations across diverse real-world applications. However, existing benchmarks predominantly focus on single-turn evaluations, overlooking the models' capabilities in multi-turn interactions. To address this gap, we introduce MT-Eval, a comprehensive benchmark designed to evaluate multi-turn conversational abilities. By analyzing human-LLM conversations, we categorize interaction patterns into four types: recollection, expansion, refinement, and follow-up. We construct multi-turn queries for each category eith"},"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":"2401.16745","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-30T04:50:28Z","cross_cats_sorted":[],"title_canon_sha256":"49788efadb831d286ad22344b643fcc5ac2678856bc03853dc12d958f4e2e431","abstract_canon_sha256":"b039aa1c9848462c563d625ed289abdee9a5787050a9781f9437b455f05d653e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:38:59.578333Z","signature_b64":"5wwrR5kZQcOofdVZWJ5XkFmK+w7+be2QA6brrwFviJIPHxIFhDWP4b9M0T1mtBFcjp2dmocVUQ9exKhh98LrCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20f58434ed9fcbaa4d41a4af9ac1dcb5f3c40f89d047fadb658a9b0c3f0b363b","last_reissued_at":"2026-07-05T07:38:59.577988Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:38:59.577988Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MT-Eval: A Multi-Turn Capabilities Evaluation Benchmark for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kam-Fai Wong, Liangyou Li, Lifeng Shang, Qun Liu, Wai-Chung Kwan, Xingshan Zeng, Xin Jiang, Yufei Wang, Yuxin Jiang","submitted_at":"2024-01-30T04:50:28Z","abstract_excerpt":"Large language models (LLMs) are increasingly relied upon for complex multi-turn conversations across diverse real-world applications. However, existing benchmarks predominantly focus on single-turn evaluations, overlooking the models' capabilities in multi-turn interactions. To address this gap, we introduce MT-Eval, a comprehensive benchmark designed to evaluate multi-turn conversational abilities. By analyzing human-LLM conversations, we categorize interaction patterns into four types: recollection, expansion, refinement, and follow-up. We construct multi-turn queries for each category eith"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.16745","kind":"arxiv","version":1},"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/2401.16745/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":"2401.16745","created_at":"2026-07-05T07:38:59.578040+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.16745v1","created_at":"2026-07-05T07:38:59.578040+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.16745","created_at":"2026-07-05T07:38:59.578040+00:00"},{"alias_kind":"pith_short_12","alias_value":"ED2YINHNT7F2","created_at":"2026-07-05T07:38:59.578040+00:00"},{"alias_kind":"pith_short_16","alias_value":"ED2YINHNT7F2UTKB","created_at":"2026-07-05T07:38:59.578040+00:00"},{"alias_kind":"pith_short_8","alias_value":"ED2YINHN","created_at":"2026-07-05T07:38:59.578040+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.27914","citing_title":"Does Capability Transfer to Subjective Behavior -- and Would Our Instruments Tell Us? A Self-Evolving, Trust-by-Construction Evaluation Paradigm","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18630","citing_title":"SCICONVBENCH: Benchmarking LLMs on Multi-Turn Clarification for Task Formulation in Computational Science","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19099","citing_title":"DecisionBench: A Benchmark for Emergent Delegation in Long-Horizon Agentic Workflows","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2511.05476","citing_title":"A Metamorphic Testing Perspective on Knowledge Distillation for Language Models of Code: Does the Student Deeply Mimic the Teacher?","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12312","citing_title":"CompliBench: Benchmarking LLM Judges for Compliance Violation Detection in Dialogue Systems","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02083","citing_title":"EditPropBench: Measuring Factual Edit Propagation in Scientific Manuscripts","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ED2YINHNT7F2UTKBUSXZVQO4WX","json":"https://pith.science/pith/ED2YINHNT7F2UTKBUSXZVQO4WX.json","graph_json":"https://pith.science/api/pith-number/ED2YINHNT7F2UTKBUSXZVQO4WX/graph.json","events_json":"https://pith.science/api/pith-number/ED2YINHNT7F2UTKBUSXZVQO4WX/events.json","paper":"https://pith.science/paper/ED2YINHN"},"agent_actions":{"view_html":"https://pith.science/pith/ED2YINHNT7F2UTKBUSXZVQO4WX","download_json":"https://pith.science/pith/ED2YINHNT7F2UTKBUSXZVQO4WX.json","view_paper":"https://pith.science/paper/ED2YINHN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.16745&json=true","fetch_graph":"https://pith.science/api/pith-number/ED2YINHNT7F2UTKBUSXZVQO4WX/graph.json","fetch_events":"https://pith.science/api/pith-number/ED2YINHNT7F2UTKBUSXZVQO4WX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ED2YINHNT7F2UTKBUSXZVQO4WX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ED2YINHNT7F2UTKBUSXZVQO4WX/action/storage_attestation","attest_author":"https://pith.science/pith/ED2YINHNT7F2UTKBUSXZVQO4WX/action/author_attestation","sign_citation":"https://pith.science/pith/ED2YINHNT7F2UTKBUSXZVQO4WX/action/citation_signature","submit_replication":"https://pith.science/pith/ED2YINHNT7F2UTKBUSXZVQO4WX/action/replication_record"}},"created_at":"2026-07-05T07:38:59.578040+00:00","updated_at":"2026-07-05T07:38:59.578040+00:00"}