{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LSXX3IAQ4JEACBLARGK2ZWT274","short_pith_number":"pith:LSXX3IAQ","schema_version":"1.0","canonical_sha256":"5caf7da010e2480105608995acda7aff3c9b4ed0bca933565cfce45cf14f17e8","source":{"kind":"arxiv","id":"2311.05374","version":1},"attestation_state":"computed","paper":{"title":"TencentLLMEval: A Hierarchical Evaluation of Real-World Capabilities for Human-Aligned LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dong Yu, Donlin Zhou, Jing Nie, Lifeng Jin, Pengzhi Wei, Shaobo Wang, Shuyi Xie, Wenlin Yao, Xinhua Feng, Yong Dai, Yuhong Liu, Yujie Lin, Zhengyou Zhang, Zhichao Hu","submitted_at":"2023-11-09T13:58:59Z","abstract_excerpt":"Large language models (LLMs) have shown impressive capabilities across various natural language tasks. However, evaluating their alignment with human preferences remains a challenge. To this end, we propose a comprehensive human evaluation framework to assess LLMs' proficiency in following instructions on diverse real-world tasks. We construct a hierarchical task tree encompassing 7 major areas covering over 200 categories and over 800 tasks, which covers diverse capabilities such as question answering, reasoning, multiturn dialogue, and text generation, to evaluate LLMs in a comprehensive and"},"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":"2311.05374","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-09T13:58:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9e450f32002d08d607cf83195d06dca256676252bcf500a068b0eabac6a9ac58","abstract_canon_sha256":"acd6e8fa4a1a3993ca48a4a89ae37dd0694676963cf57adbfce09c61d88ecbf1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:10:58.790912Z","signature_b64":"6pSRNUf4tdtvxkGwFo0Fiy4ScXGdFVqrAaa0G1tzae8CjeEaz/9+9Z4CgMnkF2AUZrHAYrhUstOVLTceIdeFAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5caf7da010e2480105608995acda7aff3c9b4ed0bca933565cfce45cf14f17e8","last_reissued_at":"2026-07-05T07:10:58.790383Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:10:58.790383Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TencentLLMEval: A Hierarchical Evaluation of Real-World Capabilities for Human-Aligned LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dong Yu, Donlin Zhou, Jing Nie, Lifeng Jin, Pengzhi Wei, Shaobo Wang, Shuyi Xie, Wenlin Yao, Xinhua Feng, Yong Dai, Yuhong Liu, Yujie Lin, Zhengyou Zhang, Zhichao Hu","submitted_at":"2023-11-09T13:58:59Z","abstract_excerpt":"Large language models (LLMs) have shown impressive capabilities across various natural language tasks. However, evaluating their alignment with human preferences remains a challenge. To this end, we propose a comprehensive human evaluation framework to assess LLMs' proficiency in following instructions on diverse real-world tasks. We construct a hierarchical task tree encompassing 7 major areas covering over 200 categories and over 800 tasks, which covers diverse capabilities such as question answering, reasoning, multiturn dialogue, and text generation, to evaluate LLMs in a comprehensive and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.05374","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/2311.05374/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":"2311.05374","created_at":"2026-07-05T07:10:58.790448+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.05374v1","created_at":"2026-07-05T07:10:58.790448+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.05374","created_at":"2026-07-05T07:10:58.790448+00:00"},{"alias_kind":"pith_short_12","alias_value":"LSXX3IAQ4JEA","created_at":"2026-07-05T07:10:58.790448+00:00"},{"alias_kind":"pith_short_16","alias_value":"LSXX3IAQ4JEACBLA","created_at":"2026-07-05T07:10:58.790448+00:00"},{"alias_kind":"pith_short_8","alias_value":"LSXX3IAQ","created_at":"2026-07-05T07:10:58.790448+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2405.14782","citing_title":"Lessons from the Trenches on Reproducible Evaluation of Language Models","ref_index":233,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LSXX3IAQ4JEACBLARGK2ZWT274","json":"https://pith.science/pith/LSXX3IAQ4JEACBLARGK2ZWT274.json","graph_json":"https://pith.science/api/pith-number/LSXX3IAQ4JEACBLARGK2ZWT274/graph.json","events_json":"https://pith.science/api/pith-number/LSXX3IAQ4JEACBLARGK2ZWT274/events.json","paper":"https://pith.science/paper/LSXX3IAQ"},"agent_actions":{"view_html":"https://pith.science/pith/LSXX3IAQ4JEACBLARGK2ZWT274","download_json":"https://pith.science/pith/LSXX3IAQ4JEACBLARGK2ZWT274.json","view_paper":"https://pith.science/paper/LSXX3IAQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.05374&json=true","fetch_graph":"https://pith.science/api/pith-number/LSXX3IAQ4JEACBLARGK2ZWT274/graph.json","fetch_events":"https://pith.science/api/pith-number/LSXX3IAQ4JEACBLARGK2ZWT274/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LSXX3IAQ4JEACBLARGK2ZWT274/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LSXX3IAQ4JEACBLARGK2ZWT274/action/storage_attestation","attest_author":"https://pith.science/pith/LSXX3IAQ4JEACBLARGK2ZWT274/action/author_attestation","sign_citation":"https://pith.science/pith/LSXX3IAQ4JEACBLARGK2ZWT274/action/citation_signature","submit_replication":"https://pith.science/pith/LSXX3IAQ4JEACBLARGK2ZWT274/action/replication_record"}},"created_at":"2026-07-05T07:10:58.790448+00:00","updated_at":"2026-07-05T07:10:58.790448+00:00"}