{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KVEJ77XWX3OK736IFD4F3PAXDR","short_pith_number":"pith:KVEJ77XW","schema_version":"1.0","canonical_sha256":"55489ffef6bedcafefc828f85dbc171c5124273fda923e097aa09df2df2e4423","source":{"kind":"arxiv","id":"2401.12794","version":3},"attestation_state":"computed","paper":{"title":"Benchmarking LLMs via Uncertainty Quantification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Derek F. Wong, Emine Yilmaz, Fanghua Ye, Jianhui Pang, Longyue Wang, Mingming Yang, Shuming Shi, Zhaopeng Tu","submitted_at":"2024-01-23T14:29:17Z","abstract_excerpt":"The proliferation of open-source Large Language Models (LLMs) from various institutions has highlighted the urgent need for comprehensive evaluation methods. However, current evaluation platforms, such as the widely recognized HuggingFace open LLM leaderboard, neglect a crucial aspect -- uncertainty, which is vital for thoroughly assessing LLMs. To bridge this gap, we introduce a new benchmarking approach for LLMs that integrates uncertainty quantification. Our examination involves nine LLMs (LLM series) spanning five representative natural language processing tasks. Our findings reveal that: "},"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":"2401.12794","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-23T14:29:17Z","cross_cats_sorted":[],"title_canon_sha256":"44b96fa7ce0bdf51123806868b7423b8c716abf4806a2ea084474fd43843777a","abstract_canon_sha256":"a37929bb11a3397da1245a1b2a38d5d8808cea820b1bb31ebcb30e64498f9e7b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:29:13.728685Z","signature_b64":"R1/SKGiD0Ro19ZaLj5zQu9sFraFqRUFqFgHPZT780FBGUk8ZqFROMRw8agwCstjsms31uSQ7noFtxtubuyiyBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55489ffef6bedcafefc828f85dbc171c5124273fda923e097aa09df2df2e4423","last_reissued_at":"2026-07-05T09:29:13.728193Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:29:13.728193Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking LLMs via Uncertainty Quantification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Derek F. Wong, Emine Yilmaz, Fanghua Ye, Jianhui Pang, Longyue Wang, Mingming Yang, Shuming Shi, Zhaopeng Tu","submitted_at":"2024-01-23T14:29:17Z","abstract_excerpt":"The proliferation of open-source Large Language Models (LLMs) from various institutions has highlighted the urgent need for comprehensive evaluation methods. However, current evaluation platforms, such as the widely recognized HuggingFace open LLM leaderboard, neglect a crucial aspect -- uncertainty, which is vital for thoroughly assessing LLMs. To bridge this gap, we introduce a new benchmarking approach for LLMs that integrates uncertainty quantification. Our examination involves nine LLMs (LLM series) spanning five representative natural language processing tasks. Our findings reveal that: "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.12794","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/2401.12794/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":"2401.12794","created_at":"2026-07-05T09:29:13.728245+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.12794v3","created_at":"2026-07-05T09:29:13.728245+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.12794","created_at":"2026-07-05T09:29:13.728245+00:00"},{"alias_kind":"pith_short_12","alias_value":"KVEJ77XWX3OK","created_at":"2026-07-05T09:29:13.728245+00:00"},{"alias_kind":"pith_short_16","alias_value":"KVEJ77XWX3OK736I","created_at":"2026-07-05T09:29:13.728245+00:00"},{"alias_kind":"pith_short_8","alias_value":"KVEJ77XW","created_at":"2026-07-05T09:29:13.728245+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2410.06431","citing_title":"Functional-level Uncertainty Quantification for Calibrated Fine-tuning on LLMs","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2501.09775","citing_title":"Multiple Choice Questions: Reasoning Makes Large Language Models (LLMs) More Self-Confident, Especially When They are Wrong","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KVEJ77XWX3OK736IFD4F3PAXDR","json":"https://pith.science/pith/KVEJ77XWX3OK736IFD4F3PAXDR.json","graph_json":"https://pith.science/api/pith-number/KVEJ77XWX3OK736IFD4F3PAXDR/graph.json","events_json":"https://pith.science/api/pith-number/KVEJ77XWX3OK736IFD4F3PAXDR/events.json","paper":"https://pith.science/paper/KVEJ77XW"},"agent_actions":{"view_html":"https://pith.science/pith/KVEJ77XWX3OK736IFD4F3PAXDR","download_json":"https://pith.science/pith/KVEJ77XWX3OK736IFD4F3PAXDR.json","view_paper":"https://pith.science/paper/KVEJ77XW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.12794&json=true","fetch_graph":"https://pith.science/api/pith-number/KVEJ77XWX3OK736IFD4F3PAXDR/graph.json","fetch_events":"https://pith.science/api/pith-number/KVEJ77XWX3OK736IFD4F3PAXDR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KVEJ77XWX3OK736IFD4F3PAXDR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KVEJ77XWX3OK736IFD4F3PAXDR/action/storage_attestation","attest_author":"https://pith.science/pith/KVEJ77XWX3OK736IFD4F3PAXDR/action/author_attestation","sign_citation":"https://pith.science/pith/KVEJ77XWX3OK736IFD4F3PAXDR/action/citation_signature","submit_replication":"https://pith.science/pith/KVEJ77XWX3OK736IFD4F3PAXDR/action/replication_record"}},"created_at":"2026-07-05T09:29:13.728245+00:00","updated_at":"2026-07-05T09:29:13.728245+00:00"}