{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4YVMUQOJ2TUA6NTZVZNRZGSDF4","short_pith_number":"pith:4YVMUQOJ","schema_version":"1.0","canonical_sha256":"e62aca41c9d4e80f3679ae5b1c9a432f37860202d455c80a5f428d4038ec94a3","source":{"kind":"arxiv","id":"2406.13415","version":1},"attestation_state":"computed","paper":{"title":"Factual Confidence of LLMs: on Reliability and Robustness of Current Estimators","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Laura Aina, Llu\\'is M\\`arquez, Mat\\'eo Mahaut, Momchil Hardalov, Paula Czarnowska, Thomas M\\\"uller","submitted_at":"2024-06-19T10:11:37Z","abstract_excerpt":"Large Language Models (LLMs) tend to be unreliable in the factuality of their answers. To address this problem, NLP researchers have proposed a range of techniques to estimate LLM's confidence over facts. However, due to the lack of a systematic comparison, it is not clear how the different methods compare to one another. To fill this gap, we present a survey and empirical comparison of estimators of factual confidence. We define an experimental framework allowing for fair comparison, covering both fact-verification and question answering. Our experiments across a series of LLMs indicate 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":"2406.13415","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-19T10:11:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1daeb8d720dd5cf9de5276dbd83ee7148d01c5f098773b3078e25a1b0e0d0182","abstract_canon_sha256":"9e7642bad223f7aab231a64a023ee0def6474ab56f4ff22ca89f49af43d843b3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:40:58.648096Z","signature_b64":"aQNXDeEwUiiCW4dPMKHtix7cyhPeI8Esksmx0cOhWbgZp9t2xpnQqYuJt17A5USPBWrKTF+ponEjuZsZH6+oCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e62aca41c9d4e80f3679ae5b1c9a432f37860202d455c80a5f428d4038ec94a3","last_reissued_at":"2026-07-05T09:40:58.647638Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:40:58.647638Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Factual Confidence of LLMs: on Reliability and Robustness of Current Estimators","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Laura Aina, Llu\\'is M\\`arquez, Mat\\'eo Mahaut, Momchil Hardalov, Paula Czarnowska, Thomas M\\\"uller","submitted_at":"2024-06-19T10:11:37Z","abstract_excerpt":"Large Language Models (LLMs) tend to be unreliable in the factuality of their answers. To address this problem, NLP researchers have proposed a range of techniques to estimate LLM's confidence over facts. However, due to the lack of a systematic comparison, it is not clear how the different methods compare to one another. To fill this gap, we present a survey and empirical comparison of estimators of factual confidence. We define an experimental framework allowing for fair comparison, covering both fact-verification and question answering. Our experiments across a series of LLMs indicate that "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.13415","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/2406.13415/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":"2406.13415","created_at":"2026-07-05T09:40:58.647694+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.13415v1","created_at":"2026-07-05T09:40:58.647694+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.13415","created_at":"2026-07-05T09:40:58.647694+00:00"},{"alias_kind":"pith_short_12","alias_value":"4YVMUQOJ2TUA","created_at":"2026-07-05T09:40:58.647694+00:00"},{"alias_kind":"pith_short_16","alias_value":"4YVMUQOJ2TUA6NTZ","created_at":"2026-07-05T09:40:58.647694+00:00"},{"alias_kind":"pith_short_8","alias_value":"4YVMUQOJ","created_at":"2026-07-05T09:40:58.647694+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01120","citing_title":"Diagnosing LLM Arbitration Behavior over Pre-evidence Epistemic States in RAG-based Fact-Checking","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30217","citing_title":"Before Thinking, Learn to Decide: Proactive Routing for Efficient Visual Reasoning","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4YVMUQOJ2TUA6NTZVZNRZGSDF4","json":"https://pith.science/pith/4YVMUQOJ2TUA6NTZVZNRZGSDF4.json","graph_json":"https://pith.science/api/pith-number/4YVMUQOJ2TUA6NTZVZNRZGSDF4/graph.json","events_json":"https://pith.science/api/pith-number/4YVMUQOJ2TUA6NTZVZNRZGSDF4/events.json","paper":"https://pith.science/paper/4YVMUQOJ"},"agent_actions":{"view_html":"https://pith.science/pith/4YVMUQOJ2TUA6NTZVZNRZGSDF4","download_json":"https://pith.science/pith/4YVMUQOJ2TUA6NTZVZNRZGSDF4.json","view_paper":"https://pith.science/paper/4YVMUQOJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.13415&json=true","fetch_graph":"https://pith.science/api/pith-number/4YVMUQOJ2TUA6NTZVZNRZGSDF4/graph.json","fetch_events":"https://pith.science/api/pith-number/4YVMUQOJ2TUA6NTZVZNRZGSDF4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4YVMUQOJ2TUA6NTZVZNRZGSDF4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4YVMUQOJ2TUA6NTZVZNRZGSDF4/action/storage_attestation","attest_author":"https://pith.science/pith/4YVMUQOJ2TUA6NTZVZNRZGSDF4/action/author_attestation","sign_citation":"https://pith.science/pith/4YVMUQOJ2TUA6NTZVZNRZGSDF4/action/citation_signature","submit_replication":"https://pith.science/pith/4YVMUQOJ2TUA6NTZVZNRZGSDF4/action/replication_record"}},"created_at":"2026-07-05T09:40:58.647694+00:00","updated_at":"2026-07-05T09:40:58.647694+00:00"}