{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WK4DVKWCUS4IULLVTOVKVJJ2SM","short_pith_number":"pith:WK4DVKWC","schema_version":"1.0","canonical_sha256":"b2b83aaac2a4b88a2d759baaaaa53a932053bc3b8d49ef911c67e67eb4780c42","source":{"kind":"arxiv","id":"2402.02420","version":3},"attestation_state":"computed","paper":{"title":"Factuality of Large Language Models: A Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Fei Liu, Georgi Georgiev, Minghan Wang, Muhammad Arslan Manzoor, Preslav Nakov, Rocktim Jyoti Das, Yuxia Wang","submitted_at":"2024-02-04T09:36:31Z","abstract_excerpt":"Large language models (LLMs), especially when instruction-tuned for chat, have become part of our daily lives, freeing people from the process of searching, extracting, and integrating information from multiple sources by offering a straightforward answer to a variety of questions in a single place. Unfortunately, in many cases, LLM responses are factually incorrect, which limits their applicability in real-world scenarios. As a result, research on evaluating and improving the factuality of LLMs has attracted a lot of attention recently. In this survey, we critically analyze existing work with"},"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":"2402.02420","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-04T09:36:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f18fa7f91d7777d5bffd290b06a240980ae954b1ccf4dbf1eef5e9e0549995e4","abstract_canon_sha256":"4f4855f09c973ccd30b10af55aa88599f3a71e93ee7351e80d191bb537a73431"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:47.490959Z","signature_b64":"fmvBgcrOO5wDC9RqfcDELeYmSum36uO0GZBlgKuS2p4qVg+wFZvga6I8KnTe9U+HIFZy4T5nWCkHh9LvOkHJBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2b83aaac2a4b88a2d759baaaaa53a932053bc3b8d49ef911c67e67eb4780c42","last_reissued_at":"2026-07-05T09:28:47.490369Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:47.490369Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Factuality of Large Language Models: A Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Fei Liu, Georgi Georgiev, Minghan Wang, Muhammad Arslan Manzoor, Preslav Nakov, Rocktim Jyoti Das, Yuxia Wang","submitted_at":"2024-02-04T09:36:31Z","abstract_excerpt":"Large language models (LLMs), especially when instruction-tuned for chat, have become part of our daily lives, freeing people from the process of searching, extracting, and integrating information from multiple sources by offering a straightforward answer to a variety of questions in a single place. Unfortunately, in many cases, LLM responses are factually incorrect, which limits their applicability in real-world scenarios. As a result, research on evaluating and improving the factuality of LLMs has attracted a lot of attention recently. In this survey, we critically analyze existing work with"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.02420","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/2402.02420/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":"2402.02420","created_at":"2026-07-05T09:28:47.490440+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.02420v3","created_at":"2026-07-05T09:28:47.490440+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.02420","created_at":"2026-07-05T09:28:47.490440+00:00"},{"alias_kind":"pith_short_12","alias_value":"WK4DVKWCUS4I","created_at":"2026-07-05T09:28:47.490440+00:00"},{"alias_kind":"pith_short_16","alias_value":"WK4DVKWCUS4IULLV","created_at":"2026-07-05T09:28:47.490440+00:00"},{"alias_kind":"pith_short_8","alias_value":"WK4DVKWC","created_at":"2026-07-05T09:28:47.490440+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07936","citing_title":"Illusions of the Gold Standard: A Large-scale Analysis of Human Evaluation Protocols for Long-form Text Generation","ref_index":103,"is_internal_anchor":false},{"citing_arxiv_id":"2603.11689","citing_title":"Explicit Logic Channel for Validation and Enhancement of MLLMs on Zero-Shot Tasks","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2510.02001","citing_title":"Generating Findings for Jaw Cysts in Dental Panoramic Radiographs Using a GPT-Based VLM: A Preliminary Study on Building a Two-Stage Self-Correction Loop with Structured Output (SLSO) Framework","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WK4DVKWCUS4IULLVTOVKVJJ2SM","json":"https://pith.science/pith/WK4DVKWCUS4IULLVTOVKVJJ2SM.json","graph_json":"https://pith.science/api/pith-number/WK4DVKWCUS4IULLVTOVKVJJ2SM/graph.json","events_json":"https://pith.science/api/pith-number/WK4DVKWCUS4IULLVTOVKVJJ2SM/events.json","paper":"https://pith.science/paper/WK4DVKWC"},"agent_actions":{"view_html":"https://pith.science/pith/WK4DVKWCUS4IULLVTOVKVJJ2SM","download_json":"https://pith.science/pith/WK4DVKWCUS4IULLVTOVKVJJ2SM.json","view_paper":"https://pith.science/paper/WK4DVKWC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.02420&json=true","fetch_graph":"https://pith.science/api/pith-number/WK4DVKWCUS4IULLVTOVKVJJ2SM/graph.json","fetch_events":"https://pith.science/api/pith-number/WK4DVKWCUS4IULLVTOVKVJJ2SM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WK4DVKWCUS4IULLVTOVKVJJ2SM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WK4DVKWCUS4IULLVTOVKVJJ2SM/action/storage_attestation","attest_author":"https://pith.science/pith/WK4DVKWCUS4IULLVTOVKVJJ2SM/action/author_attestation","sign_citation":"https://pith.science/pith/WK4DVKWCUS4IULLVTOVKVJJ2SM/action/citation_signature","submit_replication":"https://pith.science/pith/WK4DVKWCUS4IULLVTOVKVJJ2SM/action/replication_record"}},"created_at":"2026-07-05T09:28:47.490440+00:00","updated_at":"2026-07-05T09:28:47.490440+00:00"}