{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:F4MVOAHGT4JHHUTTWNKLYQA4KB","short_pith_number":"pith:F4MVOAHG","schema_version":"1.0","canonical_sha256":"2f195700e69f1273d273b354bc401c5073046051fc5da63fddf4633424005874","source":{"kind":"arxiv","id":"2310.07521","version":3},"attestation_state":"computed","paper":{"title":"Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cheng Jiayang, Cunxiang Wang, Jindong Wang, Linyi Yang, Tianhang Zhang, Wenyang Gao, Xiangru Tang, Xiaoze Liu, Xing Xie, Xuming Hu, Yidong Wang, Yuanhao Yue, Yue Zhang, Yunzhi Yao, Zehan Qi, Zheng Zhang","submitted_at":"2023-10-11T14:18:03Z","abstract_excerpt":"This survey addresses the crucial issue of factuality in Large Language Models (LLMs). As LLMs find applications across diverse domains, the reliability and accuracy of their outputs become vital. We define the Factuality Issue as the probability of LLMs to produce content inconsistent with established facts. We first delve into the implications of these inaccuracies, highlighting the potential consequences and challenges posed by factual errors in LLM outputs. Subsequently, we analyze the mechanisms through which LLMs store and process facts, seeking the primary causes of factual errors. Our "},"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":"2310.07521","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-11T14:18:03Z","cross_cats_sorted":[],"title_canon_sha256":"c182790b730e3081c83a8c58909f333be9d735f86dd9e4edbb16fae008a3b42f","abstract_canon_sha256":"da4e6d9bef2cb6ef03f20936b518e0f02078c171f9021ac8caa58b0bc23923b3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:24:55.446983Z","signature_b64":"AIjfX588ezQJjpxfwon3eWWwdlfew4ltmrSXWkbZ+BXxpoOyukmRnPT+VYDqj9hkVicJYI+XXx7PHddkr5FLBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f195700e69f1273d273b354bc401c5073046051fc5da63fddf4633424005874","last_reissued_at":"2026-07-05T07:24:55.446454Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:24:55.446454Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cheng Jiayang, Cunxiang Wang, Jindong Wang, Linyi Yang, Tianhang Zhang, Wenyang Gao, Xiangru Tang, Xiaoze Liu, Xing Xie, Xuming Hu, Yidong Wang, Yuanhao Yue, Yue Zhang, Yunzhi Yao, Zehan Qi, Zheng Zhang","submitted_at":"2023-10-11T14:18:03Z","abstract_excerpt":"This survey addresses the crucial issue of factuality in Large Language Models (LLMs). As LLMs find applications across diverse domains, the reliability and accuracy of their outputs become vital. We define the Factuality Issue as the probability of LLMs to produce content inconsistent with established facts. We first delve into the implications of these inaccuracies, highlighting the potential consequences and challenges posed by factual errors in LLM outputs. Subsequently, we analyze the mechanisms through which LLMs store and process facts, seeking the primary causes of factual errors. Our "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.07521","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/2310.07521/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":"2310.07521","created_at":"2026-07-05T07:24:55.446515+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.07521v3","created_at":"2026-07-05T07:24:55.446515+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.07521","created_at":"2026-07-05T07:24:55.446515+00:00"},{"alias_kind":"pith_short_12","alias_value":"F4MVOAHGT4JH","created_at":"2026-07-05T07:24:55.446515+00:00"},{"alias_kind":"pith_short_16","alias_value":"F4MVOAHGT4JHHUTT","created_at":"2026-07-05T07:24:55.446515+00:00"},{"alias_kind":"pith_short_8","alias_value":"F4MVOAHG","created_at":"2026-07-05T07:24:55.446515+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":14,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21595","citing_title":"Per-Entity Bias Mapping for AI Visibility: Why Brand Mentions Require Entity-Specific Calibration","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03713","citing_title":"Investigating Adversarial Robustness of Multi-modal Large Language Models","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30814","citing_title":"When Calibration Rankings Reverse: Accuracy-Controlled Evaluation for Fair Comparison of LLMs","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28120","citing_title":"LegalGraphRAG: Multi-Agent Graph Retrieval-Augmented Generation for Reliable Legal Reasoning","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2407.20240","citing_title":"Social and Ethical Risks Posed by General-Purpose LLMs for Settling Newcomers in Canada","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2502.02871","citing_title":"Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning","ref_index":187,"is_internal_anchor":false},{"citing_arxiv_id":"2506.17585","citing_title":"Cite Pretrain: Retrieval-Free Knowledge Attribution for Large Language Models","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2509.05219","citing_title":"Conversational AI increases political knowledge as effectively as self-directed internet search","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16313","citing_title":"MARA: A Multimodal Adaptive Retrieval-Augmented Framework for Document Question Answering","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2401.11817","citing_title":"Hallucination is Inevitable: An Innate Limitation of Large Language Models","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2603.29908","citing_title":"C-TRAIL: A Commonsense World Framework for Trajectory Planning in Autonomous Driving","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10640","citing_title":"Towards Understanding Continual Factual Knowledge Acquisition of Language Models: From Theory to Algorithm","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01123","citing_title":"PERSA: Reinforcement Learning for Professor-Style Personalized Feedback with LLMs","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19589","citing_title":"TeamFusion: Supporting Open-ended Teamwork with Multi-Agent Systems","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F4MVOAHGT4JHHUTTWNKLYQA4KB","json":"https://pith.science/pith/F4MVOAHGT4JHHUTTWNKLYQA4KB.json","graph_json":"https://pith.science/api/pith-number/F4MVOAHGT4JHHUTTWNKLYQA4KB/graph.json","events_json":"https://pith.science/api/pith-number/F4MVOAHGT4JHHUTTWNKLYQA4KB/events.json","paper":"https://pith.science/paper/F4MVOAHG"},"agent_actions":{"view_html":"https://pith.science/pith/F4MVOAHGT4JHHUTTWNKLYQA4KB","download_json":"https://pith.science/pith/F4MVOAHGT4JHHUTTWNKLYQA4KB.json","view_paper":"https://pith.science/paper/F4MVOAHG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.07521&json=true","fetch_graph":"https://pith.science/api/pith-number/F4MVOAHGT4JHHUTTWNKLYQA4KB/graph.json","fetch_events":"https://pith.science/api/pith-number/F4MVOAHGT4JHHUTTWNKLYQA4KB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F4MVOAHGT4JHHUTTWNKLYQA4KB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F4MVOAHGT4JHHUTTWNKLYQA4KB/action/storage_attestation","attest_author":"https://pith.science/pith/F4MVOAHGT4JHHUTTWNKLYQA4KB/action/author_attestation","sign_citation":"https://pith.science/pith/F4MVOAHGT4JHHUTTWNKLYQA4KB/action/citation_signature","submit_replication":"https://pith.science/pith/F4MVOAHGT4JHHUTTWNKLYQA4KB/action/replication_record"}},"created_at":"2026-07-05T07:24:55.446515+00:00","updated_at":"2026-07-05T07:24:55.446515+00:00"}