{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CPSG5ZIQ5NW4BLMQKKKKC4CHQD","short_pith_number":"pith:CPSG5ZIQ","schema_version":"1.0","canonical_sha256":"13e46ee510eb6dc0ad905294a1704780df3fc5a777c24cf77e967f3798f27cda","source":{"kind":"arxiv","id":"2409.18786","version":1},"attestation_state":"computed","paper":{"title":"A Survey on the Honesty of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Cheng Yang, Chufan Shi, Deng Cai, Jie Zhou, Lemao Liu, Mo Yu, Ngai Wong, Siheng Li, Taiqiang Wu, Wai Lam, Xinyu Zhu, Xixin Wu, Yujiu Yang, Yuji Zhang, Zesen Cheng","submitted_at":"2024-09-27T14:34:54Z","abstract_excerpt":"Honesty is a fundamental principle for aligning large language models (LLMs) with human values, requiring these models to recognize what they know and don't know and be able to faithfully express their knowledge. Despite promising, current LLMs still exhibit significant dishonest behaviors, such as confidently presenting wrong answers or failing to express what they know. In addition, research on the honesty of LLMs also faces challenges, including varying definitions of honesty, difficulties in distinguishing between known and unknown knowledge, and a lack of comprehensive understanding of re"},"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":"2409.18786","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-27T14:34:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"935b057447e2e186078bb10b1de81f2a99497ce3a13f49b63b0bed2cdc1326e3","abstract_canon_sha256":"29f6f0ce8beb99f5aece7d8b83fa0636feacd009e3066620a4cdba2ecdf42cda"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:12:41.298235Z","signature_b64":"HJluSiAwQeXNQD6RbzYQP2Jmbhg4f5mltVgFq8Qzdr2BDDWPiRPwnFd+bUDNfRBPJl8lLEoWaKD/Fr12+OgRCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13e46ee510eb6dc0ad905294a1704780df3fc5a777c24cf77e967f3798f27cda","last_reissued_at":"2026-07-05T09:12:41.297819Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:12:41.297819Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey on the Honesty of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Cheng Yang, Chufan Shi, Deng Cai, Jie Zhou, Lemao Liu, Mo Yu, Ngai Wong, Siheng Li, Taiqiang Wu, Wai Lam, Xinyu Zhu, Xixin Wu, Yujiu Yang, Yuji Zhang, Zesen Cheng","submitted_at":"2024-09-27T14:34:54Z","abstract_excerpt":"Honesty is a fundamental principle for aligning large language models (LLMs) with human values, requiring these models to recognize what they know and don't know and be able to faithfully express their knowledge. Despite promising, current LLMs still exhibit significant dishonest behaviors, such as confidently presenting wrong answers or failing to express what they know. In addition, research on the honesty of LLMs also faces challenges, including varying definitions of honesty, difficulties in distinguishing between known and unknown knowledge, and a lack of comprehensive understanding of re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.18786","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/2409.18786/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":"2409.18786","created_at":"2026-07-05T09:12:41.297879+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.18786v1","created_at":"2026-07-05T09:12:41.297879+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.18786","created_at":"2026-07-05T09:12:41.297879+00:00"},{"alias_kind":"pith_short_12","alias_value":"CPSG5ZIQ5NW4","created_at":"2026-07-05T09:12:41.297879+00:00"},{"alias_kind":"pith_short_16","alias_value":"CPSG5ZIQ5NW4BLMQ","created_at":"2026-07-05T09:12:41.297879+00:00"},{"alias_kind":"pith_short_8","alias_value":"CPSG5ZIQ","created_at":"2026-07-05T09:12:41.297879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.11548","citing_title":"Copyright Protection for Large Language Models: A Survey of Methods, Challenges, and Trends","ref_index":88,"is_internal_anchor":false},{"citing_arxiv_id":"2510.22977","citing_title":"The Reasoning Trap: How Enhancing LLM Reasoning Amplifies Tool Hallucination","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2601.14004","citing_title":"Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models","ref_index":175,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09602","citing_title":"From Scalars to Tensors: Declared Losses Recover Epistemic Distinctions That Neutrosophic Scalars Cannot Express","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2603.27771","citing_title":"Emergent Social Intelligence Risks in Generative Multi-Agent Systems","ref_index":76,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CPSG5ZIQ5NW4BLMQKKKKC4CHQD","json":"https://pith.science/pith/CPSG5ZIQ5NW4BLMQKKKKC4CHQD.json","graph_json":"https://pith.science/api/pith-number/CPSG5ZIQ5NW4BLMQKKKKC4CHQD/graph.json","events_json":"https://pith.science/api/pith-number/CPSG5ZIQ5NW4BLMQKKKKC4CHQD/events.json","paper":"https://pith.science/paper/CPSG5ZIQ"},"agent_actions":{"view_html":"https://pith.science/pith/CPSG5ZIQ5NW4BLMQKKKKC4CHQD","download_json":"https://pith.science/pith/CPSG5ZIQ5NW4BLMQKKKKC4CHQD.json","view_paper":"https://pith.science/paper/CPSG5ZIQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.18786&json=true","fetch_graph":"https://pith.science/api/pith-number/CPSG5ZIQ5NW4BLMQKKKKC4CHQD/graph.json","fetch_events":"https://pith.science/api/pith-number/CPSG5ZIQ5NW4BLMQKKKKC4CHQD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CPSG5ZIQ5NW4BLMQKKKKC4CHQD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CPSG5ZIQ5NW4BLMQKKKKC4CHQD/action/storage_attestation","attest_author":"https://pith.science/pith/CPSG5ZIQ5NW4BLMQKKKKC4CHQD/action/author_attestation","sign_citation":"https://pith.science/pith/CPSG5ZIQ5NW4BLMQKKKKC4CHQD/action/citation_signature","submit_replication":"https://pith.science/pith/CPSG5ZIQ5NW4BLMQKKKKC4CHQD/action/replication_record"}},"created_at":"2026-07-05T09:12:41.297879+00:00","updated_at":"2026-07-05T09:12:41.297879+00:00"}