{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BZX4EVYMXJBIEYJUGZE2G6N22J","short_pith_number":"pith:BZX4EVYM","schema_version":"1.0","canonical_sha256":"0e6fc2570cba428261343649a379bad27f7648a8eddda400e2d980c2c26e4b3d","source":{"kind":"arxiv","id":"2410.16251","version":3},"attestation_state":"computed","paper":{"title":"Can Knowledge Editing Really Correct Hallucinations?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ali Payani, Baixiang Huang, Canyu Chen, Kai Shu, Xiongxiao Xu","submitted_at":"2024-10-21T17:55:54Z","abstract_excerpt":"Large Language Models (LLMs) suffer from hallucinations, referring to the non-factual information in generated content, despite their superior capacities across tasks. Meanwhile, knowledge editing has been developed as a new popular paradigm to correct erroneous factual knowledge encoded in LLMs with the advantage of avoiding retraining from scratch. However, a common issue of existing evaluation datasets for knowledge editing is that they do not ensure that LLMs actually generate hallucinated answers to the evaluation questions before editing. When LLMs are evaluated on such datasets after be"},"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":"2410.16251","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-21T17:55:54Z","cross_cats_sorted":[],"title_canon_sha256":"6970939579f40e9d140d789c5c18173b2fae9951dd8f483c1af88e5e416f0477","abstract_canon_sha256":"610c226c18e2a327f98471444ff7c96dbe36a5c07e5ac8a8b1b602077002dbdf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:52.734930Z","signature_b64":"h9nMUdIvD/MF8/N0qd01i9QkfSFCAI9vyacXo0CNrbpyGHT1kKsQNVXHdEEJBvDQPBfmTMqHFANE6SKthbCVDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e6fc2570cba428261343649a379bad27f7648a8eddda400e2d980c2c26e4b3d","last_reissued_at":"2026-07-05T10:22:52.734150Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:52.734150Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can Knowledge Editing Really Correct Hallucinations?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ali Payani, Baixiang Huang, Canyu Chen, Kai Shu, Xiongxiao Xu","submitted_at":"2024-10-21T17:55:54Z","abstract_excerpt":"Large Language Models (LLMs) suffer from hallucinations, referring to the non-factual information in generated content, despite their superior capacities across tasks. Meanwhile, knowledge editing has been developed as a new popular paradigm to correct erroneous factual knowledge encoded in LLMs with the advantage of avoiding retraining from scratch. However, a common issue of existing evaluation datasets for knowledge editing is that they do not ensure that LLMs actually generate hallucinated answers to the evaluation questions before editing. When LLMs are evaluated on such datasets after be"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16251","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/2410.16251/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":"2410.16251","created_at":"2026-07-05T10:22:52.734251+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.16251v3","created_at":"2026-07-05T10:22:52.734251+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16251","created_at":"2026-07-05T10:22:52.734251+00:00"},{"alias_kind":"pith_short_12","alias_value":"BZX4EVYMXJBI","created_at":"2026-07-05T10:22:52.734251+00:00"},{"alias_kind":"pith_short_16","alias_value":"BZX4EVYMXJBIEYJU","created_at":"2026-07-05T10:22:52.734251+00:00"},{"alias_kind":"pith_short_8","alias_value":"BZX4EVYM","created_at":"2026-07-05T10:22:52.734251+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.17057","citing_title":"Correct When Paired, Wrong When Split: Decoupling and Editing Modality-Specific Neurons in MLLMs","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2606.23276","citing_title":"Exposing the Illusion of Erasure in Knowledge Editing for LLMs","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26942","citing_title":"Neuro-Symbolic Verification of LLM Outputs for Data-Sensitive Domains (extended preprint)","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08284","citing_title":"Distributed Multi-Layer Editing for Rule-Level Knowledge in Large Language Models","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BZX4EVYMXJBIEYJUGZE2G6N22J","json":"https://pith.science/pith/BZX4EVYMXJBIEYJUGZE2G6N22J.json","graph_json":"https://pith.science/api/pith-number/BZX4EVYMXJBIEYJUGZE2G6N22J/graph.json","events_json":"https://pith.science/api/pith-number/BZX4EVYMXJBIEYJUGZE2G6N22J/events.json","paper":"https://pith.science/paper/BZX4EVYM"},"agent_actions":{"view_html":"https://pith.science/pith/BZX4EVYMXJBIEYJUGZE2G6N22J","download_json":"https://pith.science/pith/BZX4EVYMXJBIEYJUGZE2G6N22J.json","view_paper":"https://pith.science/paper/BZX4EVYM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.16251&json=true","fetch_graph":"https://pith.science/api/pith-number/BZX4EVYMXJBIEYJUGZE2G6N22J/graph.json","fetch_events":"https://pith.science/api/pith-number/BZX4EVYMXJBIEYJUGZE2G6N22J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BZX4EVYMXJBIEYJUGZE2G6N22J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BZX4EVYMXJBIEYJUGZE2G6N22J/action/storage_attestation","attest_author":"https://pith.science/pith/BZX4EVYMXJBIEYJUGZE2G6N22J/action/author_attestation","sign_citation":"https://pith.science/pith/BZX4EVYMXJBIEYJUGZE2G6N22J/action/citation_signature","submit_replication":"https://pith.science/pith/BZX4EVYMXJBIEYJUGZE2G6N22J/action/replication_record"}},"created_at":"2026-07-05T10:22:52.734251+00:00","updated_at":"2026-07-05T10:22:52.734251+00:00"}