{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:H4ETT5KAUZMM2JMXXIQCESLTLF","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d8b61cf0c3daad76c6196c8b99dced1b64357353502d15c183af04c1bcaa4205","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-12T12:01:32Z","title_canon_sha256":"af7febd1a195b6bdeae51a79a6710320f143e87e6eaf99e89bdb7310fa888e03"},"schema_version":"1.0","source":{"id":"2310.08256","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.08256","created_at":"2026-07-05T07:00:13Z"},{"alias_kind":"arxiv_version","alias_value":"2310.08256v1","created_at":"2026-07-05T07:00:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.08256","created_at":"2026-07-05T07:00:13Z"},{"alias_kind":"pith_short_12","alias_value":"H4ETT5KAUZMM","created_at":"2026-07-05T07:00:13Z"},{"alias_kind":"pith_short_16","alias_value":"H4ETT5KAUZMM2JMX","created_at":"2026-07-05T07:00:13Z"},{"alias_kind":"pith_short_8","alias_value":"H4ETT5KA","created_at":"2026-07-05T07:00:13Z"}],"graph_snapshots":[{"event_id":"sha256:b20fccaf55dc6616b2553a4c8e58fcf9b35f638ac92d82e273f398397ce40b6b","target":"graph","created_at":"2026-07-05T07:00:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2310.08256/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) often make factually incorrect responses despite their success in various applications. In this paper, we hypothesize that relying heavily on simple co-occurrence statistics of the pre-training corpora is one of the main factors that cause factual errors. Our results reveal that LLMs are vulnerable to the co-occurrence bias, defined as preferring frequently co-occurred words over the correct answer. Consequently, LLMs struggle to recall facts whose subject and object rarely co-occur in the pre-training dataset although they are seen during finetuning. We show that ","authors_text":"Cheongwoong Kang, Jaesik Choi","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-12T12:01:32Z","title":"Impact of Co-occurrence on Factual Knowledge of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.08256","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:9466a6937044206d65bcba2d8e74ad1d42dad9c7b8e900dbe0493428f9026323","target":"record","created_at":"2026-07-05T07:00:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"d8b61cf0c3daad76c6196c8b99dced1b64357353502d15c183af04c1bcaa4205","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-12T12:01:32Z","title_canon_sha256":"af7febd1a195b6bdeae51a79a6710320f143e87e6eaf99e89bdb7310fa888e03"},"schema_version":"1.0","source":{"id":"2310.08256","kind":"arxiv","version":1}},"canonical_sha256":"3f0939f540a658cd2597ba20224973597a5a4c63923559a3433d81d8a16801a9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3f0939f540a658cd2597ba20224973597a5a4c63923559a3433d81d8a16801a9","first_computed_at":"2026-07-05T07:00:13.044867Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:00:13.044867Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9bYTi6LhIqCE58tbvoJdYtCFg2PHqnAxuTlZ8Y0RECmMof1JZKT86wGG0uI1MFRTLyirad9sHI3vlPVdkIzTBg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:00:13.045272Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.08256","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9466a6937044206d65bcba2d8e74ad1d42dad9c7b8e900dbe0493428f9026323","sha256:b20fccaf55dc6616b2553a4c8e58fcf9b35f638ac92d82e273f398397ce40b6b"],"state_sha256":"7c2f91f2c54f1d04cc4777bbbde76ac96c4e3917d444f4ca8248d86bb7bc48dc"}