{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZRIZNLTIWAEUGUKRJRDUK35L7U","short_pith_number":"pith:ZRIZNLTI","schema_version":"1.0","canonical_sha256":"cc5196ae68b0094351514c47456fabfd2b339624deeaa0d800092929cdc4955f","source":{"kind":"arxiv","id":"2311.08401","version":1},"attestation_state":"computed","paper":{"title":"Fine-tuning Language Models for Factuality","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chelsea Finn, Christopher D. Manning, Eric Mitchell, Huaxiu Yao, Katherine Tian","submitted_at":"2023-11-14T18:59:15Z","abstract_excerpt":"The fluency and creativity of large pre-trained language models (LLMs) have led to their widespread use, sometimes even as a replacement for traditional search engines. Yet language models are prone to making convincing but factually inaccurate claims, often referred to as 'hallucinations.' These errors can inadvertently spread misinformation or harmfully perpetuate misconceptions. Further, manual fact-checking of model responses is a time-consuming process, making human factuality labels expensive to acquire. In this work, we fine-tune language models to be more factual, without human labelin"},"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":"2311.08401","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-14T18:59:15Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"4ebf28d87c99ee6af0762ac0e87df61db3728fe8d1c6ee530be666b70fe7c1ee","abstract_canon_sha256":"cabdae30029fe43b429f212008daccf6b5a86d4ccb219d81188a8e67e0c03264"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:12:44.626601Z","signature_b64":"xvRflmp8f1ggYKW2aBXm4JmSPHNLgbOzevnCOTggcOQamO9G8PK6eN/hUznCod+e57jPJEfI2TSUxLhPDCjDAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc5196ae68b0094351514c47456fabfd2b339624deeaa0d800092929cdc4955f","last_reissued_at":"2026-07-05T07:12:44.626115Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:12:44.626115Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fine-tuning Language Models for Factuality","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chelsea Finn, Christopher D. Manning, Eric Mitchell, Huaxiu Yao, Katherine Tian","submitted_at":"2023-11-14T18:59:15Z","abstract_excerpt":"The fluency and creativity of large pre-trained language models (LLMs) have led to their widespread use, sometimes even as a replacement for traditional search engines. Yet language models are prone to making convincing but factually inaccurate claims, often referred to as 'hallucinations.' These errors can inadvertently spread misinformation or harmfully perpetuate misconceptions. Further, manual fact-checking of model responses is a time-consuming process, making human factuality labels expensive to acquire. In this work, we fine-tune language models to be more factual, without human labelin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.08401","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/2311.08401/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":"2311.08401","created_at":"2026-07-05T07:12:44.626177+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.08401v1","created_at":"2026-07-05T07:12:44.626177+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.08401","created_at":"2026-07-05T07:12:44.626177+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZRIZNLTIWAEU","created_at":"2026-07-05T07:12:44.626177+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZRIZNLTIWAEUGUKR","created_at":"2026-07-05T07:12:44.626177+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZRIZNLTI","created_at":"2026-07-05T07:12:44.626177+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.15300","citing_title":"Deep Pre-Alignment for VLMs","ref_index":101,"is_internal_anchor":false},{"citing_arxiv_id":"2403.07691","citing_title":"ORPO: Monolithic Preference Optimization without Reference Model","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12813","citing_title":"REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations","ref_index":174,"is_internal_anchor":false},{"citing_arxiv_id":"2402.01306","citing_title":"KTO: Model Alignment as Prospect Theoretic Optimization","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZRIZNLTIWAEUGUKRJRDUK35L7U","json":"https://pith.science/pith/ZRIZNLTIWAEUGUKRJRDUK35L7U.json","graph_json":"https://pith.science/api/pith-number/ZRIZNLTIWAEUGUKRJRDUK35L7U/graph.json","events_json":"https://pith.science/api/pith-number/ZRIZNLTIWAEUGUKRJRDUK35L7U/events.json","paper":"https://pith.science/paper/ZRIZNLTI"},"agent_actions":{"view_html":"https://pith.science/pith/ZRIZNLTIWAEUGUKRJRDUK35L7U","download_json":"https://pith.science/pith/ZRIZNLTIWAEUGUKRJRDUK35L7U.json","view_paper":"https://pith.science/paper/ZRIZNLTI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.08401&json=true","fetch_graph":"https://pith.science/api/pith-number/ZRIZNLTIWAEUGUKRJRDUK35L7U/graph.json","fetch_events":"https://pith.science/api/pith-number/ZRIZNLTIWAEUGUKRJRDUK35L7U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZRIZNLTIWAEUGUKRJRDUK35L7U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZRIZNLTIWAEUGUKRJRDUK35L7U/action/storage_attestation","attest_author":"https://pith.science/pith/ZRIZNLTIWAEUGUKRJRDUK35L7U/action/author_attestation","sign_citation":"https://pith.science/pith/ZRIZNLTIWAEUGUKRJRDUK35L7U/action/citation_signature","submit_replication":"https://pith.science/pith/ZRIZNLTIWAEUGUKRJRDUK35L7U/action/replication_record"}},"created_at":"2026-07-05T07:12:44.626177+00:00","updated_at":"2026-07-05T07:12:44.626177+00:00"}