{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6S3TCC342TGFJ7S2NXGWDNDDOI","short_pith_number":"pith:6S3TCC34","schema_version":"1.0","canonical_sha256":"f4b7310b7cd4cc54fe5a6dcd61b4637223a15ee2edfad7dd6f998b3cd8429176","source":{"kind":"arxiv","id":"2507.20930","version":2},"attestation_state":"computed","paper":{"title":"FRED: Financial Retrieval-Enhanced Detection and Editing of Hallucinations in Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Kevin Wu, Kuan-Wei Huang, Likun Tan","submitted_at":"2025-07-28T15:41:53Z","abstract_excerpt":"Hallucinations in large language models pose a critical challenge for applications requiring factual reliability, particularly in high-stakes domains such as finance. This work presents an effective approach for detecting and editing factually incorrect content in model-generated responses based on the provided context. Given a user-defined domain-specific error taxonomy, we construct a synthetic dataset by inserting tagged errors into financial question-answering corpora and then fine-tune four language models, Phi-4, Phi-4-mini, Qwen3-4B, and Qwen3-14B, to detect and edit these factual inacc"},"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":"2507.20930","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-28T15:41:53Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"a332d98a5f3fcb74537e583b43dc93a45920aeca314cc0dab4fcbbac7f8e481e","abstract_canon_sha256":"655436ad7bc7dcbab0eaf66b8c0b928b1fcd066cae2532e92ac2277f8c3ac0f8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:45:38.554433Z","signature_b64":"vCBIRLt3wQh7NQfMAyzMspN8Ei91sB3HX2fHlqvzfs0WqFJHAHQ+egl1Jk+KWBXC1dUd6FetUVXwSng/JINUAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f4b7310b7cd4cc54fe5a6dcd61b4637223a15ee2edfad7dd6f998b3cd8429176","last_reissued_at":"2026-07-05T11:45:38.553872Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:45:38.553872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FRED: Financial Retrieval-Enhanced Detection and Editing of Hallucinations in Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Kevin Wu, Kuan-Wei Huang, Likun Tan","submitted_at":"2025-07-28T15:41:53Z","abstract_excerpt":"Hallucinations in large language models pose a critical challenge for applications requiring factual reliability, particularly in high-stakes domains such as finance. This work presents an effective approach for detecting and editing factually incorrect content in model-generated responses based on the provided context. Given a user-defined domain-specific error taxonomy, we construct a synthetic dataset by inserting tagged errors into financial question-answering corpora and then fine-tune four language models, Phi-4, Phi-4-mini, Qwen3-4B, and Qwen3-14B, to detect and edit these factual inacc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.20930","kind":"arxiv","version":2},"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/2507.20930/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":"2507.20930","created_at":"2026-07-05T11:45:38.553946+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.20930v2","created_at":"2026-07-05T11:45:38.553946+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.20930","created_at":"2026-07-05T11:45:38.553946+00:00"},{"alias_kind":"pith_short_12","alias_value":"6S3TCC342TGF","created_at":"2026-07-05T11:45:38.553946+00:00"},{"alias_kind":"pith_short_16","alias_value":"6S3TCC342TGFJ7S2","created_at":"2026-07-05T11:45:38.553946+00:00"},{"alias_kind":"pith_short_8","alias_value":"6S3TCC34","created_at":"2026-07-05T11:45:38.553946+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6S3TCC342TGFJ7S2NXGWDNDDOI","json":"https://pith.science/pith/6S3TCC342TGFJ7S2NXGWDNDDOI.json","graph_json":"https://pith.science/api/pith-number/6S3TCC342TGFJ7S2NXGWDNDDOI/graph.json","events_json":"https://pith.science/api/pith-number/6S3TCC342TGFJ7S2NXGWDNDDOI/events.json","paper":"https://pith.science/paper/6S3TCC34"},"agent_actions":{"view_html":"https://pith.science/pith/6S3TCC342TGFJ7S2NXGWDNDDOI","download_json":"https://pith.science/pith/6S3TCC342TGFJ7S2NXGWDNDDOI.json","view_paper":"https://pith.science/paper/6S3TCC34","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.20930&json=true","fetch_graph":"https://pith.science/api/pith-number/6S3TCC342TGFJ7S2NXGWDNDDOI/graph.json","fetch_events":"https://pith.science/api/pith-number/6S3TCC342TGFJ7S2NXGWDNDDOI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6S3TCC342TGFJ7S2NXGWDNDDOI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6S3TCC342TGFJ7S2NXGWDNDDOI/action/storage_attestation","attest_author":"https://pith.science/pith/6S3TCC342TGFJ7S2NXGWDNDDOI/action/author_attestation","sign_citation":"https://pith.science/pith/6S3TCC342TGFJ7S2NXGWDNDDOI/action/citation_signature","submit_replication":"https://pith.science/pith/6S3TCC342TGFJ7S2NXGWDNDDOI/action/replication_record"}},"created_at":"2026-07-05T11:45:38.553946+00:00","updated_at":"2026-07-05T11:45:38.553946+00:00"}