{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:J6BH6UAYYB2NKGED3J4CH4OIS7","short_pith_number":"pith:J6BH6UAY","schema_version":"1.0","canonical_sha256":"4f827f5018c074d51883da7823f1c897e0ec355b5e5b4b3f283d16c8304407a7","source":{"kind":"arxiv","id":"2410.23526","version":1},"attestation_state":"computed","paper":{"title":"LEAF: Learning and Evaluation Augmented by Fact-Checking to Improve Factualness in Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hieu Tran, Junda Wang, Terrence Chen, Weijing Huang, Yujan Ting","submitted_at":"2024-10-31T00:18:05Z","abstract_excerpt":"Large language models (LLMs) have shown remarkable capabilities in various natural language processing tasks, yet they often struggle with maintaining factual accuracy, particularly in knowledge-intensive domains like healthcare. This study introduces LEAF: Learning and Evaluation Augmented by Fact-Checking, a novel approach designed to enhance the factual reliability of LLMs, with a focus on medical question answering (QA). LEAF utilizes a dual strategy to enhance the factual accuracy of responses from models such as Llama 3 70B Instruct and Llama 3 8B Instruct. The first strategy, Fact-Check"},"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":"2410.23526","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-31T00:18:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a01fa8a99817eb38684468df83728cbecbbfdd60fc7d61b39249dc4d808fc141","abstract_canon_sha256":"d47ebbb7fa67a00b1c3693b68a6562c610935ca6353c2f567a5300d1e4f49cc0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:29:01.579641Z","signature_b64":"rNspmmLXLlTPoj/dSiZG51YFLHATf1+hkf7rMietztvxmmzZYeKdMsDyoAoDLa16Jv+WAFknv7YDZ7U5bZDIDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f827f5018c074d51883da7823f1c897e0ec355b5e5b4b3f283d16c8304407a7","last_reissued_at":"2026-07-05T09:29:01.579105Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:29:01.579105Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LEAF: Learning and Evaluation Augmented by Fact-Checking to Improve Factualness in Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hieu Tran, Junda Wang, Terrence Chen, Weijing Huang, Yujan Ting","submitted_at":"2024-10-31T00:18:05Z","abstract_excerpt":"Large language models (LLMs) have shown remarkable capabilities in various natural language processing tasks, yet they often struggle with maintaining factual accuracy, particularly in knowledge-intensive domains like healthcare. This study introduces LEAF: Learning and Evaluation Augmented by Fact-Checking, a novel approach designed to enhance the factual reliability of LLMs, with a focus on medical question answering (QA). LEAF utilizes a dual strategy to enhance the factual accuracy of responses from models such as Llama 3 70B Instruct and Llama 3 8B Instruct. The first strategy, Fact-Check"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.23526","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/2410.23526/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":"2410.23526","created_at":"2026-07-05T09:29:01.579161+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.23526v1","created_at":"2026-07-05T09:29:01.579161+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.23526","created_at":"2026-07-05T09:29:01.579161+00:00"},{"alias_kind":"pith_short_12","alias_value":"J6BH6UAYYB2N","created_at":"2026-07-05T09:29:01.579161+00:00"},{"alias_kind":"pith_short_16","alias_value":"J6BH6UAYYB2NKGED","created_at":"2026-07-05T09:29:01.579161+00:00"},{"alias_kind":"pith_short_8","alias_value":"J6BH6UAY","created_at":"2026-07-05T09:29:01.579161+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.21024","citing_title":"An Agile Method for Implementing Retrieval Augmented Generation Tools in Industrial SMEs","ref_index":80,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J6BH6UAYYB2NKGED3J4CH4OIS7","json":"https://pith.science/pith/J6BH6UAYYB2NKGED3J4CH4OIS7.json","graph_json":"https://pith.science/api/pith-number/J6BH6UAYYB2NKGED3J4CH4OIS7/graph.json","events_json":"https://pith.science/api/pith-number/J6BH6UAYYB2NKGED3J4CH4OIS7/events.json","paper":"https://pith.science/paper/J6BH6UAY"},"agent_actions":{"view_html":"https://pith.science/pith/J6BH6UAYYB2NKGED3J4CH4OIS7","download_json":"https://pith.science/pith/J6BH6UAYYB2NKGED3J4CH4OIS7.json","view_paper":"https://pith.science/paper/J6BH6UAY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.23526&json=true","fetch_graph":"https://pith.science/api/pith-number/J6BH6UAYYB2NKGED3J4CH4OIS7/graph.json","fetch_events":"https://pith.science/api/pith-number/J6BH6UAYYB2NKGED3J4CH4OIS7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J6BH6UAYYB2NKGED3J4CH4OIS7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J6BH6UAYYB2NKGED3J4CH4OIS7/action/storage_attestation","attest_author":"https://pith.science/pith/J6BH6UAYYB2NKGED3J4CH4OIS7/action/author_attestation","sign_citation":"https://pith.science/pith/J6BH6UAYYB2NKGED3J4CH4OIS7/action/citation_signature","submit_replication":"https://pith.science/pith/J6BH6UAYYB2NKGED3J4CH4OIS7/action/replication_record"}},"created_at":"2026-07-05T09:29:01.579161+00:00","updated_at":"2026-07-05T09:29:01.579161+00:00"}