{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QOG4AHPBSLOEBV4TTDCILBX3H4","short_pith_number":"pith:QOG4AHPB","schema_version":"1.0","canonical_sha256":"838dc01de192dc40d79398c48586fb3f28c2e9c39a3505e5d672be59dad6a22f","source":{"kind":"arxiv","id":"2405.14654","version":1},"attestation_state":"computed","paper":{"title":"Efficient Medical Question Answering with Knowledge-Augmented Question Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alaedine Bennani, Corentin Dancette, Elodie Ferreres, Julien Khlaut, Paul H\\'erent, Pierre Manceron","submitted_at":"2024-05-23T14:53:52Z","abstract_excerpt":"In the expanding field of language model applications, medical knowledge representation remains a significant challenge due to the specialized nature of the domain. Large language models, such as GPT-4, obtain reasonable scores on medical question answering tasks, but smaller models are far behind. In this work, we introduce a method to improve the proficiency of a small language model in the medical domain by employing a two-fold approach. We first fine-tune the model on a corpus of medical textbooks. Then, we use GPT-4 to generate questions similar to the downstream task, prompted with textb"},"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":"2405.14654","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-23T14:53:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b5d5fc7190e8b054caa85a9a35e513a5bcc2c1c21ff6f3d49ef5ccdcf6b971be","abstract_canon_sha256":"57b534c0c854f2ff84fac1d5c0f173e31fe329de38dcb989fb7c6c4377eca1c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:22:26.285710Z","signature_b64":"wslX1v6IvZiKqd298QUQbbsJcxVnBvRS5XWy94cgqynD8OcoI3yphOETJRsBZQOav2wjUzQgqnYz0QLmbQGEAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"838dc01de192dc40d79398c48586fb3f28c2e9c39a3505e5d672be59dad6a22f","last_reissued_at":"2026-07-05T08:22:26.285304Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:22:26.285304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Medical Question Answering with Knowledge-Augmented Question Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alaedine Bennani, Corentin Dancette, Elodie Ferreres, Julien Khlaut, Paul H\\'erent, Pierre Manceron","submitted_at":"2024-05-23T14:53:52Z","abstract_excerpt":"In the expanding field of language model applications, medical knowledge representation remains a significant challenge due to the specialized nature of the domain. Large language models, such as GPT-4, obtain reasonable scores on medical question answering tasks, but smaller models are far behind. In this work, we introduce a method to improve the proficiency of a small language model in the medical domain by employing a two-fold approach. We first fine-tune the model on a corpus of medical textbooks. Then, we use GPT-4 to generate questions similar to the downstream task, prompted with textb"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.14654","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/2405.14654/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":"2405.14654","created_at":"2026-07-05T08:22:26.285373+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.14654v1","created_at":"2026-07-05T08:22:26.285373+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.14654","created_at":"2026-07-05T08:22:26.285373+00:00"},{"alias_kind":"pith_short_12","alias_value":"QOG4AHPBSLOE","created_at":"2026-07-05T08:22:26.285373+00:00"},{"alias_kind":"pith_short_16","alias_value":"QOG4AHPBSLOEBV4T","created_at":"2026-07-05T08:22:26.285373+00:00"},{"alias_kind":"pith_short_8","alias_value":"QOG4AHPB","created_at":"2026-07-05T08:22:26.285373+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.04666","citing_title":"Enhancing Health Information Retrieval with RAG by Prioritizing Topical Relevance and Factual Accuracy","ref_index":62,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QOG4AHPBSLOEBV4TTDCILBX3H4","json":"https://pith.science/pith/QOG4AHPBSLOEBV4TTDCILBX3H4.json","graph_json":"https://pith.science/api/pith-number/QOG4AHPBSLOEBV4TTDCILBX3H4/graph.json","events_json":"https://pith.science/api/pith-number/QOG4AHPBSLOEBV4TTDCILBX3H4/events.json","paper":"https://pith.science/paper/QOG4AHPB"},"agent_actions":{"view_html":"https://pith.science/pith/QOG4AHPBSLOEBV4TTDCILBX3H4","download_json":"https://pith.science/pith/QOG4AHPBSLOEBV4TTDCILBX3H4.json","view_paper":"https://pith.science/paper/QOG4AHPB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.14654&json=true","fetch_graph":"https://pith.science/api/pith-number/QOG4AHPBSLOEBV4TTDCILBX3H4/graph.json","fetch_events":"https://pith.science/api/pith-number/QOG4AHPBSLOEBV4TTDCILBX3H4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QOG4AHPBSLOEBV4TTDCILBX3H4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QOG4AHPBSLOEBV4TTDCILBX3H4/action/storage_attestation","attest_author":"https://pith.science/pith/QOG4AHPBSLOEBV4TTDCILBX3H4/action/author_attestation","sign_citation":"https://pith.science/pith/QOG4AHPBSLOEBV4TTDCILBX3H4/action/citation_signature","submit_replication":"https://pith.science/pith/QOG4AHPBSLOEBV4TTDCILBX3H4/action/replication_record"}},"created_at":"2026-07-05T08:22:26.285373+00:00","updated_at":"2026-07-05T08:22:26.285373+00:00"}