{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UXNN4SW7C7PBM5HJR33P4MSWGJ","short_pith_number":"pith:UXNN4SW7","schema_version":"1.0","canonical_sha256":"a5dade4adf17de1674e98ef6fe32563261b7c4ed51e3b2c5e61cb4115f8ce9c1","source":{"kind":"arxiv","id":"2402.17887","version":4},"attestation_state":"computed","paper":{"title":"JMLR: Joint Medical LLM and Retrieval Training for Enhancing Reasoning and Professional Question Answering Capability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Hong Yu, Junda Wang, Zhichao Yang, Zonghai Yao","submitted_at":"2024-02-27T21:01:41Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated a remarkable potential in medical knowledge acquisition and question-answering. However, LLMs can potentially hallucinate and yield factually incorrect outcomes, even with domain-specific pretraining. Previously, retrieval augmented generation (RAG) has limited success in addressing hallucinations. Unlike previous methods in RAG where the retrieval model was trained separately from the LLM, we introduce JMLR (for Jointly trains LLM and information Retrieval) during the fine-tuning phase. The synchronized training mechanism enhances JMLR's ability "},"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":"2402.17887","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-27T21:01:41Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"f62ead4a7aba2f67e86b4f18afac059aeb8babb87fe86bb1ae7822d3062efe2c","abstract_canon_sha256":"78b000ee9f4e653c691bffe83f426188be7964cb43202881ad0e52361f0ff964"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:37:51.544773Z","signature_b64":"0qXBd5RsgRqADBPoSgQGzqgxon/3J19Xy6aB2pA/nyjaE9IzFkAAFaAyavvqMPLxISt/xarus+x250LRNf1TCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5dade4adf17de1674e98ef6fe32563261b7c4ed51e3b2c5e61cb4115f8ce9c1","last_reissued_at":"2026-07-05T08:37:51.544339Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:37:51.544339Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"JMLR: Joint Medical LLM and Retrieval Training for Enhancing Reasoning and Professional Question Answering Capability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Hong Yu, Junda Wang, Zhichao Yang, Zonghai Yao","submitted_at":"2024-02-27T21:01:41Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated a remarkable potential in medical knowledge acquisition and question-answering. However, LLMs can potentially hallucinate and yield factually incorrect outcomes, even with domain-specific pretraining. Previously, retrieval augmented generation (RAG) has limited success in addressing hallucinations. Unlike previous methods in RAG where the retrieval model was trained separately from the LLM, we introduce JMLR (for Jointly trains LLM and information Retrieval) during the fine-tuning phase. The synchronized training mechanism enhances JMLR's ability "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.17887","kind":"arxiv","version":4},"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/2402.17887/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":"2402.17887","created_at":"2026-07-05T08:37:51.544393+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.17887v4","created_at":"2026-07-05T08:37:51.544393+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.17887","created_at":"2026-07-05T08:37:51.544393+00:00"},{"alias_kind":"pith_short_12","alias_value":"UXNN4SW7C7PB","created_at":"2026-07-05T08:37:51.544393+00:00"},{"alias_kind":"pith_short_16","alias_value":"UXNN4SW7C7PBM5HJ","created_at":"2026-07-05T08:37:51.544393+00:00"},{"alias_kind":"pith_short_8","alias_value":"UXNN4SW7","created_at":"2026-07-05T08:37:51.544393+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.20591","citing_title":"Do No Harm? Hallucination and Actor-Level Abuse in Web-Deployed Medical Large Language Models","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09584","citing_title":"CLR-voyance: Reinforcing Open-Ended Reasoning for Inpatient Clinical Decision Support with Outcome-Aware Rubrics","ref_index":120,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UXNN4SW7C7PBM5HJR33P4MSWGJ","json":"https://pith.science/pith/UXNN4SW7C7PBM5HJR33P4MSWGJ.json","graph_json":"https://pith.science/api/pith-number/UXNN4SW7C7PBM5HJR33P4MSWGJ/graph.json","events_json":"https://pith.science/api/pith-number/UXNN4SW7C7PBM5HJR33P4MSWGJ/events.json","paper":"https://pith.science/paper/UXNN4SW7"},"agent_actions":{"view_html":"https://pith.science/pith/UXNN4SW7C7PBM5HJR33P4MSWGJ","download_json":"https://pith.science/pith/UXNN4SW7C7PBM5HJR33P4MSWGJ.json","view_paper":"https://pith.science/paper/UXNN4SW7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.17887&json=true","fetch_graph":"https://pith.science/api/pith-number/UXNN4SW7C7PBM5HJR33P4MSWGJ/graph.json","fetch_events":"https://pith.science/api/pith-number/UXNN4SW7C7PBM5HJR33P4MSWGJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UXNN4SW7C7PBM5HJR33P4MSWGJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UXNN4SW7C7PBM5HJR33P4MSWGJ/action/storage_attestation","attest_author":"https://pith.science/pith/UXNN4SW7C7PBM5HJR33P4MSWGJ/action/author_attestation","sign_citation":"https://pith.science/pith/UXNN4SW7C7PBM5HJR33P4MSWGJ/action/citation_signature","submit_replication":"https://pith.science/pith/UXNN4SW7C7PBM5HJR33P4MSWGJ/action/replication_record"}},"created_at":"2026-07-05T08:37:51.544393+00:00","updated_at":"2026-07-05T08:37:51.544393+00:00"}