{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7LF4ASBEWQOFKK663YUWG7YEM4","short_pith_number":"pith:7LF4ASBE","schema_version":"1.0","canonical_sha256":"facbc04824b41c552bdede29637f04670f41fbd975bfdc4b71bf67089ed566d0","source":{"kind":"arxiv","id":"2305.15075","version":1},"attestation_state":"computed","paper":{"title":"HuatuoGPT, towards Taming Language Model to Be a Doctor","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Benyou Wang, Fei Yu, Feng Jiang, Guiming Chen, Haizhou Li, Hongbo Zhang, Jianquan Li, Junying Chen, Qingying Xiao, Xiangbo Wu, Xiang Wan, Zhihong Chen, Zhiyi Zhang","submitted_at":"2023-05-24T11:56:01Z","abstract_excerpt":"In this paper, we present HuatuoGPT, a large language model (LLM) for medical consultation. The core recipe of HuatuoGPT is to leverage both \\textit{distilled data from ChatGPT} and \\textit{real-world data from doctors} in the supervised fine-tuned stage. The responses of ChatGPT are usually detailed, well-presented and informative while it cannot perform like a doctor in many aspects, e.g. for integrative diagnosis. We argue that real-world data from doctors would be complementary to distilled data in the sense the former could tame a distilled language model to perform like doctors. To bette"},"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":"2305.15075","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T11:56:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ed30c7fbaf941e1d3b1e1b82a467c98bb2324b987744d9af4d2ba503cb737970","abstract_canon_sha256":"9e49e19e3afce647059777d40e1fb32bd7c5e6b0f26dd21d758745d039a14113"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:13:30.933758Z","signature_b64":"mRihVbhbIk4GWLSRYAhexYmv1H8eh2vfrC8lw55HK2x5R59/WAQ2Ah/8oG+n+z/eLgZSWqrYnw4bbwyJg8WpBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"facbc04824b41c552bdede29637f04670f41fbd975bfdc4b71bf67089ed566d0","last_reissued_at":"2026-07-05T06:13:30.933271Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:13:30.933271Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HuatuoGPT, towards Taming Language Model to Be a Doctor","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Benyou Wang, Fei Yu, Feng Jiang, Guiming Chen, Haizhou Li, Hongbo Zhang, Jianquan Li, Junying Chen, Qingying Xiao, Xiangbo Wu, Xiang Wan, Zhihong Chen, Zhiyi Zhang","submitted_at":"2023-05-24T11:56:01Z","abstract_excerpt":"In this paper, we present HuatuoGPT, a large language model (LLM) for medical consultation. The core recipe of HuatuoGPT is to leverage both \\textit{distilled data from ChatGPT} and \\textit{real-world data from doctors} in the supervised fine-tuned stage. The responses of ChatGPT are usually detailed, well-presented and informative while it cannot perform like a doctor in many aspects, e.g. for integrative diagnosis. We argue that real-world data from doctors would be complementary to distilled data in the sense the former could tame a distilled language model to perform like doctors. To bette"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.15075","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/2305.15075/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":"2305.15075","created_at":"2026-07-05T06:13:30.933338+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.15075v1","created_at":"2026-07-05T06:13:30.933338+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.15075","created_at":"2026-07-05T06:13:30.933338+00:00"},{"alias_kind":"pith_short_12","alias_value":"7LF4ASBEWQOF","created_at":"2026-07-05T06:13:30.933338+00:00"},{"alias_kind":"pith_short_16","alias_value":"7LF4ASBEWQOFKK66","created_at":"2026-07-05T06:13:30.933338+00:00"},{"alias_kind":"pith_short_8","alias_value":"7LF4ASBE","created_at":"2026-07-05T06:13:30.933338+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17412","citing_title":"Enhancing Pathological VLMs with Cross-scale Reasoning","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2502.07143","citing_title":"Ask Patients with Patience: Enabling LLMs for Human-Centric Medical Dialogue with Grounded Reasoning","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2401.05561","citing_title":"TrustLLM: Trustworthiness in Large Language Models","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2601.13262","citing_title":"CURE-Med: Curriculum-Informed Reinforcement Learning for Multilingual Medical Reasoning","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2601.20375","citing_title":"LLM-AutoDP: Automatic Data Processing via LLM Agents for Model Fine-tuning","ref_index":57,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7LF4ASBEWQOFKK663YUWG7YEM4","json":"https://pith.science/pith/7LF4ASBEWQOFKK663YUWG7YEM4.json","graph_json":"https://pith.science/api/pith-number/7LF4ASBEWQOFKK663YUWG7YEM4/graph.json","events_json":"https://pith.science/api/pith-number/7LF4ASBEWQOFKK663YUWG7YEM4/events.json","paper":"https://pith.science/paper/7LF4ASBE"},"agent_actions":{"view_html":"https://pith.science/pith/7LF4ASBEWQOFKK663YUWG7YEM4","download_json":"https://pith.science/pith/7LF4ASBEWQOFKK663YUWG7YEM4.json","view_paper":"https://pith.science/paper/7LF4ASBE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.15075&json=true","fetch_graph":"https://pith.science/api/pith-number/7LF4ASBEWQOFKK663YUWG7YEM4/graph.json","fetch_events":"https://pith.science/api/pith-number/7LF4ASBEWQOFKK663YUWG7YEM4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7LF4ASBEWQOFKK663YUWG7YEM4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7LF4ASBEWQOFKK663YUWG7YEM4/action/storage_attestation","attest_author":"https://pith.science/pith/7LF4ASBEWQOFKK663YUWG7YEM4/action/author_attestation","sign_citation":"https://pith.science/pith/7LF4ASBEWQOFKK663YUWG7YEM4/action/citation_signature","submit_replication":"https://pith.science/pith/7LF4ASBEWQOFKK663YUWG7YEM4/action/replication_record"}},"created_at":"2026-07-05T06:13:30.933338+00:00","updated_at":"2026-07-05T06:13:30.933338+00:00"}