{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:H56GT67LFXB2ZCW4RKDMYFN5J2","short_pith_number":"pith:H56GT67L","schema_version":"1.0","canonical_sha256":"3f7c69fbeb2dc3ac8adc8a86cc15bd4ebf275c274c1b2acd48077956e8111f90","source":{"kind":"arxiv","id":"2410.04112","version":1},"attestation_state":"computed","paper":{"title":"Exploring LLM-based Data Annotation Strategies for Medical Dialogue Preference Alignment","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chengfeng Dou, Haiyan Zhao, Wenpin Jiao, Ying Zhang, Yongqiang Zhao, Zhengwei Tao, Zhi Jin","submitted_at":"2024-10-05T10:29:19Z","abstract_excerpt":"This research examines the use of Reinforcement Learning from AI Feedback (RLAIF) techniques to improve healthcare dialogue models, with the aim of tackling the challenges of preference-aligned data annotation while reducing the reliance on medical experts. We argue that the primary challenges in current RLAIF research for healthcare are the limitations of automated evaluation methods and the difficulties in accurately representing physician preferences. To address these challenges, we present a new evaluation framework based on standardized patient examinations. This framework is designed to "},"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":"2410.04112","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-05T10:29:19Z","cross_cats_sorted":[],"title_canon_sha256":"9854d5ce4725b51412c6c9f04237cb134b1cd44f014b1f77c2547880f7afb3e5","abstract_canon_sha256":"8fbf1070e51ad0d864027897b8922d1d6de9cd8632c259456e2b262654429244"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:16:29.268100Z","signature_b64":"3VHsmee0elLQ7rfmYG1+XMioe/WXK3kDRww40+ATe9HNlkzOSVMoFSqKXfyFZFAlsQnJsNMoBZNkSfuQHHtGBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f7c69fbeb2dc3ac8adc8a86cc15bd4ebf275c274c1b2acd48077956e8111f90","last_reissued_at":"2026-07-05T09:16:29.267605Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:16:29.267605Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring LLM-based Data Annotation Strategies for Medical Dialogue Preference Alignment","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chengfeng Dou, Haiyan Zhao, Wenpin Jiao, Ying Zhang, Yongqiang Zhao, Zhengwei Tao, Zhi Jin","submitted_at":"2024-10-05T10:29:19Z","abstract_excerpt":"This research examines the use of Reinforcement Learning from AI Feedback (RLAIF) techniques to improve healthcare dialogue models, with the aim of tackling the challenges of preference-aligned data annotation while reducing the reliance on medical experts. We argue that the primary challenges in current RLAIF research for healthcare are the limitations of automated evaluation methods and the difficulties in accurately representing physician preferences. To address these challenges, we present a new evaluation framework based on standardized patient examinations. This framework is designed to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.04112","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/2410.04112/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":"2410.04112","created_at":"2026-07-05T09:16:29.267667+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.04112v1","created_at":"2026-07-05T09:16:29.267667+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.04112","created_at":"2026-07-05T09:16:29.267667+00:00"},{"alias_kind":"pith_short_12","alias_value":"H56GT67LFXB2","created_at":"2026-07-05T09:16:29.267667+00:00"},{"alias_kind":"pith_short_16","alias_value":"H56GT67LFXB2ZCW4","created_at":"2026-07-05T09:16:29.267667+00:00"},{"alias_kind":"pith_short_8","alias_value":"H56GT67L","created_at":"2026-07-05T09:16:29.267667+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/H56GT67LFXB2ZCW4RKDMYFN5J2","json":"https://pith.science/pith/H56GT67LFXB2ZCW4RKDMYFN5J2.json","graph_json":"https://pith.science/api/pith-number/H56GT67LFXB2ZCW4RKDMYFN5J2/graph.json","events_json":"https://pith.science/api/pith-number/H56GT67LFXB2ZCW4RKDMYFN5J2/events.json","paper":"https://pith.science/paper/H56GT67L"},"agent_actions":{"view_html":"https://pith.science/pith/H56GT67LFXB2ZCW4RKDMYFN5J2","download_json":"https://pith.science/pith/H56GT67LFXB2ZCW4RKDMYFN5J2.json","view_paper":"https://pith.science/paper/H56GT67L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.04112&json=true","fetch_graph":"https://pith.science/api/pith-number/H56GT67LFXB2ZCW4RKDMYFN5J2/graph.json","fetch_events":"https://pith.science/api/pith-number/H56GT67LFXB2ZCW4RKDMYFN5J2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H56GT67LFXB2ZCW4RKDMYFN5J2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H56GT67LFXB2ZCW4RKDMYFN5J2/action/storage_attestation","attest_author":"https://pith.science/pith/H56GT67LFXB2ZCW4RKDMYFN5J2/action/author_attestation","sign_citation":"https://pith.science/pith/H56GT67LFXB2ZCW4RKDMYFN5J2/action/citation_signature","submit_replication":"https://pith.science/pith/H56GT67LFXB2ZCW4RKDMYFN5J2/action/replication_record"}},"created_at":"2026-07-05T09:16:29.267667+00:00","updated_at":"2026-07-05T09:16:29.267667+00:00"}