{"id":"https://openalex.org/W4390833246","doi":"https://doi.org/10.48550/arxiv.2401.05695","title":"Integrating Physician Diagnostic Logic into Large Language Models: Preference Learning from Process Feedback","display_name":"Integrating Physician Diagnostic Logic into Large Language Models: Preference Learning from Process Feedback","publication_year":2024,"publication_date":"2024-01-11","ids":{"openalex":"https://openalex.org/W4390833246","doi":"https://doi.org/10.48550/arxiv.2401.05695"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2401.05695","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2401.05695","pdf_url":"https://arxiv.org/pdf/2401.05695","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2401.05695","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024794387","display_name":"Chengfeng Dou","orcid":"https://orcid.org/0000-0001-8135-0421"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Dou, Chengfeng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049100391","display_name":"Zhi Jin","orcid":"https://orcid.org/0000-0003-1087-226X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin, Zhi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065817676","display_name":"Wenpin Jiao","orcid":"https://orcid.org/0000-0001-9374-3900"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiao, Wenpin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100738980","display_name":"Haiyan Zhao","orcid":"https://orcid.org/0009-0006-5358-6895"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Haiyan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102331494","display_name":"Yongqiang Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Yongqiang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5080738811","display_name":"Zhenwei Tao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao, Zhenwei","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5024794387"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.9889000058174133,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.944599986076355,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/fluency","display_name":"Fluency","score":0.8609509468078613},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.7111778855323792},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7094222903251648},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6059406995773315},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5503265261650085},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4922727644443512},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.48100194334983826},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.47607749700546265},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.21211853623390198},{"id":"https://openalex.org/keywords/mathematics-education","display_name":"Mathematics education","score":0.11905500292778015},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10148024559020996}],"concepts":[{"id":"https://openalex.org/C2777413886","wikidata":"https://www.wikidata.org/wiki/Q3276013","display_name":"Fluency","level":2,"score":0.8609509468078613},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.7111778855323792},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7094222903251648},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6059406995773315},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5503265261650085},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4922727644443512},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.48100194334983826},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.47607749700546265},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.21211853623390198},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.11905500292778015},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10148024559020996},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2401.05695","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2401.05695","pdf_url":"https://arxiv.org/pdf/2401.05695","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2401.05695","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2401.05695","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2401.05695","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2401.05695","pdf_url":"https://arxiv.org/pdf/2401.05695","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7300000190734863,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G5482656022","display_name":null,"funder_award_id":"62192731","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390833246.pdf","grobid_xml":"https://content.openalex.org/works/W4390833246.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2365169615","https://openalex.org/W1970538215","https://openalex.org/W2400151637","https://openalex.org/W2975827637","https://openalex.org/W2354089692","https://openalex.org/W595497825","https://openalex.org/W4236323843","https://openalex.org/W2002616876","https://openalex.org/W3174418441","https://openalex.org/W4309298167"],"abstract_inverted_index":{"The":[0],"use":[1],"of":[2,108],"large":[3],"language":[4],"models":[5],"in":[6,29,112,128],"medical":[7,35,113,140],"dialogue":[8,133,141],"generation":[9],"has":[10],"garnered":[11],"significant":[12],"attention,":[13],"with":[14],"a":[15,40],"focus":[16],"on":[17],"improving":[18,139],"response":[19],"quality":[20],"and":[21,82,131],"fluency.":[22],"While":[23],"previous":[24],"studies":[25],"have":[26],"made":[27],"progress":[28],"optimizing":[30],"model":[31,88,111],"performance":[32],"for":[33,47,138],"single-round":[34,132],"Q&A":[36],"tasks,":[37,134],"there":[38],"is":[39],"need":[41],"to":[42,50,85,89,91],"enhance":[43],"the":[44,69,87,92,105,109],"model's":[45],"capability":[46],"multi-round":[48,130],"conversations":[49,114],"avoid":[51],"logical":[52],"inconsistencies.":[53],"To":[54],"address":[55],"this,":[56],"we":[57],"propose":[58],"an":[59],"approach":[60],"called":[61],"preference":[62,79,83],"learning":[63,120],"from":[64,121],"process":[65],"feedback~(PLPF),":[66],"which":[67],"integrates":[68],"doctor's":[70],"diagnostic":[71,93,106],"logic":[72],"into":[73],"LLMs.":[74],"PLPF":[75,103,125],"involves":[76],"rule":[77],"modeling,":[78],"data":[80],"generation,":[81],"alignment":[84],"train":[86],"adhere":[90],"process.":[94],"Experimental":[95],"results":[96],"using":[97],"Standardized":[98],"Patient":[99],"Testing":[100],"show":[101],"that":[102],"enhances":[104],"accuracy":[107],"baseline":[110],"by":[115],"17.6%,":[116],"outperforming":[117],"traditional":[118],"reinforcement":[119],"human":[122],"feedback.":[123],"Additionally,":[124],"demonstrates":[126],"effectiveness":[127],"both":[129],"showcasing":[135],"its":[136],"potential":[137],"generation.":[142]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2024-01-13T00:00:00"}