{"id":"https://openalex.org/W7128308090","doi":"https://doi.org/10.26599/bdma.2024.9020097","title":"Bailicai: A Domain-Optimized Retrieval-Augmented Generation Framework for Medical Applications","display_name":"Bailicai: A Domain-Optimized Retrieval-Augmented Generation Framework for Medical Applications","publication_year":2026,"publication_date":"2026-02-06","ids":{"openalex":"https://openalex.org/W7128308090","doi":"https://doi.org/10.26599/bdma.2024.9020097"},"language":"en","primary_location":{"id":"doi:10.26599/bdma.2024.9020097","is_oa":true,"landing_page_url":"https://doi.org/10.26599/bdma.2024.9020097","pdf_url":null,"source":{"id":"https://openalex.org/S4210209060","display_name":"Big Data Mining and Analytics","issn_l":"2096-0654","issn":["2096-0654","2097-406X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311901","host_organization_name":"Tsinghua University Press","host_organization_lineage":["https://openalex.org/P4310311901"],"host_organization_lineage_names":["Tsinghua University Press"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Big Data Mining and Analytics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.26599/bdma.2024.9020097","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125352773","display_name":"Long Cui","orcid":null},"institutions":[{"id":"https://openalex.org/I91935597","display_name":"University of South China","ror":"https://ror.org/03mqfn238","country_code":"CN","type":"education","lineage":["https://openalex.org/I91935597"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Long Cui","raw_affiliation_strings":["School of Computer, University of South China,Hengyang,China,421001"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer, University of South China,Hengyang,China,421001","institution_ids":["https://openalex.org/I91935597"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100644814","display_name":"Ying Liu","orcid":"https://orcid.org/0000-0002-8951-2648"},"institutions":[{"id":"https://openalex.org/I91935597","display_name":"University of South China","ror":"https://ror.org/03mqfn238","country_code":"CN","type":"education","lineage":["https://openalex.org/I91935597"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongbin Liu","raw_affiliation_strings":["School of Computer, University of South China,Hengyang,China,421001"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer, University of South China,Hengyang,China,421001","institution_ids":["https://openalex.org/I91935597"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125366115","display_name":"Chunping Ouyang","orcid":null},"institutions":[{"id":"https://openalex.org/I91935597","display_name":"University of South China","ror":"https://ror.org/03mqfn238","country_code":"CN","type":"education","lineage":["https://openalex.org/I91935597"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunping Ouyang","raw_affiliation_strings":["School of Computer, University of South China,Hengyang,China,421001"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer, University of South China,Hengyang,China,421001","institution_ids":["https://openalex.org/I91935597"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103014226","display_name":"Ying Yu","orcid":"https://orcid.org/0000-0003-3099-1485"},"institutions":[{"id":"https://openalex.org/I91935597","display_name":"University of South China","ror":"https://ror.org/03mqfn238","country_code":"CN","type":"education","lineage":["https://openalex.org/I91935597"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Yu","raw_affiliation_strings":["School of Computer, University of South China,Hengyang,China,421001"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer, University of South China,Hengyang,China,421001","institution_ids":["https://openalex.org/I91935597"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100611354","display_name":"George Zhang","orcid":"https://orcid.org/0000-0003-2073-7109"},"institutions":[{"id":"https://openalex.org/I4210096476","display_name":"307th Hospital of Chinese People\u2019s Liberation Army","ror":"https://ror.org/00vrd0936","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210096476"]},{"id":"https://openalex.org/I4210144506","display_name":"The 309th Hospital of Chinese People's Liberation Army","ror":"https://ror.org/046x15q93","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210144506"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangtao Zhang","raw_affiliation_strings":["The 305th Hospital of the Chinese People's Liberation Army,Beijing,China,100017"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The 305th Hospital of the Chinese People's Liberation Army,Beijing,China,100017","institution_ids":["https://openalex.org/I4210096476","https://openalex.org/I4210144506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125346508","display_name":"Yaping Wan","orcid":null},"institutions":[{"id":"https://openalex.org/I91935597","display_name":"University of South China","ror":"https://ror.org/03mqfn238","country_code":"CN","type":"education","lineage":["https://openalex.org/I91935597"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaping Wan","raw_affiliation_strings":["School of Computer, University of South China,Hengyang,China,421001"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer, University of South China,Hengyang,China,421001","institution_ids":["https://openalex.org/I91935597"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100784078","display_name":"Fei Yang","orcid":"https://orcid.org/0000-0003-4262-0913"},"institutions":[{"id":"https://openalex.org/I91935597","display_name":"University of South China","ror":"https://ror.org/03mqfn238","country_code":"CN","type":"education","lineage":["https://openalex.org/I91935597"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Yang","raw_affiliation_strings":["School of Public Health, University of South China,Hengyang,China,421001"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Public Health, University of South China,Hengyang,China,421001","institution_ids":["https://openalex.org/I91935597"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":71.695,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.99793,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"9","issue":"2","first_page":"376","last_page":"392"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.16349999606609344,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.16349999606609344,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.06360000371932983,"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/T10028","display_name":"Topic Modeling","score":0.039400000125169754,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2671999931335449},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.24580000340938568},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.24500000476837158},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.2304999977350235},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.22779999673366547}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5386000275611877},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.24770000576972961},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.24580000340938568},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.24500000476837158},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.23589999973773956},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2304999977350235},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.22779999673366547},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.22429999709129333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22269999980926514}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.26599/bdma.2024.9020097","is_oa":true,"landing_page_url":"https://doi.org/10.26599/bdma.2024.9020097","pdf_url":null,"source":{"id":"https://openalex.org/S4210209060","display_name":"Big Data Mining and Analytics","issn_l":"2096-0654","issn":["2096-0654","2097-406X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311901","host_organization_name":"Tsinghua University Press","host_organization_lineage":["https://openalex.org/P4310311901"],"host_organization_lineage_names":["Tsinghua University Press"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Big Data Mining and Analytics","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:292421ff54f74db99fe392dac81e39b9","is_oa":true,"landing_page_url":"https://doaj.org/article/292421ff54f74db99fe392dac81e39b9","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Big Data Mining and Analytics, Vol 9, Iss 2, Pp 376-392 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.26599/bdma.2024.9020097","is_oa":true,"landing_page_url":"https://doi.org/10.26599/bdma.2024.9020097","pdf_url":null,"source":{"id":"https://openalex.org/S4210209060","display_name":"Big Data Mining and Analytics","issn_l":"2096-0654","issn":["2096-0654","2097-406X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311901","host_organization_name":"Tsinghua University Press","host_organization_lineage":["https://openalex.org/P4310311901"],"host_organization_lineage_names":["Tsinghua University Press"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Big Data Mining and Analytics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6668869155","display_name":null,"funder_award_id":"61533018,61402220","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7727188646","display_name":null,"funder_award_id":"16YBA323","funder_id":"https://openalex.org/F4320326278","funder_display_name":"Philosophy and Social Science Foundation of Hunan Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320326278","display_name":"Philosophy and Social Science Foundation of Hunan Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2970482702","https://openalex.org/W3099700870","https://openalex.org/W3144215978","https://openalex.org/W4213457947","https://openalex.org/W4313887030","https://openalex.org/W4319662928","https://openalex.org/W4361001766","https://openalex.org/W4377197291","https://openalex.org/W4384071683","https://openalex.org/W4384561707","https://openalex.org/W4388409299","https://openalex.org/W4388778348","https://openalex.org/W4389518671","https://openalex.org/W4389519118","https://openalex.org/W4389520468","https://openalex.org/W4391221150","https://openalex.org/W4391376033","https://openalex.org/W4391940656","https://openalex.org/W4394782456","https://openalex.org/W4400128031","https://openalex.org/W4402670290","https://openalex.org/W4402670862","https://openalex.org/W4402671748","https://openalex.org/W4402671772","https://openalex.org/W4404035160","https://openalex.org/W4406152279","https://openalex.org/W4412158322","https://openalex.org/W4415798212"],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1,8],"models":[2,56,209,218],"(LLMs)":[3],"excel":[4],"in":[5,15,23,100,121,145,210,230],"various":[6],"natural":[7],"processing":[9],"tasks":[10,235],"and":[11,33,59,92,137,163,188,216,236,254],"are":[12,142],"increasingly":[13],"applied":[14,232],"specialized":[16],"fields":[17],"like":[18,57],"medicine.":[19],"However,":[20],"their":[21],"deployment":[22],"the":[24,34,81,87,96,101,109,122,131,146,154,158,193,211,226,238],"medical":[25,97,123,175,204,212,234],"domain":[26],"is":[27,169],"challenged":[28],"by":[29,75],"limited":[30],"domain-specific":[31],"data":[32],"tendency":[35],"to":[36,54,72,116,129,152,156,233],"generate":[37],"inaccurate":[38],"information,":[39],"known":[40],"as":[41,112,220],"\u201challucinations.\u201d":[42],"While":[43],"domainspecific":[44],"fine-tuning":[45,128],"has":[46],"improved":[47],"open-source":[48],"LLMs,":[49],"they":[50],"still":[51],"underperform":[52],"compared":[53],"proprietary":[55,217],"ChatGPT":[58],"PaLM.":[60],"To":[61],"address":[62],"this":[63,105],"gap,":[64],"retrieval-augmented":[65,190],"generation":[66],"(RAG)":[67],"techniques":[68],"have":[69],"been":[70],"explored":[71],"enhance":[73],"LLMs":[74,120,231],"integrating":[76,117],"external":[77],"knowledge":[78,176],"bases.":[79],"Nevertheless,":[80],"success":[82],"of":[83,89,160,195,240],"RAG":[84,118,132,241],"depends":[85],"on":[86,202],"quality":[88,159],"retrieved":[90,161],"documents,":[91,248],"its":[93],"application":[94],"within":[95],"field":[98],"remains":[99],"early":[102],"stages.":[103],"In":[104],"paper,":[106],"we":[107],"introduce":[108],"\u201cBailicai\u201d":[110],"framework":[111,126,168],"an":[113],"exploratory":[114],"approach":[115],"with":[119,244],"field.":[124],"The":[125,167],"employs":[127],"improve":[130],"process,":[133],"where":[134],"\u201cfalsely":[135],"relevant\u201d":[136],"\u201ccompletely":[138],"irrelevant\u201d":[139],"interference":[140],"documents":[141,162],"intentionally":[143],"included":[144],"training":[147],"data.":[148],"This":[149],"enables":[150],"Bailicai":[151,198,223],"develop":[153],"ability":[155],"assess":[157],"selectively":[164],"incorporate":[165],"them.":[166],"organized":[170],"into":[171],"four":[172],"modules:":[173],"(1)":[174],"injection,":[177],"(2)":[178],"self-knowledge":[179],"boundary":[180],"identification,":[181],"(3)":[182],"directed":[183],"acyclic":[184],"graph":[185],"task":[186],"decomposition,":[187],"(4)":[189],"generation.":[191],"Through":[192],"synergy":[194],"these":[196],"modules,":[197],"achieves":[199],"superior":[200],"performance":[201],"multiple":[203],"benchmarks,":[205],"outperforming":[206],"existing":[207],"large":[208],"domain,":[213],"RAG-based":[214],"methods,":[215],"such":[219],"GPT-3.5.":[221],"Furthermore,":[222],"effectively":[224],"mitigates":[225],"hallucination":[227],"problem":[228],"common":[229],"enhances":[237],"robustness":[239],"when":[242],"dealing":[243],"irrelevant":[245],"or":[246],"misleading":[247],"enabling":[249],"more":[250],"accurate":[251],"information":[252],"retrieval":[253],"integration.":[255]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-02-09T00:00:00"}