{"id":"https://openalex.org/W4400128031","doi":"https://doi.org/10.1093/bioinformatics/btae238","title":"Improving medical reasoning through retrieval and self-reflection with retrieval-augmented large language models","display_name":"Improving medical reasoning through retrieval and self-reflection with retrieval-augmented large language models","publication_year":2024,"publication_date":"2024-06-28","ids":{"openalex":"https://openalex.org/W4400128031","doi":"https://doi.org/10.1093/bioinformatics/btae238","pmid":"https://pubmed.ncbi.nlm.nih.gov/38940167"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btae238","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btae238","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1093/bioinformatics/btae238","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007444423","display_name":"Minbyul Jeong","orcid":"https://orcid.org/0000-0002-1346-730X"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minbyul Jeong","raw_affiliation_strings":["Department of Computer Science, Korea University , Seoul 02841, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-1346-730X","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Korea University , Seoul 02841, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111160365","display_name":"Jiwoong Sohn","orcid":null},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jiwoong Sohn","raw_affiliation_strings":["Department of Computer Science, Korea University , Seoul 02841, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Korea University , Seoul 02841, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020746366","display_name":"Mujeen Sung","orcid":"https://orcid.org/0000-0002-7978-8114"},"institutions":[{"id":"https://openalex.org/I35928602","display_name":"Kyung Hee University","ror":"https://ror.org/01zqcg218","country_code":"KR","type":"education","lineage":["https://openalex.org/I35928602"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Mujeen Sung","raw_affiliation_strings":["Department of Software Convergence, School of Computing, Kyung Hee University , Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Software Convergence, School of Computing, Kyung Hee University , Republic of Korea","institution_ids":["https://openalex.org/I35928602"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076917278","display_name":"Jaewoo Kang","orcid":"https://orcid.org/0000-0001-6798-9106"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaewoo Kang","raw_affiliation_strings":["AIGEN Sciences , Seoul 04778, Republic of Korea","Department of Computer Science, Korea University , Seoul 02841, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0001-6798-9106","affiliations":[{"raw_affiliation_string":"AIGEN Sciences , Seoul 04778, Republic of Korea","institution_ids":[]},{"raw_affiliation_string":"Department of Computer Science, Korea University , Seoul 02841, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":27.2991,"has_fulltext":true,"cited_by_count":112,"citation_normalized_percentile":{"value":0.99758547,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"40","issue":"Supplement_1","first_page":"i119","last_page":"i129"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.34299999475479126,"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":0.34299999475479126,"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":0.3140999972820282,"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"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.08799999952316284,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/computer-science","display_name":"Computer science","score":0.7328013777732849},{"id":"https://openalex.org/keywords/reflection","display_name":"Reflection (computer programming)","score":0.575113832950592},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5093337297439575},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48317113518714905},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40556830167770386},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.20021462440490723}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7328013777732849},{"id":"https://openalex.org/C65682993","wikidata":"https://www.wikidata.org/wiki/Q1056451","display_name":"Reflection (computer programming)","level":2,"score":0.575113832950592},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5093337297439575},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48317113518714905},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40556830167770386},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.20021462440490723}],"mesh":[{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btae238","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btae238","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:38940167","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38940167","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:11211826","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11211826","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11211826/pdf/btae238.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btae238","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btae238","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"No poverty","id":"https://metadata.un.org/sdg/1"}],"awards":[{"id":"https://openalex.org/G1014725244","display_name":null,"funder_award_id":"NRF-2022R1C1C1008074","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G1811286182","display_name":null,"funder_award_id":"IITP-2024\u20132020-0-01819","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G2196686709","display_name":null,"funder_award_id":"RS-2023-00262002","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G2808261082","display_name":null,"funder_award_id":"RS-2023\u201300262002","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G2906057384","display_name":null,"funder_award_id":"IITP-2024-2020-0-01819","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G3497368782","display_name":null,"funder_award_id":"NRF-2023R1A2C3004176","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G3872958509","display_name":null,"funder_award_id":"RS-2022-00155911","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G4700831490","display_name":null,"funder_award_id":"2022-","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G4932531269","display_name":null,"funder_award_id":"RS-2022-00155911","funder_id":"https://openalex.org/F4320321332","funder_display_name":"Kyung Hee University"},{"id":"https://openalex.org/G585115220","display_name":null,"funder_award_id":"RS-2022-00155911","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G7071920538","display_name":null,"funder_award_id":"IITP-2024-2020-0-01819","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G7144477073","display_name":null,"funder_award_id":"2022R1C1C1008074","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G7629951494","display_name":null,"funder_award_id":"RS-2023-00262002","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G8018065544","display_name":null,"funder_award_id":"2020-0-01819","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G8932255049","display_name":null,"funder_award_id":"2023R1A2C3004176","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320321332","display_name":"Kyung Hee University","ror":"https://ror.org/01zqcg218"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W2990031975","https://openalex.org/W4388409299"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W3204019825"],"abstract_inverted_index":{"SUMMARY:":[0],"Recent":[1],"proprietary":[2],"large":[3],"language":[4],"models":[5],"(LLMs),":[6],"such":[7,143],"as":[8,144,245],"GPT-4,":[9],"have":[10,48],"achieved":[11],"a":[12,99,145,177,189,246],"milestone":[13],"in":[14,18,107,204,224,270],"tackling":[15],"diverse":[16],"challenges":[17,31],"the":[19,38,55,65,184,222,225],"biomedical":[20,103,121,271],"domain,":[21],"ranging":[22],"from":[23,54,239],"multiple-choice":[24],"questions":[25],"to":[26,64,76,85,124,157,235,267],"long-form":[27,211],"generations.":[28],"To":[29],"address":[30],"that":[32,105,127,140,219],"still":[33],"cannot":[34],"be":[35],"handled":[36],"with":[37,133,188,237],"encoded":[39,243],"knowledge":[40,56,244],"of":[41,67,169,192],"LLMs,":[42],"various":[43],"retrieval-augmented":[44],"generation":[45],"(RAG)":[46],"methods":[47,75],"been":[49],"developed":[50],"by":[51,175,200],"searching":[52],"documents":[53,88,229,241],"corpus":[57],"and":[58,113,150,232,242,254,261,265,272],"appending":[59],"them":[60],"unconditionally":[61],"or":[62,89,194],"selectively":[63],"input":[66],"LLMs":[68],"for":[69,102,155,256],"generation.":[70],"However,":[71],"when":[72],"applying":[73],"existing":[74],"different":[77],"domain-specific":[78,111,141],"problems,":[79],"poor":[80],"generalization":[81],"becomes":[82],"apparent,":[83],"leading":[84],"fetching":[86],"incorrect":[87],"making":[90],"inaccurate":[91],"judgments.":[92],"In":[93],"this":[94],"paper,":[95],"we":[96,217],"introduce":[97],"Self-BioRAG,":[98],"framework":[100,259],"reliable":[101],"text":[104],"specializes":[106],"generating":[108,205],"explanations,":[109],"retrieving":[110],"documents,":[112],"self-reflecting":[114],"generated":[115,131],"responses.":[116],"We":[117,250],"utilize":[118],"84k":[119],"filtered":[120],"instruction":[122,151],"sets":[123,152],"train":[125],"Self-BioRAG":[126,170,197,220,278],"can":[128],"assess":[129],"its":[130],"explanations":[132],"customized":[134],"reflective":[135],"tokens.":[136],"Our":[137],"work":[138],"proves":[139],"components,":[142],"retriever,":[146],"domain-related":[147,158],"document":[148],"corpus,":[149],"are":[153],"necessary":[154],"adhering":[156],"instructions.":[159],"Using":[160],"three":[161],"major":[162],"medical":[163,247],"question-answering":[164,212],"benchmark":[165],"datasets,":[166],"experimental":[167],"results":[168],"demonstrate":[171],"significant":[172],"performance":[173],"gains":[174],"achieving":[176],"7.2%":[178],"absolute":[179],"improvement":[180],"on":[181,209,214],"average":[182],"over":[183],"state-of-the-art":[185],"open-foundation":[186],"model":[187,262],"parameter":[190],"size":[191],"7B":[193],"less.":[195],"Similarly,":[196],"outperforms":[198],"RAG":[199],"8%":[201],"Rouge-1":[202],"score":[203],"more":[206],"proficient":[207],"answers":[208],"two":[210],"benchmarks":[213],"average.":[215],"Overall,":[216],"analyze":[218],"finds":[221],"clues":[223],"question,":[226],"retrieves":[227],"relevant":[228],"if":[230],"needed,":[231],"understands":[233],"how":[234],"answer":[236],"information":[238],"retrieved":[240],"expert":[248],"does.":[249],"release":[251],"our":[252,258],"data":[253],"code":[255],"training":[257],"components":[260],"weights":[263],"(7B":[264],"13B)":[266],"enhance":[268],"capabilities":[269],"clinical":[273],"domains.":[274],"AVAILABILITY":[275],"AND":[276],"IMPLEMENTATION:":[277],"is":[279],"available":[280],"at":[281],"https://github.com/dmis-lab/self-biorag.":[282]},"counts_by_year":[{"year":2026,"cited_by_count":41},{"year":2025,"cited_by_count":53},{"year":2024,"cited_by_count":18}],"updated_date":"2026-07-21T08:15:58.654021","created_date":"2025-10-10T00:00:00"}