{"id":"https://openalex.org/W7126050284","doi":"https://doi.org/10.1109/bibm66473.2025.11356087","title":"Beyond Accuracy: Assessing LLMS' Ability to Recognize Their Limits in Medical Decision-Making","display_name":"Beyond Accuracy: Assessing LLMS' Ability to Recognize Their Limits in Medical Decision-Making","publication_year":2025,"publication_date":"2025-12-15","ids":{"openalex":"https://openalex.org/W7126050284","doi":"https://doi.org/10.1109/bibm66473.2025.11356087"},"language":null,"primary_location":{"id":"doi:10.1109/bibm66473.2025.11356087","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm66473.2025.11356087","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124152682","display_name":"Hao Fu","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hao Fu","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University,Tianjin,China"],"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124234717","display_name":"Zibo Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zibo Xiao","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University,Tianjin,China"],"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101987257","display_name":"Chuang LIU","orcid":"https://orcid.org/0000-0002-4728-670X"},"institutions":[{"id":"https://openalex.org/I4210165734","display_name":"National Supercomputing Center of Tianjin","ror":"https://ror.org/05tngxm14","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210165734"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuang Liu","raw_affiliation_strings":["National SuperComputer Center in Tianjin,Tianjin,China"],"affiliations":[{"raw_affiliation_string":"National SuperComputer Center in Tianjin,Tianjin,China","institution_ids":["https://openalex.org/I4210165734"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124211458","display_name":"Xiangfei Meng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165734","display_name":"National Supercomputing Center of Tianjin","ror":"https://ror.org/05tngxm14","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210165734"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangfei Meng","raw_affiliation_strings":["National SuperComputer Center in Tianjin,Tianjin,China"],"affiliations":[{"raw_affiliation_string":"National SuperComputer Center in Tianjin,Tianjin,China","institution_ids":["https://openalex.org/I4210165734"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5124152682"],"corresponding_institution_ids":["https://openalex.org/I162868743"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.71834238,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3579","last_page":"3582"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.8222000002861023,"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"}},"topics":[{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.8222000002861023,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.05400000140070915,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.026100000366568565,"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/autonomy","display_name":"Autonomy","score":0.6104999780654907},{"id":"https://openalex.org/keywords/metacognition","display_name":"Metacognition","score":0.5242000222206116},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.45210000872612},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.40790000557899475},{"id":"https://openalex.org/keywords/health-care","display_name":"Health care","score":0.3869999945163727},{"id":"https://openalex.org/keywords/medline","display_name":"MEDLINE","score":0.3010999858379364}],"concepts":[{"id":"https://openalex.org/C65414064","wikidata":"https://www.wikidata.org/wiki/Q484105","display_name":"Autonomy","level":2,"score":0.6104999780654907},{"id":"https://openalex.org/C118147538","wikidata":"https://www.wikidata.org/wiki/Q1126970","display_name":"Metacognition","level":3,"score":0.5242000222206116},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.47440001368522644},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.45210000872612},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4271000027656555},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.40790000557899475},{"id":"https://openalex.org/C160735492","wikidata":"https://www.wikidata.org/wiki/Q31207","display_name":"Health care","level":2,"score":0.3869999945163727},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.3862999975681305},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3560999929904938},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.34940001368522644},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.33730000257492065},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33660000562667847},{"id":"https://openalex.org/C195094911","wikidata":"https://www.wikidata.org/wiki/Q14167904","display_name":"Process management","level":1,"score":0.3190999925136566},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C2985722590","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medical knowledge","level":2,"score":0.2867000102996826},{"id":"https://openalex.org/C2982822547","wikidata":"https://www.wikidata.org/wiki/Q179661","display_name":"Medical treatment","level":2,"score":0.28049999475479126},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.27619999647140503},{"id":"https://openalex.org/C2988170871","wikidata":"https://www.wikidata.org/wiki/Q11000047","display_name":"Healthcare system","level":3,"score":0.25859999656677246},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.2540999948978424},{"id":"https://openalex.org/C3019354653","wikidata":"https://www.wikidata.org/wiki/Q5690885","display_name":"Medical costs","level":3,"score":0.25209999084472656}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm66473.2025.11356087","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm66473.2025.11356087","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7734404802322388}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":1,"referenced_works":["https://openalex.org/W4394782456"],"related_works":[],"abstract_inverted_index":{"While":[0],"Large":[1],"Language":[2],"Models":[3],"(LLMs)":[4],"demonstrate":[5,115],"impressive":[6],"medical":[7,33,110,137],"capabilities":[8],"through":[9,59],"Retrieval-Augmented":[10],"Generation":[11],"(RAG)":[12],"and":[13,70,130],"domain":[14],"optimization,":[15],"a":[16,50],"critical":[17],"question":[18],"remains:":[19],"can":[20],"LLMs":[21,79],"autonomously":[22],"recognize":[23],"when":[24],"to":[25,136],"seek":[26],"external":[27,64],"help":[28],"rather":[29],"than":[30],"provide":[31],"independent":[32],"recommendations?":[34],"This":[35],"metacognitive":[36,107],"capability":[37],"is":[38],"essential":[39],"for":[40],"safe":[41],"healthcare":[42],"deployment.":[43],"To":[44],"address":[45],"this":[46],"gap,":[47],"we":[48],"introduce":[49],"novel":[51],"evaluation":[52,76],"framework":[53],"assessing":[54],"LLMs'":[55],"autonomous":[56],"help-seeking":[57,100,132],"behavior":[58,133],"three":[60,90],"workflows:":[61],"Force-RAG":[62],"(mandated":[63],"retrieval),":[65],"No-RAG":[66],"(internal":[67],"knowledge":[68],"only),":[69],"Auto-RAG":[71],"(autonomous":[72],"decision-making).":[73],"Our":[74],"comprehensive":[75],"of":[77],"13":[78],"configurations":[80],"across":[81,109],"six":[82],"clinical":[83],"departments":[84],"using":[85],"954":[86],"real-world":[87],"cases":[88],"reveals":[89],"key":[91],"insights:":[92],"(1)":[93],"larger":[94],"models":[95,114],"don't":[96],"necessarily":[97],"exhibit":[98],"superior":[99,116],"calibration;":[101],"(2)":[102],"reasoning":[103],"strategies":[104],"significantly":[105],"impact":[106],"performance":[108],"domains;":[111],"(3)":[112],"proprietary":[113],"autonomy":[117],"in":[118],"balancing":[119],"self-reliance":[120],"with":[121],"appropriate":[122],"help-seeking.":[123],"These":[124],"findings":[125],"challenge":[126],"conventional":[127],"scaling":[128],"assumptions":[129],"establish":[131],"as":[134],"fundamental":[135],"AI":[138],"reliability.":[139]},"counts_by_year":[],"updated_date":"2026-02-23T20:09:44.859080","created_date":"2026-01-30T00:00:00"}
