{"id":"https://openalex.org/W4407308237","doi":"https://doi.org/10.1038/s41598-025-22940-0","title":"Limitations of large language models in clinical problem-solving arising from inflexible reasoning","display_name":"Limitations of large language models in clinical problem-solving arising from inflexible reasoning","publication_year":2025,"publication_date":"2025-11-11","ids":{"openalex":"https://openalex.org/W4407308237","doi":"https://doi.org/10.1038/s41598-025-22940-0","pmid":"https://pubmed.ncbi.nlm.nih.gov/41219270","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/12606185"},"language":"en","primary_location":{"id":"doi:10.1038/s41598-025-22940-0","doi":"https://doi.org/10.1038/s41598-025-22940-0","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41598-025-22940-0","pdf_url":"https://www.nature.com/articles/s41598-025-22940-0.pdf","source":{"id":"https://openalex.org/S196734849","display_name":"Scientific Reports","issn_l":"2045-2322","issn":["2045-2322"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-1","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientific Reports","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["arxiv","crossref","datacite","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.nature.com/articles/s41598-025-22940-0.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101455605","display_name":"Jonathan Kim","orcid":"https://orcid.org/0000-0001-5817-348X","observed_orcids":["https://orcid.org/0000-0001-5817-348X"]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan Kim","raw_affiliation_strings":["Department of Neurology and Neurologic Sciences, Stanford University, Palo Alto, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Neurology and Neurologic Sciences, Stanford University, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036597666","display_name":"Anna Podlasek","orcid":"https://orcid.org/0000-0001-7297-7169","observed_orcids":["https://orcid.org/0000-0001-7297-7169"]},"institutions":[{"id":"https://openalex.org/I177639307","display_name":"University of Dundee","ror":"https://ror.org/03h2bxq36","country_code":"GB","type":"education","lineage":["https://openalex.org/I177639307"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Anna Podlasek","raw_affiliation_strings":["Image Guided Therapy and Research Facility, University of Dundee, Dundee, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Image Guided Therapy and Research Facility, University of Dundee, Dundee, UK","institution_ids":["https://openalex.org/I177639307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116210769","display_name":"Kie Shidara","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I180670191","display_name":"University of California, San Francisco","ror":"https://ror.org/043mz5j54","country_code":"US","type":"education","lineage":["https://openalex.org/I180670191"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kie Shidara","raw_affiliation_strings":["Weill Institute of Neurology and Neurosciences, University of California, San Francisco, San Francisco, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Weill Institute of Neurology and Neurosciences, University of California, San Francisco, San Francisco, CA, USA","institution_ids":["https://openalex.org/I180670191"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100415282","display_name":"Feng Liu","orcid":"https://orcid.org/0000-0002-5225-8199","observed_orcids":["https://orcid.org/0000-0002-5225-8199"]},"institutions":[{"id":"https://openalex.org/I108468826","display_name":"Stevens Institute of Technology","ror":"https://ror.org/02z43xh36","country_code":"US","type":"education","lineage":["https://openalex.org/I108468826"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Feng Liu","raw_affiliation_strings":["Department of Systems and Enterprises, Stevens Institute of Technology, Hoboken, NJ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Systems and Enterprises, Stevens Institute of Technology, Hoboken, NJ, USA","institution_ids":["https://openalex.org/I108468826"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ahmed Alaa","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ahmed Alaa","raw_affiliation_strings":["Department of EECS, University of California Berkeley, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of EECS, University of California Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5105924929","display_name":"Danilo Bernardo","orcid":"https://orcid.org/0000-0003-1077-2963","observed_orcids":["https://orcid.org/0000-0003-1077-2963"]},"institutions":[{"id":"https://openalex.org/I180670191","display_name":"University of California, San Francisco","ror":"https://ror.org/043mz5j54","country_code":"US","type":"education","lineage":["https://openalex.org/I180670191"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Danilo Bernardo","raw_affiliation_strings":["Weill Institute of Neurology and Neurosciences, University of California, San Francisco, San Francisco, CA, USA. dbernardoj@gmail.com"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Weill Institute of Neurology and Neurosciences, University of California, San Francisco, San Francisco, CA, USA. dbernardoj@gmail.com","institution_ids":["https://openalex.org/I180670191"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5105924929"],"corresponding_institution_ids":["https://openalex.org/I180670191"],"apc_list":{"value":2690,"currency":"USD","value_usd":2690},"apc_paid":{"value":2690,"currency":"USD","value_usd":2690},"fwci":21.0245,"has_fulltext":true,"cited_by_count":111,"citation_normalized_percentile":{"value":0.99610964,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"15","issue":"1","first_page":"39426","last_page":"39426"},"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":0.9829000234603882,"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":0.9829000234603882,"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/T12574","display_name":"Clinical Reasoning and Diagnostic Skills","score":0.005900000222027302,"subfield":{"id":"https://openalex.org/subfields/2714","display_name":"Family Practice"},"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":0.0044999998062849045,"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/large-language-models","display_name":"large language models","score":0.996999979019165},{"id":"https://openalex.org/keywords/clinical-reasoning","display_name":"clinical reasoning","score":0.9599999785423279},{"id":"https://openalex.org/keywords/einstellung-effect","display_name":"Einstellung effect","score":0.8740000128746033},{"id":"https://openalex.org/keywords/medical-question-answering","display_name":"medical question answering","score":0.6809999942779541},{"id":"https://openalex.org/keywords/hallucinations","display_name":"hallucinations","score":0.7789999842643738},{"id":"https://openalex.org/keywords/overconfidence","display_name":"overconfidence","score":0.875},{"id":"https://openalex.org/keywords/uncertainty-estimation","display_name":"uncertainty estimation","score":0.9789999723434448},{"id":"https://openalex.org/keywords/inductive-bias","display_name":"inductive bias","score":0.7720000147819519},{"id":"https://openalex.org/keywords/failure-modes","display_name":"failure modes","score":0.6169999837875366},{"id":"https://openalex.org/keywords/clinical-problem-solving","display_name":"clinical problem solving","score":0.4189999997615814}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.47821947932243347},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.4020383059978485},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.38484102487564087},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.3749442398548126},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3594607710838318},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3443605303764343},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.1613900363445282},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.14098510146141052}],"mesh":[{"descriptor_ui":"D000086723","descriptor_name":"Clinical Reasoning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000098342","descriptor_name":"Large Language Models","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":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008962","descriptor_name":"Models, Theoretical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011340","descriptor_name":"Problem Solving","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":8,"locations":[{"id":"doi:10.1038/s41598-025-22940-0","doi":"https://doi.org/10.1038/s41598-025-22940-0","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41598-025-22940-0","pdf_url":"https://www.nature.com/articles/s41598-025-22940-0.pdf","source":{"id":"https://openalex.org/S196734849","display_name":"Scientific Reports","issn_l":"2045-2322","issn":["2045-2322"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-1","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientific Reports","raw_type":"journal-article"},{"id":"pmh:oai:europepmc.org:11417470","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12606185","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"Text"},{"id":"pmid:41219270","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41219270","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,"listed_in":[],"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":"Scientific reports","raw_type":"Journal Article"},{"id":"pmh:oai:discovery.dundee.ac.uk:openaire/32a67e0c-9414-4d7d-a6bc-d2968affc2bd","doi":null,"is_oa":true,"landing_page_url":"https://discovery.dundee.ac.uk/en/publications/32a67e0c-9414-4d7d-a6bc-d2968affc2bd","pdf_url":null,"source":{"id":"https://openalex.org/S4306400523","display_name":"Discovery Research Portal (University of Dundee)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I177639307","host_organization_name":"University of Dundee","host_organization_lineage":["https://openalex.org/I177639307"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Kim, J, Podlasek, A, Shidara, K, Liu, F, Alaa, A & Bernardo, D 2025, 'Limitations of large language models in clinical problem-solving arising from inflexible reasoning', Scientific Reports, vol. 15, 39426. https://doi.org/10.1038/s41598-025-22940-0","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:arXiv.org:2502.04381","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.04381","pdf_url":"https://arxiv.org/pdf/2502.04381","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:escholarship.org:ark:/13030/qt3mv5h5vs","doi":null,"is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/3mv5h5vs","pdf_url":"https://escholarship.org/content/qt3mv5h5vs/qt3mv5h5vs.pdf","source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"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":"Scientific Reports, vol 15, iss 1","raw_type":"article"},{"id":"pmh:oai:doaj.org/article:d43276798bfb41a6b30c67a7a8a2277c","doi":null,"is_oa":true,"landing_page_url":"https://doaj.org/article/d43276798bfb41a6b30c67a7a8a2277c","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,"listed_in":[],"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":"Scientific Reports, Vol 15, Iss 1, Pp 1-12 (2025)","raw_type":"article"},{"id":"doi:10.48550/arxiv.2502.04381","doi":"https://doi.org/10.48550/arxiv.2502.04381","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2502.04381","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1038/s41598-025-22940-0","doi":"https://doi.org/10.1038/s41598-025-22940-0","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41598-025-22940-0","pdf_url":"https://www.nature.com/articles/s41598-025-22940-0.pdf","source":{"id":"https://openalex.org/S196734849","display_name":"Scientific Reports","issn_l":"2045-2322","issn":["2045-2322"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-1","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientific Reports","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being","score":0.5683000087738037}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4407308237.pdf","grobid_xml":"https://content.openalex.org/works/W4407308237.grobid-xml"},"referenced_works_count":64,"referenced_works":["https://openalex.org/W1854828342","https://openalex.org/W2001598681","https://openalex.org/W2106578604","https://openalex.org/W2165160383","https://openalex.org/W2738724892","https://openalex.org/W2984217758","https://openalex.org/W2985039534","https://openalex.org/W3083410900","https://openalex.org/W3130133331","https://openalex.org/W4221161695","https://openalex.org/W4309674289","https://openalex.org/W4319460874","https://openalex.org/W4353091694","https://openalex.org/W4360836968","https://openalex.org/W4365143687","https://openalex.org/W4366327625","https://openalex.org/W4376632417","https://openalex.org/W4379769651","https://openalex.org/W4384154861","https://openalex.org/W4385495347","https://openalex.org/W4385714397","https://openalex.org/W4385767671","https://openalex.org/W4386721614","https://openalex.org/W4387561528","https://openalex.org/W4388725043","https://openalex.org/W4388787315","https://openalex.org/W4389116614","https://openalex.org/W4389431826","https://openalex.org/W4389520103","https://openalex.org/W4389520749","https://openalex.org/W4390041933","https://openalex.org/W4392359953","https://openalex.org/W4393160078","https://openalex.org/W4393386222","https://openalex.org/W4396802056","https://openalex.org/W4398183239","https://openalex.org/W4398859673","https://openalex.org/W4399401573","https://openalex.org/W4399774223","https://openalex.org/W4400199239","https://openalex.org/W4400324908","https://openalex.org/W4401042580","https://openalex.org/W4401043095","https://openalex.org/W4401863414","https://openalex.org/W4402670101","https://openalex.org/W4402703048","https://openalex.org/W4402748869","https://openalex.org/W4403122979","https://openalex.org/W4403229099","https://openalex.org/W4403324134","https://openalex.org/W4403362497","https://openalex.org/W4404330874","https://openalex.org/W4405173200","https://openalex.org/W4405766390","https://openalex.org/W4406371336","https://openalex.org/W4406614997","https://openalex.org/W4409363988","https://openalex.org/W4414838811","https://openalex.org/W4415796274","https://openalex.org/W4415798414","https://openalex.org/W4415798433","https://openalex.org/W4416045832","https://openalex.org/W7055216282","https://openalex.org/W7133241468"],"related_works":["https://openalex.org/W7125137563","https://openalex.org/W7162846872","https://openalex.org/W7153979526","https://openalex.org/W7126179102","https://openalex.org/W7166829865","https://openalex.org/W4415634189","https://openalex.org/W7165391806","https://openalex.org/W4415956903","https://openalex.org/W4414639542","https://openalex.org/W7219155282"],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"have":[4,23],"attained":[5],"human-level":[6],"accuracy":[7],"on":[8,115],"medical":[9,40,54,122,154],"question-answer":[10],"(QA)":[11],"benchmarks.":[12],"However,":[13],"their":[14,88,140,143],"limitations":[15],"in":[16,48,94,139,152,166],"navigating":[17],"clinical":[18,49,62,167],"scenarios":[19,65],"requiring":[20],"flexible":[21,95],"reasoning":[22,36,57,63,123,155],"recently":[24],"been":[25],"shown,":[26],"raising":[27],"concerns":[28],"about":[29],"the":[30,53,69,157],"robustness":[31],"and":[32,56,107,124],"generalizability":[33],"of":[34,73,120],"LLM":[35,45,80,153],"across":[37],"diverse,":[38],"real-world":[39],"tasks.":[41],"To":[42],"probe":[43],"potential":[44],"failure":[46,147],"modes":[47,148],"problem-solving,":[50],"we":[51],"present":[52],"abstraction":[55],"corpus":[58],"(mARC-QA).":[59],"mARC-QA":[60,151],"assesses":[61],"through":[64],"designed":[66],"to":[67,113,127,159],"exploit":[68],"Einstellung":[70],"effect-the":[71],"fixation":[72],"thought":[74],"arising":[75],"from":[76,87],"prior":[77],"experience,":[78],"targeting":[79],"inductive":[81],"biases":[82],"toward":[83],"inflexible":[84],"pattern":[85],"matching":[86],"training":[89],"data":[90],"rather":[91],"than":[92],"engaging":[93],"reasoning.":[96],"We":[97],"find":[98],"that":[99,135],"LLMs,":[100],"including":[101],"current":[102],"state-of-the-art":[103],"o1,":[104],"Gemini,":[105],"Claude,":[106],"DeepSeek":[108],"models,":[109],"perform":[110],"poorly":[111],"compared":[112],"physicians":[114],"mARC-QA,":[116],"often":[117],"demonstrating":[118],"lack":[119],"commonsense":[121],"a":[125],"propensity":[126],"hallucinate.":[128],"In":[129],"addition,":[130],"uncertainty":[131],"estimation":[132],"analyses":[133],"indicate":[134],"LLMs":[136],"exhibit":[137],"overconfidence":[138],"answers,":[141],"despite":[142],"limited":[144],"accuracy.":[145],"The":[146],"revealed":[149],"by":[150],"underscore":[156],"need":[158],"exercise":[160],"caution":[161],"when":[162],"deploying":[163],"these":[164],"models":[165],"settings.":[168]},"counts_by_year":[{"year":2026,"cited_by_count":95},{"year":2025,"cited_by_count":16}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-02-11T00:00:00"}
