{"id":"https://openalex.org/W4395064833","doi":"https://doi.org/10.1145/3626772.3657882","title":"Beyond Accuracy: Investigating Error Types in GPT-4 Responses to USMLE Questions","display_name":"Beyond Accuracy: Investigating Error Types in GPT-4 Responses to USMLE Questions","publication_year":2024,"publication_date":"2024-07-10","ids":{"openalex":"https://openalex.org/W4395064833","doi":"https://doi.org/10.1145/3626772.3657882"},"language":"en","primary_location":{"id":"doi:10.1145/3626772.3657882","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626772.3657882","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3626772.3657882","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010730449","display_name":"Soumyadeep Roy","orcid":"https://orcid.org/0000-0001-7269-2163"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Soumyadeep Roy","raw_affiliation_strings":["IIT Kharagpur, Kharagpur, India"],"affiliations":[{"raw_affiliation_string":"IIT Kharagpur, Kharagpur, India","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016242562","display_name":"Aparup Khatua","orcid":"https://orcid.org/0000-0001-8235-1637"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]},{"id":"https://openalex.org/I4210111179","display_name":"Michigan United","ror":"https://ror.org/0291ys696","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210111179"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aparup Khatua","raw_affiliation_strings":["University of Michigan, Ann Arbor, USA","University of Michigan Ann Arbor, United States"],"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, USA","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"University of Michigan Ann Arbor, United States","institution_ids":["https://openalex.org/I4210111179","https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5095848434","display_name":"Fatemeh Ghoochani","orcid":"https://orcid.org/0009-0003-1814-8513"},"institutions":[{"id":"https://openalex.org/I4210136150","display_name":"L3S Research Center","ror":"https://ror.org/039t4wk02","country_code":"DE","type":"facility","lineage":["https://openalex.org/I114112103","https://openalex.org/I4210136150","https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Fatemeh Ghoochani","raw_affiliation_strings":["L3S Research Center, Hannover, Germany"],"affiliations":[{"raw_affiliation_string":"L3S Research Center, Hannover, Germany","institution_ids":["https://openalex.org/I4210136150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5095848435","display_name":"Uwe Hadler","orcid":"https://orcid.org/0009-0003-8122-7572"},"institutions":[{"id":"https://openalex.org/I4210136150","display_name":"L3S Research Center","ror":"https://ror.org/039t4wk02","country_code":"DE","type":"facility","lineage":["https://openalex.org/I114112103","https://openalex.org/I4210136150","https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Uwe Hadler","raw_affiliation_strings":["L3S Research Center, Hannover, Germany"],"affiliations":[{"raw_affiliation_string":"L3S Research Center, Hannover, Germany","institution_ids":["https://openalex.org/I4210136150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074427964","display_name":"Wolfgang Nejdl","orcid":"https://orcid.org/0000-0003-3374-2193"},"institutions":[{"id":"https://openalex.org/I4210136150","display_name":"L3S Research Center","ror":"https://ror.org/039t4wk02","country_code":"DE","type":"facility","lineage":["https://openalex.org/I114112103","https://openalex.org/I4210136150","https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Wolfgang Nejdl","raw_affiliation_strings":["L3S Research Center, Hannover, Germany"],"affiliations":[{"raw_affiliation_string":"L3S Research Center, Hannover, Germany","institution_ids":["https://openalex.org/I4210136150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073812421","display_name":"Niloy Ganguly","orcid":"https://orcid.org/0000-0002-3967-186X"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Niloy Ganguly","raw_affiliation_strings":["IIT Kharagpur, Kharagpur, India"],"affiliations":[{"raw_affiliation_string":"IIT Kharagpur, Kharagpur, India","institution_ids":["https://openalex.org/I145894827"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5010730449"],"corresponding_institution_ids":["https://openalex.org/I145894827"],"apc_list":null,"apc_paid":null,"fwci":3.6636,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":{"value":0.93670672,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1073","last_page":"1082"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12574","display_name":"Clinical Reasoning and Diagnostic Skills","score":0.9901000261306763,"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/T10028","display_name":"Topic Modeling","score":0.9783999919891357,"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/computer-science","display_name":"Computer science","score":0.5953328609466553}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5953328609466553}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3626772.3657882","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626772.3657882","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2404.13307","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2404.13307","pdf_url":"https://arxiv.org/pdf/2404.13307","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":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3626772.3657882","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626772.3657882","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G352791218","display_name":null,"funder_award_id":"(BMBF)","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"},{"id":"https://openalex.org/G367552324","display_name":null,"funder_award_id":"01DD20003","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"},{"id":"https://openalex.org/G6955755495","display_name":null,"funder_award_id":"Germany","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"}],"funders":[{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"},{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"},{"id":"https://openalex.org/F4320325536","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2098201295","https://openalex.org/W2970482702","https://openalex.org/W2995225687","https://openalex.org/W3026298482","https://openalex.org/W3099977667","https://openalex.org/W3100468923","https://openalex.org/W3162922479","https://openalex.org/W4221143046","https://openalex.org/W4282570892","https://openalex.org/W4284711125","https://openalex.org/W4285242550","https://openalex.org/W4285807172","https://openalex.org/W4380730209","https://openalex.org/W4382318396","https://openalex.org/W4384071683","https://openalex.org/W4385570634","https://openalex.org/W4385572910","https://openalex.org/W4388725043","https://openalex.org/W4389520696","https://openalex.org/W4389958742","https://openalex.org/W4391170193","https://openalex.org/W4392359953","https://openalex.org/W4393160302","https://openalex.org/W4400921803","https://openalex.org/W4404534210"],"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/W4395014643"],"abstract_inverted_index":{"GPT-4":[0,30,56,75,82,111],"demonstrates":[1],"high":[2],"accuracy":[3,11],"in":[4,233],"medical":[5,72,131,207,212,215,242],"QA":[6],"tasks,":[7],"leading":[8],"with":[9,71],"an":[10],"of":[12,23,143,175,195,237],"86.70%,":[13],"followed":[14],"by":[15,55,185,187],"Med-PaLM":[16],"2":[17],"at":[18,149,249],"86.50%.":[19],"However,":[20],"around":[21],"14%":[22],"errors":[24],"remain.":[25],"Additionally,":[26],"current":[27],"works":[28],"use":[29],"to":[31,89,161,201,239],"only":[32],"predict":[33],"the":[34,49,90,113,124,163,166,193,220,235,246],"correct":[35,83],"option":[36],"without":[37],"providing":[38],"any":[39,46],"explanation":[40],"and":[41,52,85,128,156,214],"thus":[42],"do":[43],"not":[44],"provide":[45,211],"insight":[47],"into":[48],"thinking":[50],"process":[51],"reasoning":[53],"used":[54],"or":[57],"other":[58],"LLMs.":[59],"Therefore,":[60],"we":[61],"introduce":[62],"a":[63,119,135,150,158,172,182],"new":[64],"domain-specific":[65],"error":[66],"taxonomy":[67],"derived":[68],"from":[69,110],"collaboration":[70],"students.":[73],"Our":[74],"USMLE":[76],"Error":[77],"(G4UE)":[78],"dataset":[79],"comprises":[80],"4153":[81],"responses":[84,88,99,178],"919":[86,145],"incorrect":[87,146,177,202],"United":[91],"States":[92],"Medical":[93],"Licensing":[94],"Examination":[95],"(USMLE)":[96],"respectively.":[97],"These":[98],"are":[100],"quite":[101],"long":[102],"(258":[103],"words":[104],"on":[105,192],"average),":[106],"containing":[107],"detailed":[108],"explanations":[109,197],"justifying":[112],"selected":[114],"option.":[115],"We":[116,139,209,227,244],"then":[117],"launch":[118],"large-scale":[120],"annotation":[121,126],"study":[122],"using":[123,219],"Potato":[125],"platform":[127],"recruit":[129],"44":[130],"experts":[132],"through":[133],"Prolific,":[134],"well-known":[136],"crowdsourcing":[137],"platform.":[138],"annotated":[140,170],"300":[141],"out":[142],"these":[144],"data":[147,225],"points":[148],"granular":[151],"level":[152],"for":[153,223],"different":[154],"classes":[155],"created":[157],"multi-label":[159],"span":[160],"identify":[162],"reasons":[164],"behind":[165],"error.":[167],"In":[168],"our":[169],"dataset,":[171],"substantial":[173],"portion":[174],"GPT-4's":[176],"is":[179],"categorized":[180],"as":[181],"\"Reasonable":[183],"response":[184],"GPT-4,\"":[186],"annotators.":[188],"This":[189],"sheds":[190],"light":[191],"challenge":[194],"discerning":[196],"that":[198,229],"may":[199],"lead":[200],"options,":[203],"even":[204],"among":[205],"trained":[206],"professionals.":[208],"also":[210],"concepts":[213],"semantic":[216],"predications":[217],"extracted":[218],"SemRep":[221],"tool":[222],"every":[224],"point.":[226],"believe":[228],"it":[230],"will":[231],"aid":[232],"evaluating":[234],"ability":[236],"LLMs":[238],"answer":[240],"complex":[241],"questions.":[243],"make":[245],"resources":[247],"available":[248],"https://github.com/roysoumya/usmle-gpt4-error-taxonomy.":[250]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2024-04-24T00:00:00"}