{"id":"https://openalex.org/W7220709809","doi":"https://doi.org/10.31234/osf.io/msp9f_v1","title":"Evaluating Large Language Models on Clinical Risk Judgement: An Example from Alcohol Use Disorder","display_name":"Evaluating Large Language Models on Clinical Risk Judgement: An Example from Alcohol Use Disorder","publication_year":2026,"publication_date":"2026-10-07","ids":{"openalex":"https://openalex.org/W7220709809","doi":"https://doi.org/10.31234/osf.io/msp9f_v1"},"language":"en","primary_location":{"id":"doi:10.31234/osf.io/msp9f_v1","doi":"https://doi.org/10.31234/osf.io/msp9f_v1","is_oa":true,"landing_page_url":"https://doi.org/10.31234/osf.io/msp9f_v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306401687","display_name":"PsyArXiv (OSF Preprints)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2799848540","host_organization_name":"Center for Open Science","host_organization_lineage":["https://openalex.org/I2799848540"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.31234/osf.io/msp9f_v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008260319","display_name":"Charles M. Bolton","orcid":"https://orcid.org/0009-0003-2443-6554","observed_orcids":["https://orcid.org/0009-0003-2443-6554"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Charles M. Bolton","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0003-2443-6554","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5157725553","display_name":"Kiwon Song","orcid":"https://orcid.org/0009-0004-7014-1324","observed_orcids":["https://orcid.org/0009-0004-7014-1324"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kiwon Song","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0004-7014-1324","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5157776622","display_name":"Katelyn A. Wasson","orcid":"https://orcid.org/0009-0001-0125-7348","observed_orcids":["https://orcid.org/0009-0001-0125-7348"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Katelyn A Wasson","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0001-0125-7348","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021103186","display_name":"Clintin P. Davis\u2010Stober","orcid":"https://orcid.org/0000-0002-6836-6979","observed_orcids":["https://orcid.org/0000-0002-6836-6979"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Clintin P Davis-Stober","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5079193085","display_name":"Konstantina Sokratous","orcid":"https://orcid.org/0000-0003-4489-5494","observed_orcids":["https://orcid.org/0000-0003-4489-5494"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Konstantina Sokratous","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-4489-5494","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.9063000082969666,"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":0.9063000082969666,"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/T11396","display_name":"Artificial Intelligence in Healthcare","score":0.044599998742341995,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.01769999973475933,"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":0.9990000128746033},{"id":"https://openalex.org/keywords/alcoholism","display_name":"alcoholism","score":0.8730000257492065},{"id":"https://openalex.org/keywords/clinical-risk-assessment","display_name":"clinical risk assessment","score":0.824999988079071},{"id":"https://openalex.org/keywords/risk-judgment","display_name":"risk judgment","score":0.5709999799728394},{"id":"https://openalex.org/keywords/dsm-5-criteria","display_name":"DSM-5 diagnostic criteria","score":0.8259999752044678},{"id":"https://openalex.org/keywords/demographic-bias","display_name":"demographic bias","score":0.7730000019073486},{"id":"https://openalex.org/keywords/clinical-vignettes","display_name":"clinical vignettes","score":0.7649999856948853},{"id":"https://openalex.org/keywords/nesarc-iii","display_name":"NESARC-III","score":0.7540000081062317},{"id":"https://openalex.org/keywords/gpt-5-5","display_name":"GPT-5.5","score":0.8100000023841858},{"id":"https://openalex.org/keywords/model-evaluation","display_name":"model evaluation","score":0.367000013589859},{"id":"https://openalex.org/keywords/clinical-decision-support","display_name":"clinical decision support","score":0.49799999594688416}],"concepts":[{"id":"https://openalex.org/C107130276","wikidata":"https://www.wikidata.org/wiki/Q133805","display_name":"Epidemiology","level":2,"score":0.6485999822616577},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5971999764442444},{"id":"https://openalex.org/C2779442783","wikidata":"https://www.wikidata.org/wiki/Q15326","display_name":"Alcohol use disorder","level":3,"score":0.574400007724762},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.501800000667572},{"id":"https://openalex.org/C7493553","wikidata":"https://www.wikidata.org/wiki/Q1520777","display_name":"Certainty","level":2,"score":0.4277999997138977},{"id":"https://openalex.org/C166735990","wikidata":"https://www.wikidata.org/wiki/Q1750812","display_name":"Human factors and ergonomics","level":3,"score":0.41839998960494995},{"id":"https://openalex.org/C3017944768","wikidata":"https://www.wikidata.org/wiki/Q1450463","display_name":"Poison control","level":2,"score":0.4120999872684479},{"id":"https://openalex.org/C12174686","wikidata":"https://www.wikidata.org/wiki/Q1058438","display_name":"Risk assessment","level":2,"score":0.38749998807907104},{"id":"https://openalex.org/C190385971","wikidata":"https://www.wikidata.org/wiki/Q373494","display_name":"Injury prevention","level":3,"score":0.3840000033378601},{"id":"https://openalex.org/C70410870","wikidata":"https://www.wikidata.org/wiki/Q199906","display_name":"Clinical psychology","level":1,"score":0.38089999556541443},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.3709000051021576},{"id":"https://openalex.org/C118552586","wikidata":"https://www.wikidata.org/wiki/Q7867","display_name":"Psychiatry","level":1,"score":0.36809998750686646},{"id":"https://openalex.org/C526869908","wikidata":"https://www.wikidata.org/wiki/Q3298118","display_name":"Suicide prevention","level":3,"score":0.36640000343322754},{"id":"https://openalex.org/C3020000205","wikidata":"https://www.wikidata.org/wiki/Q2412849","display_name":"Narrative review","level":2,"score":0.3345000147819519},{"id":"https://openalex.org/C50440223","wikidata":"https://www.wikidata.org/wiki/Q1475848","display_name":"Risk factor","level":2,"score":0.3057999908924103},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.2838999927043915},{"id":"https://openalex.org/C110379092","wikidata":"https://www.wikidata.org/wiki/Q1571836","display_name":"Social environment","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C138816342","wikidata":"https://www.wikidata.org/wiki/Q189603","display_name":"Public health","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C2777725460","wikidata":"https://www.wikidata.org/wiki/Q7256237","display_name":"Psychiatric epidemiology","level":3,"score":0.27239999175071716},{"id":"https://openalex.org/C187155963","wikidata":"https://www.wikidata.org/wiki/Q629029","display_name":"Occupational safety and health","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C162118730","wikidata":"https://www.wikidata.org/wiki/Q1128453","display_name":"Actuarial science","level":1,"score":0.2547999918460846}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.31234/osf.io/msp9f_v1","doi":"https://doi.org/10.31234/osf.io/msp9f_v1","is_oa":true,"landing_page_url":"https://doi.org/10.31234/osf.io/msp9f_v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306401687","display_name":"PsyArXiv (OSF Preprints)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2799848540","host_organization_name":"Center for Open Science","host_organization_lineage":["https://openalex.org/I2799848540"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.31234/osf.io/msp9f_v1","doi":"https://doi.org/10.31234/osf.io/msp9f_v1","is_oa":true,"landing_page_url":"https://doi.org/10.31234/osf.io/msp9f_v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306401687","display_name":"PsyArXiv (OSF Preprints)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2799848540","host_organization_name":"Center for Open Science","host_organization_lineage":["https://openalex.org/I2799848540"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"sustainable_development_goals":[{"display_name":"Good health and well-being","score":0.98580002784729,"id":"https://metadata.un.org/sdg/3"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4409855004","https://openalex.org/W7154670927","https://openalex.org/W7196962902","https://openalex.org/W7213240961","https://openalex.org/W4411589031","https://openalex.org/W7156315081","https://openalex.org/W4416073034","https://openalex.org/W4409351794","https://openalex.org/W4417146151","https://openalex.org/W7161473605"],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"are":[4],"being":[5],"explored":[6],"for":[7],"medical":[8],"risk":[9,32,113],"assessment,":[10],"yet":[11],"performance":[12],"on":[13,83],"standardized":[14],"benchmarks":[15,76],"does":[16],"not":[17],"necessarily":[18],"establish":[19],"clinical":[20,42,68,129],"competency.":[21],"The":[22],"present":[23],"study":[24],"evaluated":[25],"whether":[26],"LLM-generated":[27],"Alcohol":[28,84],"Use":[29],"Disorder":[30],"(AUD)":[31],"judgments":[33,184],"aligned":[34],"with":[35,63,74,147],"epidemiological":[36,75],"evidence":[37],"and":[38,43,50,66,85,118,128,170,180],"remained":[39],"consistent":[40],"as":[41,138],"demographic":[44,59,64,126],"context":[45],"changed.":[46,141],"Three":[47,89],"LLMs\u2014GPT-5.5,":[48],"LLaMA-2-70B,":[49],"MEDITRON-70B\u2014completed":[51],"four":[52],"pairwise-comparison":[53],"experiments":[54],"involving":[55],"DSM-5":[56],"AUD":[57,106,112],"criteria,":[58],"characteristics,":[60,65],"criteria":[61],"paired":[62],"narrative":[67],"vignettes.":[69],"LLM-implied":[70],"rankings":[71,132],"were":[72],"compared":[73],"derived":[77],"from":[78],"the":[79,97,100,105,116,172,176],"National":[80],"Epidemiological":[81],"Survey":[82],"Related":[86],"Conditions,":[87],"Wave":[88],"(NESARC-III).":[90],"Our":[91],"results":[92],"show":[93],"that":[94],"none":[95],"of":[96,104,120,174,182],"LLMs":[98,142],"reproduced":[99],"implied":[101],"severity":[102],"ordering":[103],"criteria.":[107],"Demographic":[108,131],"cues":[109],"consistently":[110],"influenced":[111],"judgments,":[114],"although":[115],"direction":[117],"magnitude":[119],"these":[121],"effects":[122],"varied":[123],"across":[124],"LLMs,":[125],"attributes,":[127],"contexts.":[130],"also":[133],"showed":[134],"only":[135],"partial":[136],"stability":[137],"contextual":[139],"information":[140],"differed":[143],"substantially":[144,150],"in":[145,165],"decisiveness,":[146],"GPT-5.5":[148],"assigning":[149],"higher":[151],"probability":[152],"to":[153],"selected":[154],"responses":[155],"than":[156],"LLaMA-2-70B":[157],"or":[158],"MEDITRON-70B.":[159],"These":[160],"findings":[161],"demonstrate":[162],"a":[163],"gap":[164],"current":[166],"LLM":[167,183],"risk-assessment":[168],"capabilities":[169],"highlight":[171],"importance":[173],"evaluating":[175],"direction,":[177],"magnitude,":[178],"stability,":[179],"certainty":[181],"alongside":[185],"accuracy.":[186]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-10-07T00:00:00"}