{"id":"https://openalex.org/W7223226170","doi":"https://doi.org/10.31234/osf.io/pwbhy_v1","title":"Passing the Wrong Test: Model Size and Discriminant Validity in LLM-Based Psychological Assessment","display_name":"Passing the Wrong Test: Model Size and Discriminant Validity in LLM-Based Psychological Assessment","publication_year":2026,"publication_date":"2026-10-22","ids":{"openalex":"https://openalex.org/W7223226170","doi":"https://doi.org/10.31234/osf.io/pwbhy_v1"},"language":"en","primary_location":{"id":"doi:10.31234/osf.io/pwbhy_v1","doi":"https://doi.org/10.31234/osf.io/pwbhy_v1","is_oa":true,"landing_page_url":"https://doi.org/10.31234/osf.io/pwbhy_v1","pdf_url":null,"source":null,"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","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.31234/osf.io/pwbhy_v1","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025375066","display_name":"Yosef Sokol","orcid":"https://orcid.org/0000-0003-1536-853X","observed_orcids":["https://orcid.org/0000-0003-1536-853X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yosef Sokol","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-1536-853X","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074303374","display_name":"Amar D. Mandavia","orcid":"https://orcid.org/0000-0002-7166-7692","observed_orcids":["https://orcid.org/0000-0002-7166-7692"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Amar D. Mandavia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5090591509","display_name":"Jaclyn C. Kearns","orcid":"https://orcid.org/0000-0001-9246-9057","observed_orcids":["https://orcid.org/0000-0001-9246-9057"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jaclyn C. Kearns","raw_affiliation_strings":[],"raw_orcid":null,"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/T12488","display_name":"Mental Health via Writing","score":0.3513000011444092,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12488","display_name":"Mental Health via Writing","score":0.3513000011444092,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12848","display_name":"Psychological Testing and Assessment","score":0.2628999948501587,"subfield":{"id":"https://openalex.org/subfields/3202","display_name":"Applied Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10467","display_name":"Psychometric Methodologies and Testing","score":0.05429999902844429,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/discriminant-validity","display_name":"discriminant validity","score":0.9049999713897705},{"id":"https://openalex.org/keywords/convergent-validity","display_name":"convergent validity","score":0.8899999856948853},{"id":"https://openalex.org/keywords/psychological-assessment","display_name":"psychological assessment","score":0.7730000019073486},{"id":"https://openalex.org/keywords/clinical-interview","display_name":"clinical interview","score":0.5199999809265137},{"id":"https://openalex.org/keywords/model-size","display_name":"model size","score":0.8539999723434448},{"id":"https://openalex.org/keywords/parameter-count","display_name":"parameter count","score":0.8270000219345093},{"id":"https://openalex.org/keywords/open-weight-language-models","display_name":"open-weight language models","score":0.7379999756813049},{"id":"https://openalex.org/keywords/future-self-continuity","display_name":"future self-continuity","score":0.9399999976158142},{"id":"https://openalex.org/keywords/life-satisfaction","display_name":"life satisfaction","score":0.8560000061988831},{"id":"https://openalex.org/keywords/repeatability","display_name":"repeatability","score":0.7080000042915344},{"id":"https://openalex.org/keywords/gemma-4","display_name":"Gemma 4","score":0.7210000157356262},{"id":"https://openalex.org/keywords/llama-3-3","display_name":"Llama 3.3","score":0.9850000143051147}],"concepts":[{"id":"https://openalex.org/C120107772","wikidata":"https://www.wikidata.org/wiki/Q168554","display_name":"Discriminant validity","level":4,"score":0.767300009727478},{"id":"https://openalex.org/C78397625","wikidata":"https://www.wikidata.org/wiki/Q192487","display_name":"Discriminant","level":2,"score":0.6320000290870667},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.5566999912261963},{"id":"https://openalex.org/C121244757","wikidata":"https://www.wikidata.org/wiki/Q1783487","display_name":"Convergent validity","level":4,"score":0.551800012588501},{"id":"https://openalex.org/C41771347","wikidata":"https://www.wikidata.org/wiki/Q1228929","display_name":"Discriminant function analysis","level":2,"score":0.5296000242233276},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.5270000100135803},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.5041000247001648},{"id":"https://openalex.org/C64341305","wikidata":"https://www.wikidata.org/wiki/Q4919225","display_name":"Bivariate analysis","level":2,"score":0.49160000681877136},{"id":"https://openalex.org/C69738355","wikidata":"https://www.wikidata.org/wiki/Q1228929","display_name":"Linear discriminant analysis","level":2,"score":0.4876999855041504},{"id":"https://openalex.org/C49453240","wikidata":"https://www.wikidata.org/wiki/Q1592163","display_name":"Construct validity","level":3,"score":0.46239998936653137},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4221999943256378},{"id":"https://openalex.org/C20685875","wikidata":"https://www.wikidata.org/wiki/Q7239678","display_name":"Predictive validity","level":2,"score":0.37369999289512634},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.36010000109672546},{"id":"https://openalex.org/C18747219","wikidata":"https://www.wikidata.org/wiki/Q620994","display_name":"Standard error","level":2,"score":0.35350000858306885},{"id":"https://openalex.org/C116211729","wikidata":"https://www.wikidata.org/wiki/Q5372350","display_name":"Test validity","level":3,"score":0.3531999886035919},{"id":"https://openalex.org/C171606756","wikidata":"https://www.wikidata.org/wiki/Q506132","display_name":"Psychometrics","level":2,"score":0.3488999903202057},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.33980000019073486},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.321399986743927},{"id":"https://openalex.org/C2778571376","wikidata":"https://www.wikidata.org/wiki/Q1355821","display_name":"Frontier","level":2,"score":0.31189998984336853},{"id":"https://openalex.org/C174106493","wikidata":"https://www.wikidata.org/wiki/Q1057880","display_name":"External validity","level":2,"score":0.3116999864578247},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.31119999289512634},{"id":"https://openalex.org/C163515075","wikidata":"https://www.wikidata.org/wiki/Q873512","display_name":"Psychological testing","level":2,"score":0.2973000109195709},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.29260000586509705},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.28949999809265137},{"id":"https://openalex.org/C161584116","wikidata":"https://www.wikidata.org/wiki/Q1952580","display_name":"Multivariate statistics","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.28700000047683716},{"id":"https://openalex.org/C70364389","wikidata":"https://www.wikidata.org/wiki/Q18757","display_name":"Validity","level":3,"score":0.2809999883174896},{"id":"https://openalex.org/C27181475","wikidata":"https://www.wikidata.org/wiki/Q541014","display_name":"Cross-validation","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C154020017","wikidata":"https://www.wikidata.org/wiki/Q520171","display_name":"Repeatability","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C2780092901","wikidata":"https://www.wikidata.org/wiki/Q3433612","display_name":"Correlation coefficient","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C138496976","wikidata":"https://www.wikidata.org/wiki/Q175002","display_name":"Developmental psychology","level":1,"score":0.2621999979019165},{"id":"https://openalex.org/C90963130","wikidata":"https://www.wikidata.org/wiki/Q6015484","display_name":"Incremental validity","level":4,"score":0.2549999952316284},{"id":"https://openalex.org/C105054674","wikidata":"https://www.wikidata.org/wiki/Q3707381","display_name":"Mean difference","level":3,"score":0.25380000472068787},{"id":"https://openalex.org/C113238511","wikidata":"https://www.wikidata.org/wiki/Q1071612","display_name":"k-nearest neighbors algorithm","level":2,"score":0.2526000142097473},{"id":"https://openalex.org/C3019714060","wikidata":"https://www.wikidata.org/wiki/Q322514","display_name":"Validation test","level":4,"score":0.251800000667572},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.31234/osf.io/pwbhy_v1","doi":"https://doi.org/10.31234/osf.io/pwbhy_v1","is_oa":true,"landing_page_url":"https://doi.org/10.31234/osf.io/pwbhy_v1","pdf_url":null,"source":null,"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/pwbhy_v1","doi":"https://doi.org/10.31234/osf.io/pwbhy_v1","is_oa":true,"landing_page_url":"https://doi.org/10.31234/osf.io/pwbhy_v1","pdf_url":null,"source":null,"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7165797804","https://openalex.org/W7165131863","https://openalex.org/W7169570512","https://openalex.org/W7090873411","https://openalex.org/W7164528386","https://openalex.org/W7161590410","https://openalex.org/W7165360612","https://openalex.org/W7167841355","https://openalex.org/W7204498261","https://openalex.org/W7212856926"],"abstract_inverted_index":{"Validation":[0],"studies":[1],"of":[2,6,66,105,220],"zero-shot":[3],"language-model":[4],"scoring":[5],"psychological":[7],"interviews":[8,68],"often":[9],"rely":[10],"primarily":[11],"on":[12,192,227],"a":[13,18,24,30,137,156,181,218,232],"single":[14],"convergent":[15,107],"correlation":[16,26],"with":[17,89,109,136,144,155,168,172],"questionnaire":[19],"to":[20],"establish":[21],"validity.":[22],"However,":[23,95],"bivariate":[25],"cannot":[27],"reveal":[28],"whether":[29],"model":[31,90],"lacks":[32],"discriminant":[33,194,207,215],"validity,":[34,108],"agrees":[35],"poorly":[36],"in":[37,92,121],"absolute":[38,113],"terms,":[39],"produces":[40],"non-random":[41],"missing":[42],"scores,":[43],"or":[44],"scores":[45],"inconsistently.":[46],"We":[47],"evaluated":[48],"eight":[49,56],"open-weight":[50,98],"families":[51],"(1\u201370B":[52],"active":[53],"parameters)":[54],"and":[55,118],"commercial":[57],"frontier":[58,106,163,190],"models.":[59],"The":[60],"models":[61,99,129],"scored":[62],"the":[63,96,145,169,189],"same":[64],"sets":[65],"clinical":[67],"(Study":[69],"1:":[70],"suicide":[71],"recovery,":[72],"n":[73,80],"=":[74,81],"149;":[75],"Study":[76,122,125],"2:":[77],"future":[78],"self-continuity,":[79],"164)":[82],"across":[83,236],"52":[84],"configurations.":[85],"Convergent":[86],"validity":[87,195,208,216],"improves":[88],"size":[91],"both":[93],"studies.":[94],"standard":[97,127,235],"tested":[100],"achieve":[101],"only":[102],"about":[103],"three-quarters":[104],"11-fold":[110],"greater":[111,206],"mean":[112],"bias,":[114],"more":[115,166],"format":[116],"failures,":[117],"lower":[119],"repeatability":[120],"1.":[123],"In":[124],"2,":[126],"open":[128],"(\u2264":[130],"27B)":[131],"are":[132],"as":[133,143],"strongly":[134,154,167],"correlated":[135],"closely":[138],"related":[139],"construct":[140],"(suicide":[141],"recovery)":[142],"target":[146,170],"(mean":[147,175],"difference":[148,176],"\u22120.014),":[149],"although":[150],"they":[151],"correlate":[152,165],"less":[153],"distal":[157],"neighbor":[158,174],"(life":[159],"satisfaction).":[160],"All":[161],"six":[162],"generations":[164],"than":[171,209],"either":[173],"from":[177],"recovery":[178],"+0.117).":[179],"On":[180],"local":[182],"workstation,":[183],"Gemma":[184,210],"4":[185,211],"31B":[186],"is":[187,217],"within":[188],"range":[191],"all":[193],"indices,":[196],"outperforming":[197],"its":[198],"similar-sized":[199],"predecessor.":[200],"Llama":[201],"3.3":[202],"70B":[203],"shows":[204],"no":[205],"31B,":[212],"suggesting":[213],"that":[214],"function":[219],"release,":[221],"not":[222],"parameter":[223],"count":[224],"alone.":[225],"Based":[226],"these":[228],"findings,":[229],"we":[230],"suggest":[231],"minimum":[233],"validation":[234],"five":[237],"domains.":[238]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-10-23T00:00:00"}
