{"id":"https://openalex.org/W7166809719","doi":"https://doi.org/10.18653/v1/2026.clpsych-1.7","title":"The Reliability Illusion in Synthetic Patients: Psychometric Misalignment of Open-weight LLMs on PHQ-9 and GAD-7","display_name":"The Reliability Illusion in Synthetic Patients: Psychometric Misalignment of Open-weight LLMs on PHQ-9 and GAD-7","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166809719","doi":"https://doi.org/10.18653/v1/2026.clpsych-1.7"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.clpsych-1.7","doi":"https://doi.org/10.18653/v1/2026.clpsych-1.7","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.clpsych-1.7","pdf_url":"https://aclanthology.org/2026.clpsych-1.7.pdf","source":{"id":"https://openalex.org/S7407087913","display_name":"Workshop on Computational Linguistics and Clinical Psychology (CLPsych)","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":"conference"},"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 10th Workshop on Computational Linguistics and Clinical Psychology (CLPsych 2026)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.clpsych-1.7.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139786357","display_name":"Qian Shen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qian Shen","raw_affiliation_strings":["University of Florida"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Florida","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139744083","display_name":"Yu Han","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I368840534","display_name":"University of Mississippi","ror":"https://ror.org/02teq1165","country_code":"US","type":"education","lineage":["https://openalex.org/I368840534","https://openalex.org/I4210141039"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Han","raw_affiliation_strings":["University of Mississippi"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Mississippi","institution_ids":["https://openalex.org/I368840534"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.45603768,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"88","last_page":"99"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10467","display_name":"Psychometric Methodologies and Testing","score":0.9110999703407288,"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"}},"topics":[{"id":"https://openalex.org/T10467","display_name":"Psychometric Methodologies and Testing","score":0.9110999703407288,"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"}},{"id":"https://openalex.org/T10853","display_name":"Anxiety, Depression, Psychometrics, Treatment, Cognitive Processes","score":0.04450000077486038,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive 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/T13283","display_name":"Mental Health Research Topics","score":0.007799999788403511,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/open-weight-large-language-models","display_name":"open-weight large language models","score":0.8880000114440918},{"id":"https://openalex.org/keywords/phq-9","display_name":"PHQ-9","score":0.9240000247955322},{"id":"https://openalex.org/keywords/gad-7","display_name":"GAD-7","score":1.0},{"id":"https://openalex.org/keywords/depression-screening","display_name":"depression screening","score":0.8399999737739563},{"id":"https://openalex.org/keywords/anxiety-screening","display_name":"anxiety screening","score":0.9950000047683716},{"id":"https://openalex.org/keywords/measurement-invariance","display_name":"measurement invariance","score":0.8429999947547913},{"id":"https://openalex.org/keywords/differential-item-functioning","display_name":"differential item functioning","score":0.9890000224113464},{"id":"https://openalex.org/keywords/factor-structure","display_name":"factor structure","score":0.8429999947547913},{"id":"https://openalex.org/keywords/prompt-sensitivity","display_name":"prompt sensitivity","score":0.5189999938011169},{"id":"https://openalex.org/keywords/reliability-statistics","display_name":"reliability statistics","score":0.3230000138282776},{"id":"https://openalex.org/keywords/stereotype-bias","display_name":"stereotype bias","score":0.3709999918937683},{"id":"https://openalex.org/keywords/mental-health-assessment","display_name":"mental health assessment","score":0.6000000238418579}],"concepts":[{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.6708999872207642},{"id":"https://openalex.org/C184047640","wikidata":"https://www.wikidata.org/wiki/Q182593","display_name":"Illusion","level":2,"score":0.414000004529953},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.41130000352859497},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.40799999237060547},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.39169999957084656},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.36399999260902405},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3465000092983246},{"id":"https://openalex.org/C75630572","wikidata":"https://www.wikidata.org/wiki/Q538904","display_name":"Applied psychology","level":1,"score":0.33399999141693115},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.3206999897956848},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2824000120162964},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2662000060081482},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2621000111103058}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.clpsych-1.7","doi":"https://doi.org/10.18653/v1/2026.clpsych-1.7","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.clpsych-1.7","pdf_url":"https://aclanthology.org/2026.clpsych-1.7.pdf","source":{"id":"https://openalex.org/S7407087913","display_name":"Workshop on Computational Linguistics and Clinical Psychology (CLPsych)","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":"conference"},"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 10th Workshop on Computational Linguistics and Clinical Psychology (CLPsych 2026)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.clpsych-1.7","doi":"https://doi.org/10.18653/v1/2026.clpsych-1.7","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.clpsych-1.7","pdf_url":"https://aclanthology.org/2026.clpsych-1.7.pdf","source":{"id":"https://openalex.org/S7407087913","display_name":"Workshop on Computational Linguistics and Clinical Psychology (CLPsych)","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":"conference"},"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 10th Workshop on Computational Linguistics and Clinical Psychology (CLPsych 2026)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.8560000061988831,"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166809719.pdf","grobid_xml":"https://content.openalex.org/works/W7166809719.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7212093641","https://openalex.org/W7213924229","https://openalex.org/W7123289395","https://openalex.org/W7203681875","https://openalex.org/W4414986010","https://openalex.org/W7168615648","https://openalex.org/W4417010789","https://openalex.org/W7166812445","https://openalex.org/W7204437025","https://openalex.org/W4416788674"],"abstract_inverted_index":{"Globally,":[0],"the":[1,11,42,59,91],"incidence":[2],"of":[3,13,33,44,94],"depression":[4],"and":[5,10,35,48,61,67,85,97,123,137],"anxiety":[6],"continues":[7],"to":[8,29,57,71,102,125],"rise,":[9],"importance":[12],"mental":[14],"health":[15],"assessment":[16],"scales":[17],"as":[18],"diagnostic":[19],"tools":[20],"has":[21],"grown":[22],"accordingly.Researchers":[23],"are":[24],"increasingly":[25],"employing":[26],"generative":[27],"AI":[28],"produce":[30],"large":[31],"volumes":[32],"items":[34],"entire":[36],"scales,":[37],"which":[38],"in":[39],"turn":[40],"elevates":[41],"costs":[43],"validating":[45],"their":[46],"reliability":[47],"validity.In":[49],"this":[50],"study,":[51],"we":[52,89],"used":[53],"four":[54],"open-weight":[55,111],"LLMs":[56,112],"complete":[58],"GAD-7":[60],"PHQ-9,":[62],"varying":[63],"prompts,":[64],"sampling":[65],"temperature,":[66],"dynamic":[68],"contextual":[69],"scenarios":[70],"emulate":[72],"realistic":[73],"human":[74,103,131],"response":[75],"patterns.Using":[76],"multi-group":[77],"confirmatory":[78],"factor":[79,92],"analysis,":[80],"differential":[81,134],"item":[82,135],"functioning":[83,136],"analyses,":[84],"other":[86],"psychometric":[87],"methods,":[88],"evaluate":[90],"structure":[93],"LLM-generated":[95],"responses":[96],"assess":[98],"measurement":[99,128],"invariance":[100,129],"relative":[101],"responses.Our":[104],"findings":[105],"reveal":[106],"a":[107],"critical":[108],"paradox:":[109],"although":[110],"exhibit":[113],"exceptionally":[114],"high":[115],"internal":[116],"consistency,":[117],"they":[118],"demonstrate":[119],"severe":[120],"structural":[121],"mismatch":[122],"fail":[124],"achieve":[126],"scalar":[127],"against":[130],"baselines.Furthermore,":[132],"pervasive":[133],"extreme":[138],"prompt":[139],"fragility":[140],"indicate":[141],"that":[142],"these":[143],"models":[144],"rely":[145],"on":[146],"superficial,":[147],"stereotype-driven":[148],"semantic":[149],"matching":[150],"rather":[151],"than":[152],"simulating":[153],"stable":[154],"latent":[155],"psychological":[156],"dynamics.":[157]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-07-02T00:00:00"}