{"id":"https://openalex.org/W7203671971","doi":"https://doi.org/10.48550/arxiv.2608.15630","title":"Do Assessment Instruments Measure the Same Thing for Humans and LLMs? A Latent Structure Analysis","display_name":"Do Assessment Instruments Measure the Same Thing for Humans and LLMs? A Latent Structure Analysis","publication_year":2026,"publication_date":"2026-08-16","ids":{"openalex":"https://openalex.org/W7203671971","doi":"https://doi.org/10.48550/arxiv.2608.15630"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.15630","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.15630","pdf_url":"https://arxiv.org/pdf/2608.15630","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-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.15630","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052266289","display_name":"Alona Strugatski","orcid":"https://orcid.org/0009-0001-3282-7067","observed_orcids":["https://orcid.org/0009-0001-3282-7067"]},"institutions":[{"id":"https://openalex.org/I53964585","display_name":"Weizmann Institute of Science","ror":"https://ror.org/0316ej306","country_code":"IL","type":"education","lineage":["https://openalex.org/I53964585"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Strugatski, Alona","raw_affiliation_strings":["Weizmann Institute of Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Weizmann Institute of Science","institution_ids":["https://openalex.org/I53964585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139620365","display_name":"Licol Zeinfeld","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I53964585","display_name":"Weizmann Institute of Science","ror":"https://ror.org/0316ej306","country_code":"IL","type":"education","lineage":["https://openalex.org/I53964585"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Zeinfeld, Licol","raw_affiliation_strings":["Weizmann Institute of Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Weizmann Institute of Science","institution_ids":["https://openalex.org/I53964585"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059416730","display_name":"Giora Alexandron","orcid":"https://orcid.org/0000-0003-2676-6912","observed_orcids":["https://orcid.org/0000-0003-2676-6912"]},"institutions":[{"id":"https://openalex.org/I53964585","display_name":"Weizmann Institute of Science","ror":"https://ror.org/0316ej306","country_code":"IL","type":"education","lineage":["https://openalex.org/I53964585"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Alexandron, Giora","raw_affiliation_strings":["Weizmann Institute of Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Weizmann Institute of Science","institution_ids":["https://openalex.org/I53964585"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I53964585"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"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/T10467","display_name":"Psychometric Methodologies and Testing","score":0.9398999810218811,"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":0.9398999810218811,"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/T12884","display_name":"Educational Assessment and Pedagogy","score":0.012299999594688416,"subfield":{"id":"https://openalex.org/subfields/3304","display_name":"Education"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T14414","display_name":"Artificial Intelligence in Education","score":0.010599999688565731,"subfield":{"id":"https://openalex.org/subfields/3304","display_name":"Education"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9950000047683716},{"id":"https://openalex.org/keywords/assessment-validity","display_name":"assessment validity","score":0.6000000238418579},{"id":"https://openalex.org/keywords/latent-structure","display_name":"latent structure","score":0.5509999990463257},{"id":"https://openalex.org/keywords/factor-congruence","display_name":"factor congruence","score":0.8930000066757202},{"id":"https://openalex.org/keywords/standardized-testing","display_name":"standardized testing","score":0.5389999747276306},{"id":"https://openalex.org/keywords/high-school-chemistry","display_name":"high school chemistry","score":0.628000020980835},{"id":"https://openalex.org/keywords/quantitative-reasoning","display_name":"quantitative reasoning","score":0.8370000123977661},{"id":"https://openalex.org/keywords/college-entrance-examination","display_name":"college entrance examination","score":0.7950000166893005},{"id":"https://openalex.org/keywords/ai-evaluation","display_name":"AI evaluation","score":0.5799999833106995},{"id":"https://openalex.org/keywords/score-interpretation","display_name":"score interpretation","score":0.42800000309944153},{"id":"https://openalex.org/keywords/human-llm-comparison","display_name":"human-LLM comparison","score":0.6050000190734863}],"concepts":[{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.608299970626831},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.5285000205039978},{"id":"https://openalex.org/C165957694","wikidata":"https://www.wikidata.org/wiki/Q5421350","display_name":"Exploratory factor analysis","level":3,"score":0.524399995803833},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.4699000120162964},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.46480000019073486},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4332999885082245},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41269999742507935},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.35350000858306885},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.35179999470710754},{"id":"https://openalex.org/C19875794","wikidata":"https://www.wikidata.org/wiki/Q1207340","display_name":"Item response theory","level":3,"score":0.3504999876022339},{"id":"https://openalex.org/C20685875","wikidata":"https://www.wikidata.org/wiki/Q7239678","display_name":"Predictive validity","level":2,"score":0.3499000072479248},{"id":"https://openalex.org/C65965080","wikidata":"https://www.wikidata.org/wiki/Q1806885","display_name":"Latent variable model","level":3,"score":0.3361000120639801},{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.3310000002384186},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32580000162124634},{"id":"https://openalex.org/C171606756","wikidata":"https://www.wikidata.org/wiki/Q506132","display_name":"Psychometrics","level":2,"score":0.32109999656677246},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3176000118255615},{"id":"https://openalex.org/C116211729","wikidata":"https://www.wikidata.org/wiki/Q5372350","display_name":"Test validity","level":3,"score":0.29670000076293945},{"id":"https://openalex.org/C75630572","wikidata":"https://www.wikidata.org/wiki/Q538904","display_name":"Applied psychology","level":1,"score":0.2962000072002411},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.29319998621940613},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.29319998621940613},{"id":"https://openalex.org/C10879293","wikidata":"https://www.wikidata.org/wiki/Q726474","display_name":"Factor analysis","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.26739999651908875},{"id":"https://openalex.org/C100521375","wikidata":"https://www.wikidata.org/wiki/Q2015382","display_name":"Competence (human resources)","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.26080000400543213},{"id":"https://openalex.org/C2776517306","wikidata":"https://www.wikidata.org/wiki/Q29017317","display_name":"Similarity measure","level":2,"score":0.25360000133514404},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.2533000111579895}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.15630","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.15630","pdf_url":"https://arxiv.org/pdf/2608.15630","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-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.15630","doi":"https://doi.org/10.48550/arxiv.2608.15630","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.15630","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":"pmh:oai:arXiv.org:2608.15630","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.15630","pdf_url":"https://arxiv.org/pdf/2608.15630","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-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.8278999924659729,"display_name":"Quality education","id":"https://metadata.un.org/sdg/4"}],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320330983","display_name":"National Institute for Testing and Evaluation","ror":"https://ror.org/03pm0a810"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7203671971.pdf","grobid_xml":"https://content.openalex.org/works/W7203671971.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W3083410900","https://openalex.org/W4321277158","https://openalex.org/W4327810158","https://openalex.org/W4396913486","https://openalex.org/W4407814496","https://openalex.org/W4412886673","https://openalex.org/W4413109285","https://openalex.org/W4416610439","https://openalex.org/W4417114362","https://openalex.org/W4417280536","https://openalex.org/W7167477223"],"related_works":["https://openalex.org/W7203748057","https://openalex.org/W7140802954","https://openalex.org/W7166580071","https://openalex.org/W7154173883","https://openalex.org/W7165626181","https://openalex.org/W4404174416","https://openalex.org/W4412889255","https://openalex.org/W7165140551","https://openalex.org/W4408320960","https://openalex.org/W4415590663"],"abstract_inverted_index":{"The":[0],"rapid":[1],"development":[2],"and":[3,35,43,85,130,166,176,187,205],"growing":[4],"deployment":[5],"of":[6,110,135,214],"large":[7],"language":[8],"models":[9],"(LLMs)":[10],"have":[11],"made":[12],"it":[13],"increasingly":[14],"important":[15],"to":[16,24,32,44,67,112,168,221],"understand":[17],"their":[18],"capabilities.":[19,226],"A":[20],"common":[21],"approach":[22,159],"is":[23,104],"evaluate":[25],"LLMs":[26],"using":[27],"assessment":[28],"instruments":[29,49],"originally":[30],"designed":[31],"measure":[33,68,199],"skills":[34,62],"competencies":[36],"in":[37,69,106,124],"humans,":[38],"such":[39,76],"as":[40,50],"standardized":[41],"exams,":[42],"use":[45,218],"performance":[46,84],"on":[47,59],"these":[48],"evidence":[51,192],"for":[52,89,93,100,203],"generalizable":[53],"claims":[54,223],"about":[55,224],"LLMs'":[56],"underlying":[57,86],"abilities":[58],"the":[60,63,80,107,113,194,200,212],"same":[61,201],"assessments":[64,196,220],"are":[65],"intended":[66],"humans.":[70],"However,":[71],"from":[72],"a":[73,97,131,136,141],"validity":[74,213],"perspective,":[75],"inferences":[77],"require":[78],"that":[79,193,217],"relationship":[81],"between":[82,185],"observed":[83],"constructs":[87,202],"established":[88],"humans":[90,204],"also":[91],"holds":[92,123],"LLMs.":[94,156,177,206],"In":[95,115],"particular,":[96],"necessary":[98],"condition":[99,122],"transferring":[101],"score":[102],"interpretations":[103],"similarity":[105,172],"latent":[108,170],"structure":[109,171],"responses":[111,151],"assessment.":[114],"this":[116,121],"study,":[117],"we":[118,145,181],"examine":[119],"whether":[120],"two":[125],"educational":[126,219],"contexts:":[127],"high-school":[128],"chemistry":[129],"quantitative":[132],"reasoning":[133],"section":[134],"university":[137],"entrance":[138],"exam.":[139],"Using":[140],"case":[142],"study":[143],"design,":[144],"compare":[146],"human":[147,174,186],"response":[148],"data":[149],"with":[150],"generated":[152],"by":[153],"six":[154],"multimodal":[155],"Our":[157],"analytical":[158],"combines":[160],"exploratory":[161],"factor":[162,164,189],"analysis,":[163],"congruence,":[165],"resampling":[167],"assess":[169],"across":[173],"learners":[175],"Across":[178],"both":[179],"instruments,":[180],"find":[182],"systematic":[183],"differences":[184],"LLM":[188],"structures,":[190],"showing":[191],"analyzed":[195],"may":[197],"not":[198],"These":[207],"findings":[208],"call":[209],"into":[210],"question":[211],"evaluation":[215],"practices":[216],"make":[222],"AI":[225]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-19T00:00:00"}