{"id":"https://openalex.org/W7124492800","doi":"https://doi.org/10.48550/arxiv.2601.09953","title":"Take Out Your Calculators: Estimating the Real Difficulty of Question Items with LLM Student Simulations","display_name":"Take Out Your Calculators: Estimating the Real Difficulty of Question Items with LLM Student Simulations","publication_year":2026,"publication_date":"2026-01-15","ids":{"openalex":"https://openalex.org/W7124492800","doi":"https://doi.org/10.48550/arxiv.2601.09953"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2601.09953","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2601.09953","pdf_url":"https://arxiv.org/pdf/2601.09953","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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2601.09953","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5099261454","display_name":"Christabel Acquaye","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Acquaye, Christabel","raw_affiliation_strings":["University of Maryland , College Park"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland , College Park","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146833452","display_name":"Yi Ting Huang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huang, Yi Ting","raw_affiliation_strings":["University of Maryland , College Park"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland , College Park","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078390032","display_name":"Marine Jacinthe Carpuat","orcid":"https://orcid.org/0000-0003-1693-0782","observed_orcids":["https://orcid.org/0000-0003-1693-0782"]},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carpuat, Marine","raw_affiliation_strings":["University of Maryland , College Park"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland , College Park","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123230899","display_name":"Rachel Rudinger","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rudinger, Rachel","raw_affiliation_strings":["University of Maryland , College Park"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland , College Park","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I66946132"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.36550000309944153,"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"}},"topics":[{"id":"https://openalex.org/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.36550000309944153,"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"}},{"id":"https://openalex.org/T14414","display_name":"Artificial Intelligence in Education","score":0.25999999046325684,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10467","display_name":"Psychometric Methodologies and Testing","score":0.10419999808073044,"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/item-difficulty-estimation","display_name":"item difficulty estimation","score":0.9020000100135803},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9190000295639038},{"id":"https://openalex.org/keywords/student-simulation","display_name":"student simulation","score":0.6980000138282776},{"id":"https://openalex.org/keywords/role-play","display_name":"role play","score":0.5249999761581421},{"id":"https://openalex.org/keywords/item-response-theory","display_name":"item response theory","score":0.8159999847412109},{"id":"https://openalex.org/keywords/national-assessment-of-educational-progress","display_name":"National Assessment of Educational Progress","score":0.6389999985694885},{"id":"https://openalex.org/keywords/student-proficiency-levels","display_name":"student proficiency levels","score":0.4569999873638153},{"id":"https://openalex.org/keywords/demographic-stratification","display_name":"demographic stratification","score":0.5540000200271606}],"concepts":[{"id":"https://openalex.org/C76509639","wikidata":"https://www.wikidata.org/wiki/Q918036","display_name":"Race (biology)","level":2,"score":0.5221999883651733},{"id":"https://openalex.org/C134121241","wikidata":"https://www.wikidata.org/wiki/Q899301","display_name":"Yield (engineering)","level":2,"score":0.486299991607666},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.47940000891685486},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.46470001339912415},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.45170000195503235},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4212999939918518},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4174000024795532},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.39719998836517334},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.33180001378059387},{"id":"https://openalex.org/C19875794","wikidata":"https://www.wikidata.org/wiki/Q1207340","display_name":"Item response theory","level":3,"score":0.3294000029563904},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.32120001316070557},{"id":"https://openalex.org/C203151758","wikidata":"https://www.wikidata.org/wiki/Q3244907","display_name":"Standardized test","level":2,"score":0.2973000109195709},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2863999903202057},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2628999948501587},{"id":"https://openalex.org/C3019719930","wikidata":"https://www.wikidata.org/wiki/Q3910099","display_name":"Predictive value","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25699999928474426},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2601.09953","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2601.09953","pdf_url":"https://arxiv.org/pdf/2601.09953","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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2601.09953","doi":"https://doi.org/10.48550/arxiv.2601.09953","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.09953","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2601.09953","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2601.09953","pdf_url":"https://arxiv.org/pdf/2601.09953","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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality education","score":0.8278999924659729}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7124492800.pdf","grobid_xml":"https://content.openalex.org/works/W7124492800.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4415152300","https://openalex.org/W7161687037","https://openalex.org/W7166510560","https://openalex.org/W4412874000","https://openalex.org/W7128365992","https://openalex.org/W7172318175","https://openalex.org/W7166833243","https://openalex.org/W7167497475","https://openalex.org/W6945834842","https://openalex.org/W7166879998"],"abstract_inverted_index":{"Standardized":[0],"math":[1,32,151],"assessments":[2],"require":[3],"expensive":[4],"human":[5],"pilot":[6],"studies":[7],"to":[8,78,92,105,174],"establish":[9],"the":[10,17,28,57,61,76,87,116,141,213,219],"difficulty":[11,29,101,202],"of":[12,20,30,46,68,81,89,119,215],"test":[13],"items.":[14],"We":[15,37,85,123,164],"investigate":[16],"predictive":[18],"value":[19],"open-source":[21],"large":[22],"language":[23],"models":[24,207,217],"(LLMs)":[25],"for":[26,34,103,133,218],"evaluating":[27],"multiple-choice":[31],"questions":[33],"real-world":[35,107,201],"students.":[36],"show":[38,189],"that,":[39],"while":[40],"LLMs":[41,52,191],"are":[42],"poor":[43],"direct":[44],"judges":[45],"problem":[47],"difficulty,":[48],"simulation-based":[49],"approaches":[50],"with":[51,153,168,192],"yield":[53,199],"promising":[54],"results":[55,188],"under":[56],"right":[58],"conditions.":[59],"Under":[60],"proposed":[62],"approach,":[63],"we":[64,148],"simulate":[65],"a":[66],"``classroom''":[67],"4th,":[69],"8th,":[70],"or":[71],"12th-grade":[72],"students":[73,80,170],"by":[74,111,115],"prompting":[75],"LLM":[77],"role-play":[79],"varying":[82],"proficiency":[83],"levels.":[84],"use":[86],"outcomes":[88],"these":[90,216],"simulations":[91],"fit":[93],"Item":[94],"Response":[95],"Theory":[96],"(IRT)":[97],"models,":[98],"comparing":[99],"learned":[100],"parameters":[102],"items":[104],"their":[106],"difficulties,":[108],"as":[109,126,128],"determined":[110],"item-level":[112,142],"statistics":[113],"furnished":[114],"National":[117],"Assessment":[118],"Educational":[120],"Progress":[121],"(NAEP).":[122],"observe":[124],"correlations":[125],"high":[127],"0.75,":[129],"0.76,":[130],"and":[131,137,162,177,182,209],"0.82":[132],"grades":[134],"4,":[135],"8,":[136],"12,":[138],"respectively,":[139],"on":[140,150],"correctness":[143],"rates.":[144],"In":[145],"our":[146],"simulations,":[147],"experiment":[149],"MCQs":[152],"different":[154],"``classroom":[155],"sizes,''":[156],"showing":[157],"tradeoffs":[158],"between":[159],"computation":[160],"size":[161],"accuracy.":[163],"find":[165],"that":[166,190],"role-plays":[167],"diverse-named":[169],"improve":[171],"predictions":[172,203],"(compared":[173],"student":[175],"IDs),":[176],"stratifying":[178],"names":[179],"across":[180],"gender":[181],"race":[183],"further":[184,211],"improves":[185],"predictions.":[186],"Our":[187],"relatively":[193],"weaker":[194],"mathematical":[195],"abilities":[196],"(Gemma)":[197],"actually":[198],"better":[200],"than":[204],"mathematically":[205],"stronger":[206],"(Llama":[208],"Qwen),":[210],"underscoring":[212],"suitability":[214],"task.":[220]},"counts_by_year":[],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2026-01-17T00:00:00"}