{"id":"https://openalex.org/W4412889178","doi":"https://doi.org/10.18653/v1/2025.bea-1.75","title":"Can LLMs Reliably Simulate Real Students\u2019 Abilities in Mathematics and Reading Comprehension?","display_name":"Can LLMs Reliably Simulate Real Students\u2019 Abilities in Mathematics and Reading Comprehension?","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412889178","doi":"https://doi.org/10.18653/v1/2025.bea-1.75"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.bea-1.75","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.bea-1.75","pdf_url":"https://aclanthology.org/2025.bea-1.75.pdf","source":null,"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 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.bea-1.75.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086708404","display_name":"KV Aditya Srivatsa","orcid":"https://orcid.org/0000-0002-7583-7580"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]},{"id":"https://openalex.org/I91044093","display_name":"Zayed University","ror":"https://ror.org/03snqfa66","country_code":"AE","type":"education","lineage":["https://openalex.org/I91044093"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"KV Aditya Srivatsa","raw_affiliation_strings":["Zayed University of Artificial Intelligence , Abu Dhabi , UAE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zayed University of Artificial Intelligence , Abu Dhabi , UAE","institution_ids":["https://openalex.org/I4210113480","https://openalex.org/I91044093"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5096228950","display_name":"Kaushal Kumar Maurya","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kaushal Maurya","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5069779745","display_name":"Ekaterina Kochmar","orcid":"https://orcid.org/0000-0003-3328-1374"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]},{"id":"https://openalex.org/I91044093","display_name":"Zayed University","ror":"https://ror.org/03snqfa66","country_code":"AE","type":"education","lineage":["https://openalex.org/I91044093"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Ekaterina Kochmar","raw_affiliation_strings":["Zayed University of Artificial Intelligence , Abu Dhabi , UAE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zayed University of Artificial Intelligence , Abu Dhabi , UAE","institution_ids":["https://openalex.org/I4210113480","https://openalex.org/I91044093"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.673,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.83486324,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"988","last_page":"1001"},"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":0.9876000285148621,"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":0.9876000285148621,"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/T11122","display_name":"Online Learning and Analytics","score":0.9430000185966492,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T12884","display_name":"Educational Assessment and Pedagogy","score":0.9132999777793884,"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/comprehension","display_name":"Comprehension","score":0.6787747740745544},{"id":"https://openalex.org/keywords/mathematics-education","display_name":"Mathematics education","score":0.6272972822189331},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.5989769101142883},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5757200717926025},{"id":"https://openalex.org/keywords/reading-comprehension","display_name":"Reading comprehension","score":0.5353083610534668},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.28909212350845337},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.23259925842285156},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09931457042694092}],"concepts":[{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.6787747740745544},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.6272972822189331},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.5989769101142883},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5757200717926025},{"id":"https://openalex.org/C2778780117","wikidata":"https://www.wikidata.org/wiki/Q3269423","display_name":"Reading comprehension","level":3,"score":0.5353083610534668},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.28909212350845337},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.23259925842285156},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09931457042694092},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.bea-1.75","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.bea-1.75","pdf_url":"https://aclanthology.org/2025.bea-1.75.pdf","source":null,"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 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.bea-1.75","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.bea-1.75","pdf_url":"https://aclanthology.org/2025.bea-1.75.pdf","source":null,"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 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.800000011920929,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412889178.pdf","grobid_xml":"https://content.openalex.org/works/W4412889178.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W4231203432"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W2082296339","https://openalex.org/W2161828220","https://openalex.org/W1972348076","https://openalex.org/W2083863157"],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"are":[4],"increasingly":[5],"used":[6],"as":[7,90],"proxy":[8,27],"students":[9,28,37],"in":[10,19,64],"the":[11,31,52,86,104,128,141,148,161],"development":[12],"of":[13,35,48,55,163],"Intelligent":[14],"Tutoring":[15],"Systems":[16],"(ITSs)":[17],"and":[18,33,61,68,82,145,153],"piloting":[20],"test":[21],"questions.However,":[22],"to":[23,78],"what":[24],"extent":[25],"these":[26],"accurately":[29],"emulate":[30],"behavior":[32],"characteristics":[34],"real":[36,91],"remains":[38,132],"an":[39,72],"open":[40],"question.To":[41],"investigate":[42],"this,":[43],"we":[44],"collected":[45],"a":[46],"dataset":[47],"489":[49],"items":[50],"from":[51],"National":[53],"Assessment":[54],"Educational":[56],"Progress":[57],"(NAEP),":[58],"covering":[59],"mathematics":[60],"reading":[62],"comprehension":[63],"grades":[65],"4,":[66],"8,":[67],"12.We":[69],"then":[70],"apply":[71],"Item":[73],"Response":[74],"Theory":[75],"(IRT)":[76],"model":[77],"position":[79],"11":[80],"diverse":[81],"state-of-the-art":[83],"LLMs":[84],"on":[85,167],"same":[87],"ability":[88],"scale":[89],"student":[92,106,131],"populations.Our":[93],"findings":[94],"reveal":[95],"that,":[96],"without":[97],"guidance,":[98],"strong":[99],"general-purpose":[100],"models":[101,114],"consistently":[102],"outperform":[103],"average":[105,129],"at":[107],"every":[108],"grade,":[109],"while":[110],"weaker":[111],"or":[112],"domain-mismatched":[113],"may":[115],"align":[116,126],"incidentally.Using":[117],"gradeenforcement":[118],"prompts":[119],"changes":[120],"models'":[121],"performance,":[122],"but":[123],"whether":[124],"they":[125],"with":[127],"grade-level":[130],"highly":[133],"model-and":[134],"prompt-specific:":[135],"no":[136],"evaluated":[137],"model-prompt":[138],"pair":[139],"fits":[140],"bill":[142],"across":[143],"subjects":[144],"grades,":[146],"underscoring":[147],"need":[149],"for":[150,160],"new":[151],"training":[152],"evaluation":[154],"strategies.We":[155],"conclude":[156],"by":[157],"providing":[158],"guidelines":[159],"selection":[162],"viable":[164],"proxies":[165],"based":[166],"our":[168],"findings.":[169],"1":[170]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
