{"id":"https://openalex.org/W4412889255","doi":"https://doi.org/10.18653/v1/2025.bea-1.21","title":"Do LLMs Give Psychometrically Plausible Responses in Educational Assessments?","display_name":"Do LLMs Give Psychometrically Plausible Responses in Educational Assessments?","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412889255","doi":"https://doi.org/10.18653/v1/2025.bea-1.21"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.bea-1.21","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.bea-1.21","pdf_url":"https://aclanthology.org/2025.bea-1.21.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-1.21.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119181660","display_name":"Andreas S\u00e4uberli","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andreas S\u00e4uberli","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078541115","display_name":"Diego Frassinelli","orcid":"https://orcid.org/0000-0002-1517-2185"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Diego Frassinelli","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5088832285","display_name":"Barbara Plank","orcid":"https://orcid.org/0000-0002-4394-1965"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Barbara Plank","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":1.673,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.83494603,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"266","last_page":"278"},"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":0.38659998774528503,"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":0.38659998774528503,"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/T10467","display_name":"Psychometric Methodologies and Testing","score":0.3792000114917755,"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/T14025","display_name":"Educational Technology and Assessment","score":0.35269999504089355,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.44368845224380493},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.38325801491737366},{"id":"https://openalex.org/keywords/clinical-psychology","display_name":"Clinical psychology","score":0.3812164068222046}],"concepts":[{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.44368845224380493},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.38325801491737366},{"id":"https://openalex.org/C70410870","wikidata":"https://www.wikidata.org/wiki/Q199906","display_name":"Clinical psychology","level":1,"score":0.3812164068222046}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.bea-1.21","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.bea-1.21","pdf_url":"https://aclanthology.org/2025.bea-1.21.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-1.21","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.bea-1.21","pdf_url":"https://aclanthology.org/2025.bea-1.21.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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7300000190734863}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412889255.pdf","grobid_xml":"https://content.openalex.org/works/W4412889255.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"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/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Knowing":[0],"how":[1],"test":[2,12,21,42,58,82,108],"takers":[3],"answer":[4],"items":[5,83,149],"in":[6,104,146,172],"educational":[7,105,170],"assessments":[8,171],"is":[9],"essential":[10],"for":[11,168],"development,":[13],"to":[14,19,41,56,141,151],"evaluate":[15,63],"item":[16,111],"quality,":[17],"and":[18,90,110],"improve":[20],"validity.However,":[22],"this":[23,44,60],"process":[24],"usually":[25],"requires":[26],"extensive":[27],"pilot":[28,54],"studies":[29],"with":[30,75,132,144],"human":[31],"participants.If":[32],"large":[33],"language":[34],"models":[35,119],"(LLMs)":[36],"exhibit":[37],"human-like":[38,129],"response":[39,112,124],"behavior":[40],"items,":[43],"could":[45],"open":[46],"up":[47],"the":[48,64,154],"possibility":[49],"of":[50,69,80],"using":[51],"them":[52],"as":[53],"participants":[55],"accelerate":[57],"development.In":[59],"paper,":[61],"we":[62,136],"human-likeness":[65],"or":[66],"psychometric":[67],"plausibility":[68],"responses":[70],"from":[71,98],"18":[72],"instruction-tuned":[73],"LLMs":[74,139,163],"two":[76,95],"publicly":[77],"available":[78],"datasets":[79],"multiplechoice":[81],"across":[84],"three":[85],"subjects:":[86],"reading,":[87],"U.S.":[88],"history,":[89],"economics.Our":[91],"methodology":[92],"builds":[93],"on":[94],"theoretical":[96],"frameworks":[97],"psychometrics":[99],"which":[100],"are":[101,120,156],"commonly":[102],"used":[103,167],"assessment,":[106],"classical":[107],"theory":[109],"theory.The":[113],"results":[114],"show":[115],"that":[116,138,162],"while":[117],"larger":[118],"excessively":[121],"confident,":[122],"their":[123],"distributions":[125],"can":[126],"be":[127,166],"more":[128],"when":[130],"calibrated":[131],"temperature":[133],"scaling.In":[134],"addition,":[135],"find":[137],"tend":[140],"correlate":[142],"better":[143],"humans":[145],"reading":[147],"comprehension":[148],"compared":[150],"other":[152],"subjects.However,":[153],"correlations":[155],"not":[157,165],"very":[158],"strong":[159],"overall,":[160],"indicating":[161],"should":[164],"piloting":[169],"a":[173],"zero-shot":[174],"setting.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
