{"id":"https://openalex.org/W4404910442","doi":"https://doi.org/10.1145/3649165.3690123","title":"A Benchmark for Testing the Capabilities of LLMs in Assessing the Quality of Multiple-choice Questions in Introductory Programming Education","display_name":"A Benchmark for Testing the Capabilities of LLMs in Assessing the Quality of Multiple-choice Questions in Introductory Programming Education","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4404910442","doi":"https://doi.org/10.1145/3649165.3690123"},"language":"en","primary_location":{"id":"doi:10.1145/3649165.3690123","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3649165.3690123","pdf_url":null,"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 2024 on ACM Virtual Global Computing Education Conference V. 1","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3649165.3690123","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055097615","display_name":"Aninditha Ramesh","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Aninditha Ramesh","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, USA"],"raw_orcid":"https://orcid.org/0009-0004-3695-2780","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017723217","display_name":"Arav Agarwal","orcid":"https://orcid.org/0000-0001-9848-1663"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arav Agarwal","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, USA"],"raw_orcid":"https://orcid.org/0000-0001-9848-1663","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087407230","display_name":"Jacob Arthur Doughty","orcid":"https://orcid.org/0009-0008-5430-7282"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jacob Arthur Doughty","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, USA"],"raw_orcid":"https://orcid.org/0009-0008-5430-7282","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036173924","display_name":"Ketan Ramaneti","orcid":"https://orcid.org/0000-0003-3836-278X"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ketan Ramaneti","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, USA"],"raw_orcid":"https://orcid.org/0000-0003-3836-278X","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077762937","display_name":"Jarom\u00edr \u0160avelka","orcid":"https://orcid.org/0000-0002-3674-5456"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jaromir Savelka","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, USA"],"raw_orcid":"https://orcid.org/0000-0002-3674-5456","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001245246","display_name":"Majd Sakr","orcid":"https://orcid.org/0000-0001-5150-8259"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Majd Sakr","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, USA"],"raw_orcid":"https://orcid.org/0000-0001-5150-8259","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5055097615"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.3905,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.74483699,"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":"193","last_page":"199"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10533","display_name":"Teaching and Learning Programming","score":0.9879999756813049,"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"}},"topics":[{"id":"https://openalex.org/T10533","display_name":"Teaching and Learning Programming","score":0.9879999756813049,"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/T13836","display_name":"Educational Research and Pedagogy","score":0.9747999906539917,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T14025","display_name":"Educational Technology and Assessment","score":0.9433000087738037,"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/benchmark","display_name":"Benchmark (surveying)","score":0.7382006645202637},{"id":"https://openalex.org/keywords/multiple-choice","display_name":"Multiple choice","score":0.6020880937576294},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6005743741989136},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5513713359832764},{"id":"https://openalex.org/keywords/mathematics-education","display_name":"Mathematics education","score":0.3673875331878662},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3524860143661499},{"id":"https://openalex.org/keywords/management-science","display_name":"Management science","score":0.342027485370636},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1497395932674408},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.14886131882667542},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10891106724739075},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08091804385185242}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7382006645202637},{"id":"https://openalex.org/C176730311","wikidata":"https://www.wikidata.org/wiki/Q867668","display_name":"Multiple choice","level":3,"score":0.6020880937576294},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6005743741989136},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5513713359832764},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.3673875331878662},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3524860143661499},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.342027485370636},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1497395932674408},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.14886131882667542},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10891106724739075},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08091804385185242},{"id":"https://openalex.org/C3018023364","wikidata":"https://www.wikidata.org/wiki/Q425265","display_name":"Significant difference","level":2,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3649165.3690123","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3649165.3690123","pdf_url":null,"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 2024 on ACM Virtual Global Computing Education Conference V. 1","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3649165.3690123","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3649165.3690123","pdf_url":null,"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 2024 on ACM Virtual Global Computing Education Conference V. 1","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7900000214576721,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1989277800","https://openalex.org/W2016300738","https://openalex.org/W2161325192","https://openalex.org/W2757715585","https://openalex.org/W2887398393","https://openalex.org/W2887566655","https://openalex.org/W4230117151","https://openalex.org/W4291476001","https://openalex.org/W4321162272","https://openalex.org/W4381587445","https://openalex.org/W4382654294","https://openalex.org/W4383181289","https://openalex.org/W4384659495","https://openalex.org/W4384661504","https://openalex.org/W4389471004","https://openalex.org/W4390621416","https://openalex.org/W4393156935"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526","https://openalex.org/W2121910908","https://openalex.org/W915438175","https://openalex.org/W4230315250"],"abstract_inverted_index":{"There":[0],"has":[1,60],"been":[2],"a":[3,68,100,112,126,142],"growing":[4],"interest":[5],"in":[6,161],"utilizing":[7],"large":[8],"language":[9],"models":[10],"(LLMs)":[11],"for":[12,25,30],"numerous":[13],"educational":[14,28],"applications.":[15],"Recent":[16],"studies":[17],"have":[18],"focused":[19],"on":[20,111],"the":[21,50,89,123,131,139,147,167,172,177],"use":[22,85],"of":[23,52,62,87,91,103,125,133],"LLMs":[24,149],"generating":[26],"various":[27],"artifacts":[29],"programming":[31,35,92],"education,":[32],"such":[33,53,118,158],"as":[34,169,171],"exercises,":[36],"model":[37],"solutions,":[38],"or":[39],"multiple-choice":[40],"questions":[41],"(MCQs).":[42],"The":[43,135],"ability":[44],"to":[45,71,146,176],"efficiently":[46],"and":[47,57,73,130],"reliably":[48],"assess":[49],"quality":[51,90,108,132],"artifacts,":[54],"both":[55],"automatically":[56],"human":[58],"generated,":[59],"become":[61],"paramount":[63],"importance.":[64],"Hence,":[65],"there":[66],"is":[67,154],"pressing":[69],"need":[70],"develop":[72],"make":[74],"available":[75],"robust":[76],"benchmarks.":[77],"In":[78],"this":[79,162],"paper,":[80],"we":[81,97,165],"investigate":[82],"an":[83],"example":[84],"case":[86],"assessing":[88],"MCQs.":[93],"To":[94,156],"that":[95,114,138],"end,":[96],"carefully":[98],"curated":[99],"data":[101],"set":[102],"192":[104],"MCQs":[105],"annotated":[106],"with":[107],"scores":[109],"based":[110],"rubric":[113],"evaluates":[115],"crucial":[116],"aspects":[117],"as,":[119],"e.g.,":[120],"their":[121],"clarity,":[122],"presence":[124],"single":[127],"correct":[128],"answer,":[129],"distractors.":[134],"results":[136],"show":[137],"task":[140],"presents":[141],"considerable":[143],"challenge":[144],"even":[145],"state-of-the-art":[148],"and,":[150],"hence,":[151],"further":[152,157],"research":[153,159],"needed.":[155],"efforts":[160],"important":[163],"area":[164],"release":[166],"dataset":[168],"well":[170],"extensible":[173],"evaluation":[174],"pipeline":[175],"public.":[178]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
