{"id":"https://openalex.org/W4415961592","doi":"https://doi.org/10.1145/3774752","title":"Evaluating AI Models for Autograding Explain in Plain English Questions: Challenges and Considerations","display_name":"Evaluating AI Models for Autograding Explain in Plain English Questions: Challenges and Considerations","publication_year":2025,"publication_date":"2025-11-06","ids":{"openalex":"https://openalex.org/W4415961592","doi":"https://doi.org/10.1145/3774752"},"language":"en","primary_location":{"id":"doi:10.1145/3774752","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3774752","pdf_url":null,"source":{"id":"https://openalex.org/S4210173818","display_name":"ACM Transactions on Interactive Intelligent Systems","issn_l":"2160-6455","issn":["2160-6455","2160-6463"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Interactive Intelligent Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091001653","display_name":"Max Fowler","orcid":"https://orcid.org/0000-0002-4730-447X"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"id":"https://openalex.org/I2801919071","display_name":"University of Illinois System","ror":"https://ror.org/05e94g991","country_code":"US","type":"education","lineage":["https://openalex.org/I2801919071"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Max Fowler","raw_affiliation_strings":["Computer Science, University of Illinois, Urbana, Illinois, USA","University of Illinois, USA"],"raw_orcid":"https://orcid.org/0000-0002-4730-447X","affiliations":[{"raw_affiliation_string":"Computer Science, University of Illinois, Urbana, Illinois, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois, USA","institution_ids":["https://openalex.org/I2801919071"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041366930","display_name":"Chinedu Emeka","orcid":"https://orcid.org/0000-0002-4821-162X"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"id":"https://openalex.org/I2801919071","display_name":"University of Illinois System","ror":"https://ror.org/05e94g991","country_code":"US","type":"education","lineage":["https://openalex.org/I2801919071"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chinedu Emeka","raw_affiliation_strings":["Computer Science, University of Illinois, Urbana, Illinois, USA","University of Illinois, USA"],"raw_orcid":"https://orcid.org/0000-0002-4821-162X","affiliations":[{"raw_affiliation_string":"Computer Science, University of Illinois, Urbana, Illinois, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois, USA","institution_ids":["https://openalex.org/I2801919071"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101837457","display_name":"Binglin Chen","orcid":"https://orcid.org/0000-0001-9033-1281"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"id":"https://openalex.org/I2801919071","display_name":"University of Illinois System","ror":"https://ror.org/05e94g991","country_code":"US","type":"education","lineage":["https://openalex.org/I2801919071"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Binglin Chen","raw_affiliation_strings":["Computer Science, University of Illinois, Urbana, Illinois, USA","University of Illinois, USA"],"raw_orcid":"https://orcid.org/0000-0001-9033-1281","affiliations":[{"raw_affiliation_string":"Computer Science, University of Illinois, Urbana, Illinois, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois, USA","institution_ids":["https://openalex.org/I2801919071"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014942043","display_name":"David H. Smith","orcid":"https://orcid.org/0000-0002-6572-4347"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David H. Smith IV","raw_affiliation_strings":["Computer Science, Virginia Tech, Blacksburg, Virginia, USA","Virginia Tech, USA"],"raw_orcid":"https://orcid.org/0000-0002-6572-4347","affiliations":[{"raw_affiliation_string":"Computer Science, Virginia Tech, Blacksburg, Virginia, USA","institution_ids":["https://openalex.org/I859038795"]},{"raw_affiliation_string":"Virginia Tech, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001110474","display_name":"Matthew West","orcid":"https://orcid.org/0000-0002-7605-0050"},"institutions":[{"id":"https://openalex.org/I2801919071","display_name":"University of Illinois System","ror":"https://ror.org/05e94g991","country_code":"US","type":"education","lineage":["https://openalex.org/I2801919071"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew West","raw_affiliation_strings":["Mechanical Science and Engineering, University of Illinois, Urbana, Illinois, USA","University of Illinois, USA"],"raw_orcid":"https://orcid.org/0000-0002-7605-0050","affiliations":[{"raw_affiliation_string":"Mechanical Science and Engineering, University of Illinois, Urbana, Illinois, USA","institution_ids":["https://openalex.org/I2801919071"]},{"raw_affiliation_string":"University of Illinois, USA","institution_ids":["https://openalex.org/I2801919071"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066756473","display_name":"Craig Zilles","orcid":"https://orcid.org/0000-0003-4601-4398"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"id":"https://openalex.org/I2801919071","display_name":"University of Illinois System","ror":"https://ror.org/05e94g991","country_code":"US","type":"education","lineage":["https://openalex.org/I2801919071"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Craig Zilles","raw_affiliation_strings":["Computer Science, University of Illinois, Urbana, Illinois, USA","University of Illinois, USA"],"raw_orcid":"https://orcid.org/0000-0003-4601-4398","affiliations":[{"raw_affiliation_string":"Computer Science, University of Illinois, Urbana, Illinois, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois, USA","institution_ids":["https://openalex.org/I2801919071"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5091001653"],"corresponding_institution_ids":["https://openalex.org/I157725225","https://openalex.org/I2801919071"],"apc_list":null,"apc_paid":null,"fwci":4.3465,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.94890127,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"15","issue":"4","first_page":"1","last_page":"29"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13629","display_name":"Text Readability and Simplification","score":0.13680000603199005,"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/T13629","display_name":"Text Readability and Simplification","score":0.13680000603199005,"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/T12070","display_name":"Writing and Handwriting Education","score":0.12020000070333481,"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/T11587","display_name":"Second Language Acquisition and Learning","score":0.08510000258684158,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/bigram","display_name":"Bigram","score":0.8349999785423279},{"id":"https://openalex.org/keywords/grading","display_name":"Grading (engineering)","score":0.6432999968528748},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.5534999966621399},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5148000121116638},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.5091999769210815},{"id":"https://openalex.org/keywords/plain-english","display_name":"Plain English","score":0.44589999318122864},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.3926999866962433},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.3917999863624573},{"id":"https://openalex.org/keywords/ask-price","display_name":"Ask price","score":0.3822000026702881}],"concepts":[{"id":"https://openalex.org/C108757681","wikidata":"https://www.wikidata.org/wiki/Q2773912","display_name":"Bigram","level":3,"score":0.8349999785423279},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6739000082015991},{"id":"https://openalex.org/C2777286243","wikidata":"https://www.wikidata.org/wiki/Q5591926","display_name":"Grading (engineering)","level":2,"score":0.6432999968528748},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5938000082969666},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.5534999966621399},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5148000121116638},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.5091999769210815},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4934000074863434},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46540001034736633},{"id":"https://openalex.org/C2780957164","wikidata":"https://www.wikidata.org/wiki/Q2920188","display_name":"Plain English","level":2,"score":0.44589999318122864},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.3926999866962433},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.3917999863624573},{"id":"https://openalex.org/C90329073","wikidata":"https://www.wikidata.org/wiki/Q914232","display_name":"Ask price","level":2,"score":0.3822000026702881},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3799999952316284},{"id":"https://openalex.org/C2777083192","wikidata":"https://www.wikidata.org/wiki/Q1814648","display_name":"Plain language","level":2,"score":0.3709999918937683},{"id":"https://openalex.org/C2777413886","wikidata":"https://www.wikidata.org/wiki/Q3276013","display_name":"Fluency","level":2,"score":0.3596000075340271},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.3483000099658966},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3377000093460083},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.31520000100135803},{"id":"https://openalex.org/C2987496018","wikidata":"https://www.wikidata.org/wiki/Q1860","display_name":"English language","level":2,"score":0.314300000667572},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3111000061035156},{"id":"https://openalex.org/C2781162219","wikidata":"https://www.wikidata.org/wiki/Q26250693","display_name":"Replicate","level":2,"score":0.2854999899864197},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2741999924182892},{"id":"https://openalex.org/C2778371403","wikidata":"https://www.wikidata.org/wiki/Q7672049","display_name":"TUTOR","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.2711000144481659},{"id":"https://openalex.org/C2779041454","wikidata":"https://www.wikidata.org/wiki/Q870780","display_name":"Chatbot","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C63435697","wikidata":"https://www.wikidata.org/wiki/Q864135","display_name":"Binary code","level":3,"score":0.26269999146461487},{"id":"https://openalex.org/C151956035","wikidata":"https://www.wikidata.org/wiki/Q1132755","display_name":"Logistic regression","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C2777648619","wikidata":"https://www.wikidata.org/wiki/Q2845208","display_name":"Learning analytics","level":2,"score":0.2551000118255615}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3774752","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3774752","pdf_url":null,"source":{"id":"https://openalex.org/S4210173818","display_name":"ACM Transactions on Interactive Intelligent Systems","issn_l":"2160-6455","issn":["2160-6455","2160-6463"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Interactive Intelligent Systems","raw_type":"journal-article"},{"id":"pmh:oai:vtechworks.lib.vt.edu:10919/139800","is_oa":false,"landing_page_url":"https://hdl.handle.net/10919/139800","pdf_url":null,"source":{"id":"https://openalex.org/S4306400248","display_name":"VTechWorks (Virginia Tech)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I859038795","host_organization_name":"Virginia Tech","host_organization_lineage":["https://openalex.org/I859038795"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W43048615","https://openalex.org/W1967082761","https://openalex.org/W2012560454","https://openalex.org/W2165365113","https://openalex.org/W2739522917","https://openalex.org/W2900327614","https://openalex.org/W2912010641","https://openalex.org/W2914823529","https://openalex.org/W2970641574","https://openalex.org/W2989567029","https://openalex.org/W3000429148","https://openalex.org/W3010192453","https://openalex.org/W3161516024","https://openalex.org/W4282015716","https://openalex.org/W4294214983","https://openalex.org/W4322625259","https://openalex.org/W4323033814","https://openalex.org/W4377095850","https://openalex.org/W4382652859","https://openalex.org/W4382654294","https://openalex.org/W4391282616","https://openalex.org/W4391417542","https://openalex.org/W4392542324","https://openalex.org/W4392563703","https://openalex.org/W4392564315","https://openalex.org/W4392564669","https://openalex.org/W4392564671","https://openalex.org/W4392564824","https://openalex.org/W4400267629","https://openalex.org/W4400268428","https://openalex.org/W4400335533","https://openalex.org/W4402670856","https://openalex.org/W4407681574","https://openalex.org/W4407841980","https://openalex.org/W4409211845"],"related_works":[],"abstract_inverted_index":{"Code-reading":[0],"ability":[1,49],"has":[2,18],"traditionally":[3],"been":[4],"under-emphasized":[5],"in":[6,53,147,202,214],"assessments":[7],"as":[8,113,115,198],"it":[9],"is":[10,50],"difficult":[11],"to":[12,31,46,61,122,137,193],"assess":[13,32,47],"at":[14],"scale.":[15],"Prior":[16],"research":[17,73],"shown":[19],"that":[20,82],"code-reading":[21,48],"and":[22,33,188,236,241],"code-writing":[23],"are":[24],"closely":[25],"related":[26],"skills;":[27],"thus":[28],"being":[29],"able":[30],"train":[34],"code":[35,67,189,196],"reading":[36],"skills":[37],"may":[38],"be":[39],"necessary":[40],"for":[41,107,176,204],"student":[42,90,97],"learning.":[43],"One":[44],"way":[45],"using":[51,79],"Explain":[52],"Plain":[54],"English":[55],"(EiPE)":[56],"questions,":[57,102],"which":[58],"ask":[59],"students":[60,220],"describe":[62],"what":[63],"a":[64,75,93,199,215],"piece":[65],"of":[66,95,225],"does":[68],"with":[69,85,145,151,166,173,191],"natural":[70],"language.":[71],"Previous":[72],"deployed":[74],"binary":[76],"(correct/incorrect)":[77],"autograder":[78],"bigram":[80,120],"models":[81],"performed":[83],"comparably":[84],"human":[86,170],"teaching":[87],"assistants":[88],"on":[89,119,130,156],"responses.":[91],"With":[92],"dataset":[94],"3,064":[96],"responses":[98],"from":[99,132],"17":[100],"EiPE":[101,108],"we":[103,180],"investigated":[104],"multiple":[105,141,174],"autograders":[106,175,213],"questions.":[109],"We":[110,139],"evaluated":[111],"methods":[112],"simple":[114],"logistic":[116],"regression":[117],"trained":[118,129,155],"features,":[121],"more":[123,206,230,239],"complicated":[124],"Support":[125],"Vector":[126],"Machines":[127],"(SVMs)":[128],"embeddings":[131,158],"Large":[133],"Language":[134],"Models":[135],"(LLMs)":[136],"GPT-4.":[138],"found":[140,232],"useful":[142],"autograders,":[143,227],"most":[144],"accuracies":[146],"the":[148,160,233,243,246],"\\(86\\!\\!-\\!\\!88\\%\\)":[149],"range,":[150],"different":[152],"advantages.":[153],"SVMs":[154],"LLM":[157],"had":[159,221],"highest":[161],"accuracy;":[162],"few-shot":[163],"chat":[164],"completion":[165],"GPT-4":[167,192],"required":[168],"minimal":[169],"effort;":[171],"pipelines":[172],"specific":[177],"dimensions":[178],"(what":[179],"call":[181],"3D":[182],"autograders)":[183],"can":[184],"provide":[185],"fine-grained":[186],"feedback;":[187],"generation":[190],"leverage":[194],"automatic":[195],"testing":[197],"grading":[200,208],"mechanism":[201],"exchange":[203],"slightly":[205],"lenient":[207],"standards.":[209],"While":[210],"piloting":[211],"these":[212],"non-major":[216],"introductory":[217],"Python":[218],"course,":[219],"largely":[222],"similar":[223],"views":[224],"all":[226],"although":[228],"they":[229],"often":[231],"GPT-based":[234],"grader":[235,245],"code-generation":[237,244],"graders":[238],"helpful":[240],"liked":[242],"most.":[247]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-11-06T00:00:00"}