{"id":"https://openalex.org/W4396655344","doi":"https://doi.org/10.1007/s40593-024-00403-3","title":"GPT-4 in Education: Evaluating Aptness, Reliability, and Loss of Coherence in Solving Calculus Problems and Grading Submissions","display_name":"GPT-4 in Education: Evaluating Aptness, Reliability, and Loss of Coherence in Solving Calculus Problems and Grading Submissions","publication_year":2024,"publication_date":"2024-05-05","ids":{"openalex":"https://openalex.org/W4396655344","doi":"https://doi.org/10.1007/s40593-024-00403-3"},"language":"en","primary_location":{"id":"doi:10.1007/s40593-024-00403-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40593-024-00403-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40593-024-00403-3.pdf","source":{"id":"https://openalex.org/S171267539","display_name":"International Journal of Artificial Intelligence in Education","issn_l":"1560-4292","issn":["1560-4292","1560-4306"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Artificial Intelligence in Education","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s40593-024-00403-3.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055912056","display_name":"Alberto Gandolfi","orcid":"https://orcid.org/0000-0001-6956-7513"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Alberto Gandolfi","raw_affiliation_strings":["Division of Science, New York University Abu Dhabi, Abu Dhabi, 129188, UAE"],"affiliations":[{"raw_affiliation_string":"Division of Science, New York University Abu Dhabi, Abu Dhabi, 129188, UAE","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5055912056"],"corresponding_institution_ids":[],"apc_list":{"value":2190,"currency":"EUR","value_usd":2790},"apc_paid":{"value":2190,"currency":"EUR","value_usd":2790},"fwci":8.0065,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.97987515,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"35","issue":"1","first_page":"367","last_page":"397"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11697","display_name":"Numerical Methods and Algorithms","score":0.9287999868392944,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.9287999868392944,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/grading","display_name":"Grading (engineering)","score":0.7355006337165833},{"id":"https://openalex.org/keywords/formative-assessment","display_name":"Formative assessment","score":0.5403211116790771},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5306210517883301},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.5163882374763489},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.481202632188797},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.4811202585697174},{"id":"https://openalex.org/keywords/mathematics-education","display_name":"Mathematics education","score":0.37712591886520386},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.27658310532569885},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2523842453956604},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09976866841316223}],"concepts":[{"id":"https://openalex.org/C2777286243","wikidata":"https://www.wikidata.org/wiki/Q5591926","display_name":"Grading (engineering)","level":2,"score":0.7355006337165833},{"id":"https://openalex.org/C42525527","wikidata":"https://www.wikidata.org/wiki/Q1209955","display_name":"Formative assessment","level":2,"score":0.5403211116790771},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5306210517883301},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.5163882374763489},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.481202632188797},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.4811202585697174},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.37712591886520386},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.27658310532569885},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2523842453956604},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09976866841316223},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C147176958","wikidata":"https://www.wikidata.org/wiki/Q77590","display_name":"Civil engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s40593-024-00403-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40593-024-00403-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40593-024-00403-3.pdf","source":{"id":"https://openalex.org/S171267539","display_name":"International Journal of Artificial Intelligence in Education","issn_l":"1560-4292","issn":["1560-4292","1560-4306"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Artificial Intelligence in Education","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s40593-024-00403-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40593-024-00403-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40593-024-00403-3.pdf","source":{"id":"https://openalex.org/S171267539","display_name":"International Journal of Artificial Intelligence in Education","issn_l":"1560-4292","issn":["1560-4292","1560-4306"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Artificial Intelligence in Education","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6600000262260437,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4396655344.pdf"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W606696939","https://openalex.org/W1571434026","https://openalex.org/W2035627463","https://openalex.org/W2753032179","https://openalex.org/W2901184109","https://openalex.org/W2950784811","https://openalex.org/W2951400647","https://openalex.org/W2952422171","https://openalex.org/W2990138404","https://openalex.org/W3012049595","https://openalex.org/W3017131514","https://openalex.org/W3128455716","https://openalex.org/W3185341429","https://openalex.org/W3202285719","https://openalex.org/W3211193064","https://openalex.org/W4220966949","https://openalex.org/W4224912036","https://openalex.org/W4283768109","https://openalex.org/W4288059358","https://openalex.org/W4313294616","https://openalex.org/W4318919287","https://openalex.org/W4320516905","https://openalex.org/W4320731315","https://openalex.org/W4323655724","https://openalex.org/W4366403195","https://openalex.org/W4366783381","https://openalex.org/W4383181327","https://openalex.org/W4383751019","https://openalex.org/W4383913712","https://openalex.org/W4385443772","https://openalex.org/W4385571157","https://openalex.org/W4385571889","https://openalex.org/W4385650858","https://openalex.org/W4385820303","https://openalex.org/W4386022375","https://openalex.org/W4386053840","https://openalex.org/W4386136032","https://openalex.org/W4387037204","https://openalex.org/W4389200893","https://openalex.org/W4391071215","https://openalex.org/W4391481267","https://openalex.org/W4392681182","https://openalex.org/W4401953659","https://openalex.org/W6632297997","https://openalex.org/W6739901393","https://openalex.org/W6849710474","https://openalex.org/W7000679860"],"related_works":["https://openalex.org/W4392721137","https://openalex.org/W609482051","https://openalex.org/W3199325201","https://openalex.org/W2792035366","https://openalex.org/W4386050096","https://openalex.org/W2360976019","https://openalex.org/W2906881146","https://openalex.org/W2351166673","https://openalex.org/W2390109066","https://openalex.org/W2002537515"],"abstract_inverted_index":{"Abstract":[0],"In":[1,215],"this":[2,216],"paper,":[3],"we":[4,128],"initially":[5],"investigate":[6],"the":[7,50,68,126,144,150,158,230],"capabilities":[8],"of":[9,22,70,96,106,134,149,160,167],"GPT-3":[10],"5":[11],"and":[12,42,112,153,169,201,226],"GPT-4":[13,34,204],"in":[14,66,98,136,176,229],"solving":[15],"college-level":[16],"calculus":[17,76],"problems,":[18],"an":[19,83],"essential":[20],"segment":[21],"mathematics":[23],"that":[24,108,142],"remains":[25,188],"under-explored":[26],"so":[27],"far.":[28],"Although":[29],"improving":[30],"upon":[31],"earlier":[32],"versions,":[33],"attains":[35],"approximately":[36],"65%":[37],"accuracy":[38,187],"for":[39,46,72,117,132],"standard":[40],"problems":[41],"decreases":[43],"to":[44,53,57,75,81,125,221],"20%":[45],"competition-like":[47],"scenarios.":[48],"Overall,":[49],"models":[51,119],"prove":[52],"be":[54],"unreliable":[55],"due":[56],"common":[58],"arithmetic":[59],"errors.":[60],"Our":[61,78,139],"primary":[62],"contribution":[63],"lies":[64],"then":[65],"examining":[67],"use":[69],"ChatGPT":[71,97,146],"grading":[73,151,161],"solutions":[74],"exercises.":[77],"objectives":[79],"are":[80,122],"probe":[82],"in-context":[84],"learning":[85],"task":[86,152],"with":[87,181],"less":[88],"emphasis":[89],"over":[90],"direct":[91],"calculations;":[92],"recognize":[93],"positive":[94],"applications":[95],"educational":[99],"contexts;":[100],"highlight":[101],"a":[102,130],"potentially":[103],"emerging":[104],"facet":[105],"AI":[107,115],"could":[109],"necessitate":[110],"oversight;":[111],"introduce":[113],"unconventional":[114],"benchmarks,":[116],"which":[118],"like":[120,203],"GPT":[121],"untrained.":[123],"Pertaining":[124],"latter,":[127],"uncover":[129],"tendency":[131],"loss":[133,166],"coherence":[135,168],"extended":[137],"contexts.":[138],"findings":[140],"suggest":[141],"while":[143,210],"current":[145],"exhibits":[147],"comprehension":[148],"often":[154],"provides":[155],"relevant":[156],"outputs,":[157],"consistency":[159],"is":[162,219],"marred":[163],"by":[164],"occasional":[165],"hallucinations.":[170],"Intriguingly,":[171],"GPT-4's":[172],"overall":[173],"scores,":[174],"delivered":[175],"mere":[177],"moments,":[178],"align":[179],"closely":[180],"human":[182,199],"graders,":[183],"although":[184],"its":[185],"detailed":[186],"suboptimal.":[189],"This":[190],"work":[191],"suggests":[192],"that,":[193],"when":[194],"appropriately":[195],"orchestrated,":[196],"collaboration":[197],"between":[198],"graders":[200],"LLMs":[202],"might":[205],"combine":[206],"their":[207,212],"unique":[208],"strengths":[209],"mitigating":[211],"respective":[213],"shortcomings":[214],"direction,":[217],"it":[218],"imperative":[220],"consider":[222],"implementing":[223],"transparency,":[224],"fairness,":[225],"appropriate":[227],"regulations":[228],"near":[231],"future.":[232]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":5}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}
