{"id":"https://openalex.org/W4412889189","doi":"https://doi.org/10.18653/v1/2025.bea-1.90","title":"K-NLPers at BEA 2025 Shared Task: Evaluating the Quality of AI Tutor Responses with GPT-4.1","display_name":"K-NLPers at BEA 2025 Shared Task: Evaluating the Quality of AI Tutor Responses with GPT-4.1","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412889189","doi":"https://doi.org/10.18653/v1/2025.bea-1.90"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.bea-1.90","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.bea-1.90","pdf_url":"https://aclanthology.org/2025.bea-1.90.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-1.90.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101640227","display_name":"Geon Park","orcid":"https://orcid.org/0000-0002-6878-2649"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Geon Park","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Jiwoo Song","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiwoo Song","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085374559","display_name":"Gihyeon Choi","orcid":"https://orcid.org/0000-0002-6108-6755"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gihyeon Choi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Juoh Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Juoh Sun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5022865376","display_name":"Harksoo Kim","orcid":"https://orcid.org/0000-0002-8286-7198"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Harksoo Kim","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":0.83489429,"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":"1145","last_page":"1163"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9836000204086304,"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/T10028","display_name":"Topic Modeling","score":0.9836000204086304,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.9728000164031982,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.9598000049591064,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/tutor","display_name":"TUTOR","score":0.9130111932754517},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6992383599281311},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6493855714797974},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5844166278839111},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.37899988889694214},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.32522666454315186},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1296115219593048},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12307906150817871},{"id":"https://openalex.org/keywords/epistemology","display_name":"Epistemology","score":0.060499221086502075}],"concepts":[{"id":"https://openalex.org/C2778371403","wikidata":"https://www.wikidata.org/wiki/Q7672049","display_name":"TUTOR","level":2,"score":0.9130111932754517},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6992383599281311},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6493855714797974},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5844166278839111},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.37899988889694214},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.32522666454315186},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1296115219593048},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12307906150817871},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.060499221086502075},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.bea-1.90","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.bea-1.90","pdf_url":"https://aclanthology.org/2025.bea-1.90.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-1.90","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.bea-1.90","pdf_url":"https://aclanthology.org/2025.bea-1.90.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":[{"display_name":"Quality Education","score":0.6200000047683716,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1448736063","display_name":null,"funder_award_id":"RS-2023-00216011","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412889189.pdf","grobid_xml":"https://content.openalex.org/works/W4412889189.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2478195092","https://openalex.org/W4312351362","https://openalex.org/W2362145073","https://openalex.org/W2358338760","https://openalex.org/W183073912","https://openalex.org/W2119729863","https://openalex.org/W2887971028","https://openalex.org/W2501172308","https://openalex.org/W3196817267","https://openalex.org/W1976600725"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"automatic":[3,154],"evaluation":[4,68,87,109,155],"systems":[5,20,92,110,139,156],"for":[6,168],"assessing":[7],"the":[8,39,48,85,98,104,121,126,135,138,144,147,160],"pedagogical":[9],"capabilities":[10,73],"of":[11,26,42,101,117,162],"LLM-based":[12],"AI":[13,170],"tutors.Drawing":[14],"from":[15,44],"a":[16],"shared":[17],"task,":[18],"our":[19,108,152],"specifically":[21],"target":[22],"four":[23],"key":[24],"dimensions":[25,37],"tutor":[27,163,171],"responses:":[28],"Mistake":[29,31,105],"Identification,":[30],"Location,":[32],"Providing":[33,127],"Guidance,":[34],"and":[35,62,79,124],"Actionability.These":[36],"capture":[38],"educational":[40],"quality":[41,161],"responses":[43],"multiple":[45],"perspectives,":[46],"including":[47],"ability":[49],"to":[50,83],"detect":[51],"student":[52],"mistakes,":[53],"accurately":[54],"identify":[55],"error":[56],"locations,":[57],"provide":[58],"effective":[59],"instructional":[60],"guidance,":[61],"offer":[63],"actionable":[64],"feedback.We":[65],"propose":[66],"GPT-4.1-basedautomatic":[67],"systems,":[69],"leveraging":[70],"their":[71,166],"strong":[72],"in":[74,120,125,134,143],"comprehending":[75],"diverse":[76],"linguistic":[77],"expressions":[78],"complex":[80],"conversational":[81],"contexts":[82],"address":[84],"detailed":[86],"criteria":[88,100],"across":[89],"these":[90],"dimensions.Our":[91],"were":[93],"quantitatively":[94],"evaluated":[95],"based":[96],"on":[97],"official":[99],"each":[102],"track.In":[103],"Location":[106],"track,":[107,129],"achieved":[111,131],"an":[112],"Exact":[113],"macro":[114],"F1":[115],"score":[116],"58.80%":[118],"(ranked":[119,133],"top":[122,136],"3),":[123],"Guidance":[128],"they":[130],"56.06%":[132],"5).While":[137],"showed":[140],"mid-range":[141],"performance":[142],"remaining":[145],"tracks,":[146],"overall":[148],"results":[149],"demonstrate":[150],"that":[151],"proposed":[153],"can":[157],"effectively":[158],"assess":[159],"responses,":[164],"highlighting":[165],"potential":[167],"evaluating":[169],"effectiveness.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
