{"id":"https://openalex.org/W4412889214","doi":"https://doi.org/10.18653/v1/2025.bea-1.80","title":"bea-jh at BEA 2025 Shared Task: Evaluating AI-powered Tutors through Pedagogically-Informed Reasoning","display_name":"bea-jh at BEA 2025 Shared Task: Evaluating AI-powered Tutors through Pedagogically-Informed Reasoning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412889214","doi":"https://doi.org/10.18653/v1/2025.bea-1.80"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.bea-1.80","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.bea-1.80","pdf_url":"https://aclanthology.org/2025.bea-1.80.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-1.80.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060809042","display_name":"Jihyeon Roh","orcid":"https://orcid.org/0000-0002-1708-7259"},"institutions":[{"id":"https://openalex.org/I4210120608","display_name":"Seoil University","ror":"https://ror.org/01wf22864","country_code":"KR","type":"education","lineage":["https://openalex.org/I4210120608"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jihyeon Roh","raw_affiliation_strings":["Kakao 166 , Pangyoyeok-ro , Bundang-gu , Seongnam-si , Gyeonggi-do , 13529 , Korea Samsung Research 56 Seongchon-gil , Seocho-gu , Seoul , 06765 , Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kakao 166 , Pangyoyeok-ro , Bundang-gu , Seongnam-si , Gyeonggi-do , 13529 , Korea Samsung Research 56 Seongchon-gil , Seocho-gu , Seoul , 06765 , Korea","institution_ids":["https://openalex.org/I4210120608"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022232094","display_name":"Jinhyun Bang","orcid":"https://orcid.org/0000-0001-9505-8595"},"institutions":[{"id":"https://openalex.org/I4210120608","display_name":"Seoil University","ror":"https://ror.org/01wf22864","country_code":"KR","type":"education","lineage":["https://openalex.org/I4210120608"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jinhyun Bang","raw_affiliation_strings":["Kakao 166 , Pangyoyeok-ro , Bundang-gu , Seongnam-si , Gyeonggi-do , 13529 , Korea Samsung Research 56 Seongchon-gil , Seocho-gu , Seoul , 06765 , Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kakao 166 , Pangyoyeok-ro , Bundang-gu , Seongnam-si , Gyeonggi-do , 13529 , Korea Samsung Research 56 Seongchon-gil , Seocho-gu , Seoul , 06765 , Korea","institution_ids":["https://openalex.org/I4210120608"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210120608"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14571195,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1049","last_page":"1059"},"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":0.9818999767303467,"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":0.9818999767303467,"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/task","display_name":"Task (project management)","score":0.7197321653366089},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6354047060012817},{"id":"https://openalex.org/keywords/mathematics-education","display_name":"Mathematics education","score":0.42107006907463074},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33670732378959656},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.23723703622817993},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11362522840499878},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.07659828662872314}],"concepts":[{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7197321653366089},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6354047060012817},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.42107006907463074},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33670732378959656},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.23723703622817993},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11362522840499878},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.07659828662872314}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.bea-1.80","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.bea-1.80","pdf_url":"https://aclanthology.org/2025.bea-1.80.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-1.80","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.bea-1.80","pdf_url":"https://aclanthology.org/2025.bea-1.80.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":[{"score":0.47999998927116394,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412889214.pdf","grobid_xml":"https://content.openalex.org/works/W4412889214.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":{"The":[0],"growing":[1],"use":[2],"of":[3,19,134,165,174],"large":[4],"language":[5],"models":[6,94,116,126],"(LLMs)":[7],"for":[8,16,68,170],"AI-powered":[9],"tutors":[10],"in":[11,40,71,98,131,142,147,151],"education":[12],"highlights":[13],"the":[14,119,152,158,163,172],"need":[15],"reliable":[17],"evaluation":[18,29,50,97],"their":[20,69],"pedagogical":[21,33],"abilities.In":[22],"this":[23],"work,":[24],"we":[25],"propose":[26],"a":[27,48,83],"reasoning-based":[28],"methodology":[30],"that":[31,113],"leverages":[32],"domain":[34],"knowledge":[35],"to":[36,56,88,92,95],"assess":[37],"LLM-generated":[38],"feedback":[39,176],"mathematical":[41],"dialogues":[42],"while":[43],"providing":[44],"insights":[45],"into":[46],"why":[47],"particular":[49],"is":[51],"given.We":[52],"design":[53],"structured":[54],"prompts":[55],"invoke":[57],"pedagogically-informed":[58],"reasoning":[59,90],"from":[60],"LLMs":[61],"and":[62,74,109,122,124,144],"compare":[63],"base":[64,120],"model":[65,121],"candidates":[66],"selected":[67],"strengths":[70],"reasoning,":[72],"mathematics,":[73],"overall":[75],"instruction-following.We":[76],"employ":[77],"Group":[78],"Relative":[79],"Policy":[80],"Optimization":[81],"(GRPO),":[82],"reinforcement":[84],"learning":[85],"method":[86,138],"known":[87],"improve":[89],"performance,":[91],"train":[93],"perform":[96],"four":[99,135],"pedagogically":[100,167],"motivated":[101],"dimensions,":[102],"Mistake":[103,105],"Identification,":[104],"Location,":[106],"Providing":[107],"Guidance,":[108],"Actionability.Experimental":[110],"results":[111],"show":[112],"our":[114,137],"GRPO-based":[115],"consistently":[117],"outperform":[118],"GPT-4.1,":[123],"surpass":[125],"trained":[127],"using":[128],"supervised":[129],"finetuning":[130],"three":[132],"out":[133],"dimensions.Notably,":[136],"achieved":[139],"top-ranked":[140],"performance":[141,146],"Actionability":[143],"competitive":[145],"two":[148],"other":[149],"dimensions":[150],"BEA":[153],"2025":[154],"Shared":[155],"Task":[156],"under":[157],"team":[159],"name":[160],"bea-jh,":[161],"underscoring":[162],"value":[164],"generating":[166],"grounded":[168],"rationales":[169],"improving":[171],"quality":[173],"educational":[175],"evaluation.":[177]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
