{"id":"https://openalex.org/W4412889161","doi":"https://doi.org/10.18653/v1/2025.bea-1.95","title":"MSA at BEA 2025 Shared Task: Disagreement-Aware Instruction Tuning for Multi-Dimensional Evaluation of LLMs as Math Tutors","display_name":"MSA at BEA 2025 Shared Task: Disagreement-Aware Instruction Tuning for Multi-Dimensional Evaluation of LLMs as Math Tutors","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412889161","doi":"https://doi.org/10.18653/v1/2025.bea-1.95"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.bea-1.95","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.bea-1.95","pdf_url":"https://aclanthology.org/2025.bea-1.95.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-1.95.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5115505658","display_name":"Baraa Hikal","orcid":null},"institutions":[{"id":"https://openalex.org/I145487455","display_name":"Cairo University","ror":"https://ror.org/03q21mh05","country_code":"EG","type":"education","lineage":["https://openalex.org/I145487455"]},{"id":"https://openalex.org/I895027328","display_name":"October University of Modern Sciences and Arts","ror":"https://ror.org/01nvnhx40","country_code":"EG","type":"education","lineage":["https://openalex.org/I895027328"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Baraa Hikal","raw_affiliation_strings":["Faculty of Computer Science , MSA University , Egypt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science , MSA University , Egypt","institution_ids":["https://openalex.org/I145487455","https://openalex.org/I895027328"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115505656","display_name":"Mohamed Basem","orcid":null},"institutions":[{"id":"https://openalex.org/I145487455","display_name":"Cairo University","ror":"https://ror.org/03q21mh05","country_code":"EG","type":"education","lineage":["https://openalex.org/I145487455"]},{"id":"https://openalex.org/I895027328","display_name":"October University of Modern Sciences and Arts","ror":"https://ror.org/01nvnhx40","country_code":"EG","type":"education","lineage":["https://openalex.org/I895027328"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Mohamed Basem","raw_affiliation_strings":["Faculty of Computer Science , MSA University , Egypt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science , MSA University , Egypt","institution_ids":["https://openalex.org/I145487455","https://openalex.org/I895027328"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115505657","display_name":"Islam Oshallah","orcid":null},"institutions":[{"id":"https://openalex.org/I145487455","display_name":"Cairo University","ror":"https://ror.org/03q21mh05","country_code":"EG","type":"education","lineage":["https://openalex.org/I145487455"]},{"id":"https://openalex.org/I895027328","display_name":"October University of Modern Sciences and Arts","ror":"https://ror.org/01nvnhx40","country_code":"EG","type":"education","lineage":["https://openalex.org/I895027328"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Islam Oshallah","raw_affiliation_strings":["Faculty of Computer Science , MSA University , Egypt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science , MSA University , Egypt","institution_ids":["https://openalex.org/I145487455","https://openalex.org/I895027328"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030894498","display_name":"Ali Hamdi","orcid":"https://orcid.org/0000-0002-2301-6588"},"institutions":[{"id":"https://openalex.org/I145487455","display_name":"Cairo University","ror":"https://ror.org/03q21mh05","country_code":"EG","type":"education","lineage":["https://openalex.org/I145487455"]},{"id":"https://openalex.org/I895027328","display_name":"October University of Modern Sciences and Arts","ror":"https://ror.org/01nvnhx40","country_code":"EG","type":"education","lineage":["https://openalex.org/I895027328"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Ali Hamdi","raw_affiliation_strings":["Faculty of Computer Science , MSA University , Egypt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science , MSA University , Egypt","institution_ids":["https://openalex.org/I145487455","https://openalex.org/I895027328"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.83483219,"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":"1194","last_page":"1202"},"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":0.98089998960495,"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":0.98089998960495,"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/T11122","display_name":"Online Learning and Analytics","score":0.9532999992370605,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9156000018119812,"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":0.7455058693885803},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5362588167190552},{"id":"https://openalex.org/keywords/mathematics-education","display_name":"Mathematics education","score":0.4999995231628418},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3334699273109436},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.3330156207084656},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.08735084533691406},{"id":"https://openalex.org/keywords/management","display_name":"Management","score":0.08359363675117493}],"concepts":[{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7455058693885803},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5362588167190552},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.4999995231628418},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3334699273109436},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3330156207084656},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.08735084533691406},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.08359363675117493}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.bea-1.95","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.bea-1.95","pdf_url":"https://aclanthology.org/2025.bea-1.95.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-1.95","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.bea-1.95","pdf_url":"https://aclanthology.org/2025.bea-1.95.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","id":"https://metadata.un.org/sdg/4","score":0.6800000071525574}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412889161.pdf","grobid_xml":"https://content.openalex.org/works/W4412889161.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/W4211075255"],"abstract_inverted_index":{"We":[0],"present":[1],"MSA-MATHEVAL,":[2],"our":[3],"submission":[4],"to":[5,34],"the":[6,94],"BEA":[7],"2025":[8],"Shared":[9],"Task":[10],"on":[11],"evaluating":[12],"AI":[13],"tutor":[14],"responses":[15],"across":[16,41,69],"four":[17],"instructional":[18],"dimensions:":[19],"Mistake":[20,22,87,90],"Identification,":[21],"Location,":[23],"Providing":[24,76],"Guidance,":[25,77],"and":[26,82,89,100],"Actionability.Our":[27],"approach":[28],"uses":[29],"a":[30,36,54],"unified":[31],"training":[32],"pipeline":[33],"fine-tune":[35],"single":[37],"instructiontuned":[38],"language":[39],"model":[40],"all":[42,70],"tracks,":[43,71],"without":[44],"any":[45],"task-specific":[46],"architecture":[47],"modifications.To":[48],"improve":[49],"prediction":[50],"reliability,":[51],"we":[52],"introduce":[53],"disagreement-aware":[55],"ensemble":[56],"inference":[57],"strategy":[58],"that":[59],"enhances":[60],"coverage":[61],"of":[62,96,107],"minority":[63],"labels.Our":[64],"system":[65],"achieves":[66],"strong":[67],"performance":[68],"ranking":[72],"1":[73],"st":[74],"in":[75,80,85],"3":[78],"rd":[79],"Actionability,":[81],"4":[83],"th":[84],"both":[86],"Identification":[88],"Location.These":[91],"results":[92],"demonstrate":[93],"effectiveness":[95],"scalable":[97],"instruction":[98],"tuning":[99],"disagreementdriven":[101],"modeling":[102],"for":[103],"robust,":[104],"multi-dimensional":[105],"evaluation":[106],"LLMs":[108],"as":[109],"educational":[110],"tutors.":[111]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
