{"id":"https://openalex.org/W4412889220","doi":"https://doi.org/10.18653/v1/2025.bea-1.96","title":"TutorMind at BEA 2025 Shared Task: Leveraging Fine-Tuned LLMs and Data Augmentation for Mistake Identification","display_name":"TutorMind at BEA 2025 Shared Task: Leveraging Fine-Tuned LLMs and Data Augmentation for Mistake Identification","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412889220","doi":"https://doi.org/10.18653/v1/2025.bea-1.96"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.bea-1.96","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.bea-1.96","pdf_url":"https://aclanthology.org/2025.bea-1.96.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-1.96.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119181643","display_name":"Fatima Dekmak","orcid":null},"institutions":[{"id":"https://openalex.org/I98635879","display_name":"American University of Beirut","ror":"https://ror.org/04pznsd21","country_code":"LB","type":"education","lineage":["https://openalex.org/I98635879"]}],"countries":["LB"],"is_corresponding":false,"raw_author_name":"Fatima Dekmak","raw_affiliation_strings":["American University of Beirut Beirut , Lebanon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"American University of Beirut Beirut , Lebanon","institution_ids":["https://openalex.org/I98635879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008696387","display_name":"Christian Khairallah","orcid":null},"institutions":[{"id":"https://openalex.org/I2801277386","display_name":"Emirates Foundation","ror":"https://ror.org/05nd26619","country_code":"AE","type":"other","lineage":["https://openalex.org/I2801277386"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Christian Khairallah","raw_affiliation_strings":["Aralects Abu Dhabi , United Arab Emirates"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aralects Abu Dhabi , United Arab Emirates","institution_ids":["https://openalex.org/I2801277386"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050749439","display_name":"Wissam Antoun","orcid":"https://orcid.org/0000-0001-8021-5834"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Wissam Antoun","raw_affiliation_strings":["INRIA France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA France","institution_ids":["https://openalex.org/I1326498283"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14575335,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1203","last_page":"1211"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9555000066757202,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9555000066757202,"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/T10028","display_name":"Topic Modeling","score":0.9099000096321106,"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.9027000069618225,"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/mistake","display_name":"Mistake","score":0.9271615743637085},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7279013991355896},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6875673532485962},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5535387396812439},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.3872738480567932},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.11349338293075562},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.09715321660041809},{"id":"https://openalex.org/keywords/law","display_name":"Law","score":0.0697450339794159},{"id":"https://openalex.org/keywords/management","display_name":"Management","score":0.06540831923484802}],"concepts":[{"id":"https://openalex.org/C2777179996","wikidata":"https://www.wikidata.org/wiki/Q911222","display_name":"Mistake","level":2,"score":0.9271615743637085},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7279013991355896},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6875673532485962},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5535387396812439},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.3872738480567932},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.11349338293075562},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.09715321660041809},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0697450339794159},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.06540831923484802},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2025.bea-1.96","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.bea-1.96","pdf_url":"https://aclanthology.org/2025.bea-1.96.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"},{"id":"pmh:oai:HAL:hal-05448906v1","is_oa":true,"landing_page_url":"https://hal.science/hal-05448906","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BEA 2025 - 20th Workshop on Innovative Use of NLP for Building Educational Applications, Jul 2025, Vienna, Austria. pp.1203-1211, &#x27E8;10.18653/v1/2025.bea-1.96&#x27E9;","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.bea-1.96","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.bea-1.96","pdf_url":"https://aclanthology.org/2025.bea-1.96.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":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412889220.pdf","grobid_xml":"https://content.openalex.org/works/W4412889220.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/W1590719878","https://openalex.org/W4244271513","https://openalex.org/W2365974527","https://openalex.org/W4306382224","https://openalex.org/W4226517682","https://openalex.org/W3108263396","https://openalex.org/W2913111867"],"abstract_inverted_index":{"In":[0],"light":[1],"of":[2,6,34,45,101,113],"the":[3,30,35,43,74,91,106,111],"growing":[4],"adoption":[5],"large":[7],"language":[8],"models":[9],"(LLMs)":[10],"as":[11],"educational":[12],"tutors,":[13],"it":[14],"is":[15],"crucial":[16],"to":[17,41],"effectively":[18],"evaluate":[19],"their":[20],"pedagogical":[21,131],"capabilities":[22],"across":[23],"multiple":[24],"dimensions.Toward":[25],"this":[26],"goal,":[27],"we":[28,72],"address":[29,69],"Mistake":[31],"Identification":[32],"sub-task":[33],"BEA":[36],"2025":[37],"Shared":[38],"task,":[39],"aiming":[40],"assess":[42],"accuracy":[44],"tutors":[46],"in":[47,63,105],"detecting":[48],"and":[49,60,66,118],"identifying":[50],"student":[51],"errors.We":[52],"experiment":[53],"with":[54,77],"several":[55],"LLMs,":[56],"including":[57],"GPT-4o-mini,":[58],"Mistral-7B,":[59],"Llama-3.1-8B,evaluating":[61],"them":[62],"both":[64],"zero-shot":[65],"fine-tuned":[67,89],"settings.To":[68],"class":[70],"imbalance,":[71],"augment":[73],"training":[75],"data":[76,117,122],"synthetic":[78],"examples,":[79],"targeting":[80],"underrepresented":[81],"labels,":[82],"generated":[83],"by":[84],"Command":[85],"R+.Our":[86],"GPT-4o":[87],"model":[88],"on":[90,115,129],"full":[92],"development":[93],"set":[94],"achieves":[95],"a":[96],"strict":[97],"macro-averaged":[98],"F1":[99],"score":[100],"71.63%,":[102],"ranking":[103],"second":[104],"shared":[107],"task.Our":[108],"work":[109],"highlights":[110],"effectiveness":[112],"fine-tuning":[114],"task-specific":[116],"suggests":[119],"that":[120],"targeted":[121],"augmentation":[123],"can":[124],"further":[125],"support":[126],"LLM":[127],"performance":[128],"nuanced":[130],"evaluation":[132],"tasks.":[133]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
