{"id":"https://openalex.org/W7155525670","doi":"https://doi.org/10.48550/arxiv.2604.20996","title":"AFRILANGTUTOR: Advancing Language Tutoring and Culture Education in Low-Resource Languages with Large Language Models","display_name":"AFRILANGTUTOR: Advancing Language Tutoring and Culture Education in Low-Resource Languages with Large Language Models","publication_year":2026,"publication_date":"2026-04-22","ids":{"openalex":"https://openalex.org/W7155525670","doi":"https://doi.org/10.48550/arxiv.2604.20996"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.20996","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.20996","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.20996","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040546523","display_name":"Tadesse Destaw Belay","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Belay, Tadesse Destaw","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120721021","display_name":"Shahriar Kabir Nahin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nahin, Shahriar Kabir","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134514941","display_name":"Israel Abebe Azime","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Azime, Israel Abebe","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014340264","display_name":"Ocean Monjur","orcid":"https://orcid.org/0000-0003-1526-6808"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Monjur, Ocean","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134531965","display_name":"Shamsuddeen Hassan Muhammad","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rei, Marek","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134491455","display_name":"Seid Muhie Yimam","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Biemann, Chris","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134539284","display_name":"Anshuman Chhabra","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Muhammad, Shamsuddeen Hassan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yimam, Seid Muhie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yimam, Seid Muhie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Chhabra, Anshuman","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chhabra, Anshuman","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":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.19439999759197235,"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":0.19439999759197235,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.1216999962925911,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.11389999836683273,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/construct","display_name":"Construct (python library)","score":0.5284000039100647},{"id":"https://openalex.org/keywords/constructed-language","display_name":"Constructed language","score":0.4325999915599823},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4253000020980835},{"id":"https://openalex.org/keywords/languages-of-africa","display_name":"Languages of Africa","score":0.41530001163482666},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.3671000003814697},{"id":"https://openalex.org/keywords/computational-linguistics","display_name":"Computational linguistics","score":0.36419999599456787},{"id":"https://openalex.org/keywords/language-acquisition","display_name":"Language acquisition","score":0.36169999837875366}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7653999924659729},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5284000039100647},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5253000259399414},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4945000112056732},{"id":"https://openalex.org/C94922259","wikidata":"https://www.wikidata.org/wiki/Q33215","display_name":"Constructed language","level":2,"score":0.4325999915599823},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4253000020980835},{"id":"https://openalex.org/C108494575","wikidata":"https://www.wikidata.org/wiki/Q207930","display_name":"Languages of Africa","level":2,"score":0.41530001163482666},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.3671000003814697},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.36419999599456787},{"id":"https://openalex.org/C74672266","wikidata":"https://www.wikidata.org/wiki/Q815859","display_name":"Language acquisition","level":2,"score":0.36169999837875366},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.3531000018119812},{"id":"https://openalex.org/C85847156","wikidata":"https://www.wikidata.org/wiki/Q59015987","display_name":"Verifiable secret sharing","level":3,"score":0.35190001130104065},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3425999879837036},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.3068999946117401},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.29789999127388},{"id":"https://openalex.org/C171041071","wikidata":"https://www.wikidata.org/wiki/Q36870","display_name":"First language","level":2,"score":0.2558000087738037}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.20996","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.20996","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.20996","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.20996","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8005316853523254}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"How":[0],"can":[1],"language":[2,78,105],"learning":[3],"systems":[4,30],"be":[5],"developed":[6],"for":[7,58,75,92],"languages":[8,126],"that":[9,134],"lack":[10],"sufficient":[11],"training":[12,76,90],"resources?":[13],"This":[14],"challenge":[15],"is":[16],"increasingly":[17],"faced":[18],"by":[19],"developers":[20],"across":[21,123,162],"the":[22],"African":[23,50,125],"continent":[24],"who":[25],"aim":[26],"to":[27,64,110,157],"build":[28,83],"AI":[29],"capable":[31],"of":[32,48,87],"understanding":[33],"and":[34,69,96,119,127,144,147],"responding":[35],"in":[36],"local":[37],"languages.":[38],"To":[39,165],"address":[40],"this":[41],"gap,":[42],"we":[43,82,103],"introduce":[44],"AFRILANGDICT,":[45,81],"a":[46,85],"collection":[47],"194.7K":[49],"language-English":[51],"dictionary":[52],"entries":[53],"designed":[54],"as":[55,111],"seed":[56],"resources":[57,173],"generating":[59],"language-learning":[60],"materials,":[61],"enabling":[62],"us":[63],"automatically":[65],"construct":[66],"large-scale,":[67],"diverse,":[68],"verifiable":[70],"student-tutor":[71],"question-answer":[72],"interactions":[73],"suitable":[74],"AI-assisted":[77],"tutors.":[79],"Using":[80,101],"AFRILANGEDU,":[84,102],"dataset":[86],"78.9K":[88],"multi-turn":[89],"examples":[91],"Supervised":[93],"Fine-Tuning":[94],"(SFT)":[95],"Direct":[97],"Preference":[98],"Optimization":[99],"(DPO).":[100],"train":[104],"tutoring":[106],"models":[107,135],"collectively":[108],"referred":[109],"AFRILANGTUTOR.":[112],"We":[113],"fine-tune":[114],"two":[115],"multilingual":[116],"LLMs:":[117],"Llama-3-8B-IT":[118],"Gemma-3-12B-IT":[120],"on":[121,137,169],"AFRILANGEDU":[122,138],"10":[124],"evaluate":[128],"their":[129,141],"performance.":[130],"Our":[131],"results":[132],"show":[133],"trained":[136],"consistently":[139],"outperform":[140],"base":[142],"counterparts,":[143],"combining":[145],"SFT":[146],"DPO":[148],"yields":[149],"substantial":[150],"improvements,":[151],"with":[152],"gains":[153],"ranging":[154],"from":[155],"1.8%":[156],"15.5%":[158],"under":[159],"LLM-as-a-judge":[160],"evaluations":[161],"four":[163],"criteria.":[164],"facilitate":[166],"further":[167],"research":[168],"low-resource":[170],"languages,":[171],"all":[172],"are":[174],"available":[175],"at":[176],"https://huggingface.co/afrilang-edu.":[177]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-25T00:00:00"}
