{"id":"https://openalex.org/W7166847697","doi":"https://doi.org/10.18653/v1/2026.acl-long.267","title":"AfriqueLLM: How Data Mixing and Model Architecture Impact Continued Pre-training for African Languages","display_name":"AfriqueLLM: How Data Mixing and Model Architecture Impact Continued Pre-training for African Languages","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166847697","doi":"https://doi.org/10.18653/v1/2026.acl-long.267"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.267","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.267","pdf_url":"https://aclanthology.org/2026.acl-long.267.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.267.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139752515","display_name":"Hao Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139830503","display_name":"Tianyi Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianyi Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139747035","display_name":"Michael A. Hedderich","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael A. Hedderich","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139760354","display_name":"Wassim Hamidouche","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wassim Hamidouche","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060899114","display_name":"Syed Waqas Zamir","orcid":"https://orcid.org/0000-0002-7198-0187"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Syed Waqas Zamir","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139715280","display_name":"David Ifeoluwa Adelani","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Ifeoluwa Adelani","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.83753591,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5909","last_page":"5928"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.36739999055862427,"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":0.36739999055862427,"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":0.06679999828338623,"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/T13194","display_name":"ICT in Developing Communities","score":0.02539999969303608,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/mixing","display_name":"Mixing (physics)","score":0.4648999869823456},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4368000030517578},{"id":"https://openalex.org/keywords/languages-of-africa","display_name":"Languages of Africa","score":0.4260999858379364},{"id":"https://openalex.org/keywords/association","display_name":"Association (psychology)","score":0.35040000081062317},{"id":"https://openalex.org/keywords/computational-linguistics","display_name":"Computational linguistics","score":0.33649998903274536}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5724999904632568},{"id":"https://openalex.org/C138777275","wikidata":"https://www.wikidata.org/wiki/Q6884054","display_name":"Mixing (physics)","level":2,"score":0.4648999869823456},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4368000030517578},{"id":"https://openalex.org/C108494575","wikidata":"https://www.wikidata.org/wiki/Q207930","display_name":"Languages of Africa","level":2,"score":0.4260999858379364},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.42239999771118164},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.35040000081062317},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.33649998903274536},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33059999346733093},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.298799991607666},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.28790000081062317},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.28299999237060547},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.2676999866962433}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.267","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.267","pdf_url":"https://aclanthology.org/2026.acl-long.267.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.267","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.267","pdf_url":"https://aclanthology.org/2026.acl-long.267.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8289564847946167}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166847697.pdf","grobid_xml":"https://content.openalex.org/works/W7166847697.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Hao":[0],"Yu,":[1],"Tianyi":[2],"Xu,":[3],"Michael":[4],"A.":[5],"Hedderich,":[6],"Wassim":[7],"Hamidouche,":[8],"Syed":[9],"Waqas":[10],"Zamir,":[11],"David":[12],"Ifeoluwa":[13],"Adelani.":[14],"Proceedings":[15],"of":[16,21],"the":[17,22],"64th":[18],"Annual":[19],"Meeting":[20],"Association":[23],"for":[24],"Computational":[25],"Linguistics":[26],"(Volume":[27],"1:":[28],"Long":[29],"Papers).":[30],"2026.":[31]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}
