{"id":"https://openalex.org/W4415927745","doi":"https://doi.org/10.63317/3cy68duew55b","title":"DialectalArabicMMLU: Benchmarking Dialectal Capabilities in Arabic and Multilingual Language Models","display_name":"DialectalArabicMMLU: Benchmarking Dialectal Capabilities in Arabic and Multilingual Language Models","publication_year":2026,"publication_date":"2026-04-30","ids":{"openalex":"https://openalex.org/W4415927745","doi":"https://doi.org/10.63317/3cy68duew55b"},"language":null,"primary_location":{"id":"doi:10.63317/3cy68duew55b","is_oa":false,"landing_page_url":"https://doi.org/10.63317/3cy68duew55b","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2510.27543","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070510731","display_name":"Malik H. Altakrori","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Malik H. Altakrori","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084517393","display_name":"Nizar Habash","orcid":"https://orcid.org/0000-0002-1831-3457"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nizar Habash","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Teresa Lynn","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Teresa Lynn","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086381528","display_name":"Younes Samih","orcid":"https://orcid.org/0000-0002-0485-7920"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Younes Samih","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Abed Alhakim Freihat","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abed Alhakim Freihat","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5117865139","display_name":"Kirill Chirkunov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kirill Chirkunov","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011321118","display_name":"Muhammed AbuOdeh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Muhammed AbuOdeh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113515054","display_name":"Radu Florian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Radu Florian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012055259","display_name":"Preslav Nakov","orcid":"https://orcid.org/0000-0002-3600-1510"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Preslav Nakov","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5112924039","display_name":"Alham Fikri Aji","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alham Fikri Aji","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":0.01819574,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3199","last_page":"3219"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.33500000834465027,"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":0.33500000834465027,"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":0.2070000022649765,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.05559999868273735,"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/benchmarking","display_name":"Benchmarking","score":0.7465000152587891},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6448000073432922},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.6014000177383423},{"id":"https://openalex.org/keywords/modern-standard-arabic","display_name":"Modern Standard Arabic","score":0.541700005531311},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.476500004529953},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.4618000090122223},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.42260000109672546},{"id":"https://openalex.org/keywords/computational-linguistics","display_name":"Computational linguistics","score":0.36070001125335693}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7465000152587891},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6448000073432922},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6446999907493591},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.6014000177383423},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5625},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5605000257492065},{"id":"https://openalex.org/C2778243841","wikidata":"https://www.wikidata.org/wiki/Q56467","display_name":"Modern Standard Arabic","level":3,"score":0.541700005531311},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.476500004529953},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.4618000090122223},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45820000767707825},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.42260000109672546},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.36070001125335693},{"id":"https://openalex.org/C2778143727","wikidata":"https://www.wikidata.org/wiki/Q1820650","display_name":"Readability","level":2,"score":0.30720001459121704},{"id":"https://openalex.org/C2778883600","wikidata":"https://www.wikidata.org/wiki/Q2390977","display_name":"Language proficiency","level":2,"score":0.30640000104904175},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.3059999942779541},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.296099990606308},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.2913999855518341},{"id":"https://openalex.org/C132165367","wikidata":"https://www.wikidata.org/wiki/Q34049","display_name":"Semitic languages","level":3,"score":0.2644999921321869},{"id":"https://openalex.org/C2780035574","wikidata":"https://www.wikidata.org/wiki/Q30081","display_name":"Multilingualism","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C122783720","wikidata":"https://www.wikidata.org/wiki/Q183065","display_name":"Interpreter","level":2,"score":0.25949999690055847}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.63317/3cy68duew55b","is_oa":false,"landing_page_url":"https://doi.org/10.63317/3cy68duew55b","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.27543","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.27543","pdf_url":"https://arxiv.org/pdf/2510.27543","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2510.27543","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.27543","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"pmh:oai:arXiv.org:2510.27543","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.27543","pdf_url":"https://arxiv.org/pdf/2510.27543","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,109],"present":[1],"DialectalArabicMMLU,":[2],"a":[3,70],"new":[4],"benchmark":[5,92],"for":[6,29,139],"evaluating":[7],"the":[8,46,134],"performance":[9,122],"of":[10,54,72,96],"large":[11],"language":[12],"models":[13],"(LLMs)":[14],"across":[15,76,124],"Arabic":[16,21,32,113],"dialects.":[17],"While":[18],"recently":[19],"developed":[20],"and":[22,52,67,79,89,99,106,114,119,150],"multilingual":[23,115],"benchmarks":[24],"have":[25],"advanced":[26],"LLM":[27,97],"evaluation":[28,149],"Modern":[30],"Standard":[31],"(MSA),":[33],"dialectal":[34,130,141],"varieties":[35],"remain":[36],"underrepresented":[37],"despite":[38],"their":[39],"prevalence":[40],"in":[41,129,143],"everyday":[42],"communication.":[43],"DialectalArabicMMLU":[44,132],"extends":[45],"MMLU-Redux":[47],"framework":[48],"through":[49],"manual":[50],"translation":[51],"adaptation":[53],"3K":[55],"multiple-choice":[56],"question-answer":[57],"pairs":[58,75,84],"into":[59],"five":[60],"major":[61],"dialects":[62],"(Syrian,":[63],"Egyptian,":[64],"Emirati,":[65],"Saudi,":[66],"Moroccan),":[68],"yielding":[69],"total":[71],"15K":[73],"QA":[74,83],"32":[77],"academic":[78],"professional":[80],"domains":[81],"(22K":[82],"when":[85],"also":[86],"including":[87],"English":[88],"MSA).":[90],"The":[91],"enables":[93],"systematic":[94],"assessment":[95],"reasoning":[98],"comprehension":[100],"beyond":[101],"MSA,":[102],"supporting":[103],"both":[104],"task-based":[105],"linguistic":[107],"analysis.":[108],"evaluate":[110],"19":[111],"open-weight":[112],"LLMs":[116],"(1B-13B":[117],"parameters)":[118],"report":[120],"substantial":[121],"variation":[123],"dialects,":[125],"revealing":[126],"persistent":[127],"gaps":[128],"generalization.":[131],"provides":[133],"first":[135],"unified,":[136],"human-curated":[137],"resource":[138],"measuring":[140],"understanding":[142],"Arabic,":[144],"thus":[145],"promoting":[146],"more":[147],"inclusive":[148],"future":[151],"model":[152],"development.":[153]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-11-05T00:00:00"}
