{"id":"https://openalex.org/W4414306244","doi":"https://doi.org/10.3389/frai.2025.1661789","title":"Cross-dialectal Arabic translation: comparative analysis on large language models","display_name":"Cross-dialectal Arabic translation: comparative analysis on large language models","publication_year":2025,"publication_date":"2025-09-18","ids":{"openalex":"https://openalex.org/W4414306244","doi":"https://doi.org/10.3389/frai.2025.1661789","pmid":"https://pubmed.ncbi.nlm.nih.gov/41050103"},"language":"en","primary_location":{"id":"doi:10.3389/frai.2025.1661789","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frai.2025.1661789","pdf_url":"https://www.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2025.1661789/pdf","source":{"id":"https://openalex.org/S4210197006","display_name":"Frontiers in Artificial Intelligence","issn_l":"2624-8212","issn":["2624-8212"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2025.1661789/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055000183","display_name":"Ayah Beidas","orcid":"https://orcid.org/0000-0002-5816-007X"},"institutions":[{"id":"https://openalex.org/I2799345387","display_name":"Kuwait Petroleum Corporation (Kuwait)","ror":"https://ror.org/04wacmk20","country_code":"KW","type":"company","lineage":["https://openalex.org/I2799345387"]},{"id":"https://openalex.org/I36721946","display_name":"Kuwait University","ror":"https://ror.org/021e5j056","country_code":"KW","type":"education","lineage":["https://openalex.org/I36721946"]}],"countries":["KW"],"is_corresponding":false,"raw_author_name":"Ayah Beidas","raw_affiliation_strings":["Computer Engineering Department, College of Engineering and Petroleum, Kuwait University, Kuwait City, Kuwait"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Engineering Department, College of Engineering and Petroleum, Kuwait University, Kuwait City, Kuwait","institution_ids":["https://openalex.org/I2799345387","https://openalex.org/I36721946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119660840","display_name":"Kousar Mohi","orcid":null},"institutions":[{"id":"https://openalex.org/I2799345387","display_name":"Kuwait Petroleum Corporation (Kuwait)","ror":"https://ror.org/04wacmk20","country_code":"KW","type":"company","lineage":["https://openalex.org/I2799345387"]},{"id":"https://openalex.org/I36721946","display_name":"Kuwait University","ror":"https://ror.org/021e5j056","country_code":"KW","type":"education","lineage":["https://openalex.org/I36721946"]}],"countries":["KW"],"is_corresponding":false,"raw_author_name":"Kousar Mohi","raw_affiliation_strings":["Computer Engineering Department, College of Engineering and Petroleum, Kuwait University, Kuwait City, Kuwait"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Engineering Department, College of Engineering and Petroleum, Kuwait University, Kuwait City, Kuwait","institution_ids":["https://openalex.org/I2799345387","https://openalex.org/I36721946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079454460","display_name":"Fatme Ghaddar","orcid":"https://orcid.org/0000-0003-0570-0527"},"institutions":[{"id":"https://openalex.org/I2799345387","display_name":"Kuwait Petroleum Corporation (Kuwait)","ror":"https://ror.org/04wacmk20","country_code":"KW","type":"company","lineage":["https://openalex.org/I2799345387"]},{"id":"https://openalex.org/I36721946","display_name":"Kuwait University","ror":"https://ror.org/021e5j056","country_code":"KW","type":"education","lineage":["https://openalex.org/I36721946"]}],"countries":["KW"],"is_corresponding":false,"raw_author_name":"Fatme Ghaddar","raw_affiliation_strings":["Computer Engineering Department, College of Engineering and Petroleum, Kuwait University, Kuwait City, Kuwait"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Engineering Department, College of Engineering and Petroleum, Kuwait University, Kuwait City, Kuwait","institution_ids":["https://openalex.org/I2799345387","https://openalex.org/I36721946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077897203","display_name":"Imtiaz Ahmad","orcid":"https://orcid.org/0000-0002-0673-7324"},"institutions":[{"id":"https://openalex.org/I2799345387","display_name":"Kuwait Petroleum Corporation (Kuwait)","ror":"https://ror.org/04wacmk20","country_code":"KW","type":"company","lineage":["https://openalex.org/I2799345387"]},{"id":"https://openalex.org/I36721946","display_name":"Kuwait University","ror":"https://ror.org/021e5j056","country_code":"KW","type":"education","lineage":["https://openalex.org/I36721946"]}],"countries":["KW"],"is_corresponding":false,"raw_author_name":"Imtiaz Ahmad","raw_affiliation_strings":["Computer Engineering Department, College of Engineering and Petroleum, Kuwait University, Kuwait City, Kuwait"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Engineering Department, College of Engineering and Petroleum, Kuwait University, Kuwait City, Kuwait","institution_ids":["https://openalex.org/I2799345387","https://openalex.org/I36721946"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041607429","display_name":"Sa\u2019ed Abed","orcid":"https://orcid.org/0000-0003-1849-9316"},"institutions":[{"id":"https://openalex.org/I2799345387","display_name":"Kuwait Petroleum Corporation (Kuwait)","ror":"https://ror.org/04wacmk20","country_code":"KW","type":"company","lineage":["https://openalex.org/I2799345387"]},{"id":"https://openalex.org/I36721946","display_name":"Kuwait University","ror":"https://ror.org/021e5j056","country_code":"KW","type":"education","lineage":["https://openalex.org/I36721946"]}],"countries":["KW"],"is_corresponding":true,"raw_author_name":"Sa'Ed Abed","raw_affiliation_strings":["Computer Engineering Department, College of Engineering and Petroleum, Kuwait University, Kuwait City, Kuwait"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Engineering Department, College of Engineering and Petroleum, Kuwait University, Kuwait City, Kuwait","institution_ids":["https://openalex.org/I2799345387","https://openalex.org/I36721946"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5041607429"],"corresponding_institution_ids":["https://openalex.org/I2799345387","https://openalex.org/I36721946"],"apc_list":{"value":2125,"currency":"USD","value_usd":2125},"apc_paid":{"value":2125,"currency":"USD","value_usd":2125},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09557794,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"8","issue":null,"first_page":"1661789","last_page":"1661789"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.2955000102519989,"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":0.2955000102519989,"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":0.1265999972820282,"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":0.07989999651908875,"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/arabic","display_name":"Arabic","score":0.3939000070095062},{"id":"https://openalex.org/keywords/yield","display_name":"Yield (engineering)","score":0.3725999891757965},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3447999954223633},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.33959999680519104},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.326200008392334},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.30570000410079956}],"concepts":[{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.6294000148773193},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6071000099182129},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5717999935150146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5052000284194946},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.3939000070095062},{"id":"https://openalex.org/C134121241","wikidata":"https://www.wikidata.org/wiki/Q899301","display_name":"Yield (engineering)","level":2,"score":0.3725999891757965},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3447999954223633},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.33959999680519104},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.326200008392334},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.30570000410079956},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2858999967575073},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.3389/frai.2025.1661789","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frai.2025.1661789","pdf_url":"https://www.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2025.1661789/pdf","source":{"id":"https://openalex.org/S4210197006","display_name":"Frontiers in Artificial Intelligence","issn_l":"2624-8212","issn":["2624-8212"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence","raw_type":"journal-article"},{"id":"pmid:41050103","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41050103","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in artificial intelligence","raw_type":null},{"id":"pmh:oai:doaj.org/article:56a34a8987234740a499bf5d38552c67","is_oa":true,"landing_page_url":"https://doaj.org/article/56a34a8987234740a499bf5d38552c67","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Frontiers in Artificial Intelligence, Vol 8 (2025)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:11299323","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12488727","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"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":"pmh:oai:pubmedcentral.nih.gov:12488727","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12488727/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"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":"Front Artif Intell","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3389/frai.2025.1661789","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frai.2025.1661789","pdf_url":"https://www.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2025.1661789/pdf","source":{"id":"https://openalex.org/S4210197006","display_name":"Frontiers in Artificial Intelligence","issn_l":"2624-8212","issn":["2624-8212"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414306244.pdf","grobid_xml":"https://content.openalex.org/works/W4414306244.grobid-xml"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W623162378","https://openalex.org/W2101105183","https://openalex.org/W2115050143","https://openalex.org/W2137397532","https://openalex.org/W2150824314","https://openalex.org/W2244808429","https://openalex.org/W2251054663","https://openalex.org/W2291187241","https://openalex.org/W2551040688","https://openalex.org/W2751193242","https://openalex.org/W2769860570","https://openalex.org/W2896457183","https://openalex.org/W2905123482","https://openalex.org/W2915357442","https://openalex.org/W2970513828","https://openalex.org/W2993173751","https://openalex.org/W3025939269","https://openalex.org/W3044438666","https://openalex.org/W3089774903","https://openalex.org/W3103339821","https://openalex.org/W3113622461","https://openalex.org/W4220806038","https://openalex.org/W4225165463","https://openalex.org/W4303856974","https://openalex.org/W4323655724","https://openalex.org/W4360584537","https://openalex.org/W4365516555","https://openalex.org/W4382619177","https://openalex.org/W4385015470","https://openalex.org/W4385067052","https://openalex.org/W4385570226","https://openalex.org/W4385572280","https://openalex.org/W4385633461","https://openalex.org/W4386701652","https://openalex.org/W4388676221","https://openalex.org/W4389518309","https://openalex.org/W4389519409","https://openalex.org/W4391136507","https://openalex.org/W4391283156","https://openalex.org/W4391528951","https://openalex.org/W4401042993","https://openalex.org/W4402671393","https://openalex.org/W4402671416","https://openalex.org/W4402896967","https://openalex.org/W4406302399","https://openalex.org/W4413206126"],"related_works":[],"abstract_inverted_index":{"Introduction:":[0],"Exploring":[1],"Arabic":[2],"dialects":[3],"in":[4,22,73,121,145,163,182,228,237,252,274],"Natural":[5],"Language":[6,24],"Processing":[7],"(NLP)":[8],"is":[9,248],"essential":[10],"to":[11,149,207,211,215,297],"understand":[12],"linguistic":[13],"variation":[14],"and":[15,35,47,53,87,98,106,127,151,156,172,184,193,209,231,241,259,280,307],"meet":[16],"regional":[17],"communication":[18,34],"demands.":[19],"Recent":[20],"advances":[21],"Large":[23],"Models":[25],"(LLMs)":[26],"have":[27,70],"opened":[28],"up":[29],"new":[30],"vistas":[31],"for":[32,103,111,125,278],"multilingual":[33],"text":[36],"generation.":[37],"Methods:":[38],"This":[39],"paper":[40],"investigates":[41],"the":[42,51,74,112,161,170,219,249,298],"performance":[43,115,138],"of":[44,180],"GPT-3.5,":[45],"GPT-4,":[46],"Bard":[48,152,216,281,308],"(Gemini)":[49],"on":[50,61],"QADI":[52],"MADAR":[54,62,220],"datasets,":[55],"while":[56,233,283,293,314],"GPT-5":[57,247],"was":[58,101,108,143,160],"evaluated":[59],"exclusively":[60],"encompassing":[63],"over":[64],"15":[65],"different":[66,92],"countries.":[67],"Several":[68],"metrics":[69],"been":[71],"used":[72],"evaluation,":[75],"such":[76],"as":[77],"cosine":[78,238],"similarity,":[79,239],"universal":[80,242],"similarity":[81,147,243],"encoder,":[82],"sentence":[83,254],"BERT,":[84],"TER,":[85,232],"ROUGE,":[86],"BLEU.":[88],"In":[89],"this":[90,312],"study,":[91],"prompting":[93,208],"techniques":[94],"were":[95,226,289],"used:":[96],"zero-shot":[97],"few-shot.":[99],"Zero-shot":[100,287],"employed":[102,109],"all":[104],"dialects,":[105,292],"few-shot":[107,266,294],"only":[110],"least":[113],"translation":[114,137,198,210,224,275],"dialect,":[116],"Tunisian.":[117],"Results:":[118],"<":[119],"0.05)":[120],"most":[122],"metrics,":[123],"except":[124],"BLEU":[126,183,258],"TER":[128,189],"where":[129,169],"it":[130],"does":[131],"not":[132,269,303],"show":[133,270],"significance,":[134],"indicating":[135,195],"comparable":[136],"among":[139],"models.":[140],"Furthermore,":[141],"GPT-4":[142,159,279,306],"highest":[144],"semantic":[146],"compared":[148,214],"GPT-3.5":[150,284,315],"(Gemini),":[153,282],"0.66,":[154],"0.61,":[155],"0.63,":[157],"respectively.":[158],"best":[162],"identifying":[164,253],"overlapping":[165],"sentences":[166],"(i.e.,":[167],"those":[168],"source":[171],"target":[173],"are":[174,235],"identical)":[175],"with":[176],"a":[177,271],"combined":[178],"average":[179,262],"0.41":[181],"ROUGE-L.":[185],"All":[186],"LLMs":[187],"scored":[188],"values":[190],"between":[191],"6%":[192],"25%,":[194],"generally":[196],"good":[197],"quality.":[199],"However,":[200],"GPT":[201],"models,":[202],"especially":[203,277],"GPT-5,":[204],"responded":[205],"better":[206],"Levant":[212],"countries":[213],"(Gemini).":[217],"For":[218],"dataset,":[221],"no":[222],"significant":[223,272],"differences":[225,234],"observed":[227],"sentence-BERT,":[229],"ROUGE-L,":[230],"identified":[236],"BLEU,":[240],"encoder":[244],"metrics.":[245],"Therefore,":[246],"top":[250],"performer":[251],"overlaps":[255],"measured":[256],"by":[257],"ROUGE-L":[260],"(combined":[261],"0.37).":[263],"Discussion:":[264],"The":[265],"approach":[267],"did":[268,302],"improvement":[273],"performance,":[276],"performed":[285,309],"consistently.":[286],"prompts":[288],"effective":[290],"across":[291],"prompting,":[295],"applied":[296],"weakest-performing":[299],"dialect":[300],"(Tunisian),":[301],"yield":[304],"improvement.":[305],"worse":[310],"under":[311],"set-up,":[313],"remained":[316],"consistent.":[317]},"counts_by_year":[],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}