{"id":"https://openalex.org/W4416035163","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1756","title":"TounsiBench: Benchmarking Large Language Models for Tunisian Arabic","display_name":"TounsiBench: Benchmarking Large Language Models for Tunisian Arabic","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416035163","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1756"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.emnlp-main.1756","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1756","pdf_url":"https://aclanthology.org/2025.emnlp-main.1756.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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.emnlp-main.1756.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5118628332","display_name":"Souha Ben Hassine","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Souha Ben Hassine","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120308776","display_name":"Asma Arrak","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Asma Arrak","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120308777","display_name":"Marouene Addhoum","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marouene Addhoum","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5007185917","display_name":"Steven Lloyd Wilson","orcid":"https://orcid.org/0000-0003-4046-1357"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Steven R Wilson","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5118628332"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18309872,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"34615","last_page":"34630"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.32440000772476196,"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":0.32440000772476196,"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/T13912","display_name":"Language, Linguistics, Cultural Analysis","score":0.13220000267028809,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13629","display_name":"Text Readability and Simplification","score":0.0885000005364418,"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":0.43799999356269836},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.3903000056743622},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3714999854564667},{"id":"https://openalex.org/keywords/computational-linguistics","display_name":"Computational linguistics","score":0.36570000648498535},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.29580000042915344}],"concepts":[{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6549999713897705},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6460000276565552},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5360000133514404},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5248000025749207},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.43799999356269836},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.3903000056743622},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3714999854564667},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.36570000648498535},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.29580000042915344},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.25690001249313354}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.emnlp-main.1756","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1756","pdf_url":"https://aclanthology.org/2025.emnlp-main.1756.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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.emnlp-main.1756","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1756","pdf_url":"https://aclanthology.org/2025.emnlp-main.1756.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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416035163.pdf","grobid_xml":"https://content.openalex.org/works/W4416035163.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1,95],"work,":[2],"we":[3,27,120],"introduce":[4],"the":[5,10,47,66,103],"first":[6],"benchmark":[7,140],"for":[8,129],"evaluating":[9],"capabilities":[11],"of":[12,31,102],"large":[13],"language":[14],"models":[15],"(LLMs)":[16],"in":[17,22,114],"understanding":[18],"and":[19,35,53,62,68,73,89,111,133],"generating":[20],"responses":[21,49,128],"Tunisian":[23,32,115],"Arabic.To":[24,116],"achieve":[25],"this,":[26],"construct":[28],"a":[29,91],"dataset":[30],"Arabic":[33],"instructions":[34],"prompt":[36],"ten":[37],"widely-used":[38],"LLMs":[39,104],"that":[40,100,105],"claim":[41],"to":[42,139],"support":[43],"Arabic.We":[44],"then":[45],"assess":[46],"LLM":[48],"through":[50],"both":[51],"human":[52,87],"LLMbased":[54],"evaluations":[55],"across":[56],"four":[57],"criteria:":[58],"quality,":[59],"correctness,":[60],"relevance,":[61],"dialectal":[63],"adherence.We":[64],"analyze":[65],"agreement":[67],"correlation":[69,85],"between":[70],"these":[71],"judgments":[72],"identify":[74],"GPT-4o":[75],"as":[76],"our":[77,122,134],"automated":[78],"judge":[79],"model":[80],"based":[81],"on":[82],"its":[83],"high":[84],"with":[86,109,125],"ratings,":[88],"generate":[90],"final":[92],"leaderboard":[93],"using":[94],"model.Our":[96],"error":[97],"analysis":[98],"reveals":[99],"most":[101],"were":[106],"evaluated":[107],"struggle":[108],"recognizing":[110],"properly":[112],"responding":[113],"facilitate":[117],"further":[118],"research,":[119],"release":[121],"dataset,":[123],"along":[124],"gold-standard":[126],"humanwritten":[127],"all":[130],"744":[131],"instructions,":[132],"evaluation":[135],"framework,":[136],"allowing":[137],"others":[138],"their":[141],"own":[142],"models.":[143]},"counts_by_year":[],"updated_date":"2026-03-11T06:11:40.159057","created_date":"2025-11-08T00:00:00"}