{"id":"https://openalex.org/W7163188628","doi":"https://doi.org/10.1109/ie69249.2026.11539040","title":"Understanding Multimodal LLM Behavior in Arabic Image Captioning","display_name":"Understanding Multimodal LLM Behavior in Arabic Image Captioning","publication_year":2026,"publication_date":"2026-06-02","ids":{"openalex":"https://openalex.org/W7163188628","doi":"https://doi.org/10.1109/ie69249.2026.11539040"},"language":null,"primary_location":{"id":"doi:10.1109/ie69249.2026.11539040","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ie69249.2026.11539040","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 22nd International Conference on Intelligent Environments (IE)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137669882","display_name":"Khaoula Dahimi","orcid":null},"institutions":[{"id":"https://openalex.org/I50219554","display_name":"University of Laghouat","ror":"https://ror.org/018bbh535","country_code":"DZ","type":"education","lineage":["https://openalex.org/I50219554"]}],"countries":["DZ"],"is_corresponding":false,"raw_author_name":"Khaoula Dahimi","raw_affiliation_strings":["Amar Telidji University,Laboratoire d&#x0027;Informatique et de Math&#x00E9;matiques LIM,Laghouat,Algeria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amar Telidji University,Laboratoire d&#x0027;Informatique et de Math&#x00E9;matiques LIM,Laghouat,Algeria","institution_ids":["https://openalex.org/I50219554"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046969653","display_name":"Hadda Cherroun","orcid":"https://orcid.org/0000-0002-5117-0320"},"institutions":[{"id":"https://openalex.org/I50219554","display_name":"University of Laghouat","ror":"https://ror.org/018bbh535","country_code":"DZ","type":"education","lineage":["https://openalex.org/I50219554"]}],"countries":["DZ"],"is_corresponding":false,"raw_author_name":"Hadda Cherroun","raw_affiliation_strings":["Amar Telidji University,Laboratoire d&#x0027;Informatique et de Math&#x00E9;matiques LIM,Laghouat,Algeria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amar Telidji University,Laboratoire d&#x0027;Informatique et de Math&#x00E9;matiques LIM,Laghouat,Algeria","institution_ids":["https://openalex.org/I50219554"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076809953","display_name":"Amel Belabbaci","orcid":null},"institutions":[{"id":"https://openalex.org/I50219554","display_name":"University of Laghouat","ror":"https://ror.org/018bbh535","country_code":"DZ","type":"education","lineage":["https://openalex.org/I50219554"]}],"countries":["DZ"],"is_corresponding":false,"raw_author_name":"Amel Belabbaci","raw_affiliation_strings":["Amar Telidji University,Laboratoire d&#x0027;Informatique et de Math&#x00E9;matiques LIM,Laghouat,Algeria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amar Telidji University,Laboratoire d&#x0027;Informatique et de Math&#x00E9;matiques LIM,Laghouat,Algeria","institution_ids":["https://openalex.org/I50219554"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5092160679","display_name":"Abdelhamid Haouhat","orcid":"https://orcid.org/0009-0008-0820-5381"},"institutions":[{"id":"https://openalex.org/I50219554","display_name":"University of Laghouat","ror":"https://ror.org/018bbh535","country_code":"DZ","type":"education","lineage":["https://openalex.org/I50219554"]}],"countries":["DZ"],"is_corresponding":false,"raw_author_name":"Abdelhamid Haouhat","raw_affiliation_strings":["Amar Telidji University,Laboratoire d&#x0027;Informatique et de Math&#x00E9;matiques LIM,Laghouat,Algeria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amar Telidji University,Laboratoire d&#x0027;Informatique et de Math&#x00E9;matiques LIM,Laghouat,Algeria","institution_ids":["https://openalex.org/I50219554"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I50219554"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.79628837,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9510999917984009,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9510999917984009,"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"}},{"id":"https://openalex.org/T13310","display_name":"Subtitles and Audiovisual Media","score":0.009399999864399433,"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/T12031","display_name":"Speech and dialogue systems","score":0.008700000122189522,"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/closed-captioning","display_name":"Closed captioning","score":0.9049000144004822},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4828000068664551},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.4372999966144562},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.28450000286102295},{"id":"https://openalex.org/keywords/image-manipulation","display_name":"Image manipulation","score":0.2842999994754791}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9049000144004822},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6201000213623047},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4966000020503998},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4828000068664551},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47029998898506165},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.4372999966144562},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3070000112056732},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.30230000615119934},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.28450000286102295},{"id":"https://openalex.org/C2987933465","wikidata":"https://www.wikidata.org/wiki/Q141130","display_name":"Image manipulation","level":3,"score":0.2842999994754791},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.26330000162124634},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.26019999384880066}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ie69249.2026.11539040","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ie69249.2026.11539040","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 22nd International Conference on Intelligent Environments (IE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2101105183","https://openalex.org/W2962735233","https://openalex.org/W3011608779","https://openalex.org/W3153469116","https://openalex.org/W3196915641","https://openalex.org/W4206408702","https://openalex.org/W4362700943","https://openalex.org/W4386753702","https://openalex.org/W4389009503","https://openalex.org/W4389088607","https://openalex.org/W4389524413","https://openalex.org/W4398253493","https://openalex.org/W4401043827","https://openalex.org/W4402684027","https://openalex.org/W4416037776","https://openalex.org/W4416037802"],"related_works":[],"abstract_inverted_index":{"The":[0],"automatic":[1],"generation":[2],"of":[3,55,70],"high-quality":[4],"image":[5,33],"captions":[6],"is":[7],"a":[8,52,67],"critical":[9],"task":[10],"in":[11,31,99],"multimodal":[12,100],"artificial":[13],"intelligence,":[14],"with":[15],"applications":[16],"ranging":[17],"from":[18],"assistive":[19],"technology":[20],"to":[21],"computer-assisted":[22],"language":[23],"learning.":[24],"Recent":[25],"vision-language":[26],"foundation":[27],"models":[28,87],"have":[29],"excelled":[30],"English":[32],"captioning,":[34],"yet":[35],"their":[36],"performance":[37,84],"on":[38],"morphologically":[39],"rich,":[40],"low-resource":[41],"languages":[42],"like":[43],"Arabic":[44,63],"remains":[45],"underexplored.":[46],"In":[47],"this":[48],"study,":[49],"We":[50],"present":[51],"systematic":[53],"evaluation":[54],"leading":[56],"models\u2014Gemini,":[57],"Gemma,":[58],"LLaMA,":[59],"and":[60,77,88,96],"Fanar\u2014on":[61],"the":[62,91],"Flickr8k":[64],"dataset.":[65],"Using":[66],"diverse":[68],"suite":[69],"metrics,":[71,89],"we":[72],"assess":[73],"semantic":[74],"accuracy,":[75],"fluency,":[76],"hallucination":[78],"rates.":[79],"Our":[80],"results":[81],"reveal":[82],"significant":[83],"variation":[85],"across":[86],"highlighting":[90],"need":[92],"for":[93],"Arabic-specific":[94],"architectural":[95],"training":[97],"optimizations":[98],"AI.":[101]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2026-06-03T00:00:00"}
