{"id":"https://openalex.org/W4416037792","doi":"https://doi.org/10.18653/v1/2025.arabicnlp-sharedtasks.57","title":"PhantomTroupe at ImageEval 2025 Shared Task: Multimodal Arabic Image Captioning through Translation-Based Fine-Tuning of LLM Models","display_name":"PhantomTroupe at ImageEval 2025 Shared Task: Multimodal Arabic Image Captioning through Translation-Based Fine-Tuning of LLM Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416037792","doi":"https://doi.org/10.18653/v1/2025.arabicnlp-sharedtasks.57"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.arabicnlp-sharedtasks.57","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.arabicnlp-sharedtasks.57","pdf_url":"https://aclanthology.org/2025.arabicnlp-sharedtasks.57.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 Third Arabic Natural Language Processing Conference: Shared Tasks","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.arabicnlp-sharedtasks.57.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120309407","display_name":"Muhammad Abu Horaira","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Muhammad Abu Horaira","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007909581","display_name":"Farhan Amin","orcid":"https://orcid.org/0000-0002-6385-5511"},"institutions":[{"id":"https://openalex.org/I102782458","display_name":"Chittagong University of Engineering & Technology","ror":"https://ror.org/052qsay17","country_code":"BD","type":"education","lineage":["https://openalex.org/I102782458"]},{"id":"https://openalex.org/I91090688","display_name":"University of Science and Technology Chittagong","ror":"https://ror.org/00w9tx359","country_code":"BD","type":"education","lineage":["https://openalex.org/I91090688"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Farhan Amin","raw_affiliation_strings":["Department of Computer Science and Engineering Chittagong University of Engineering and Technology , Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering Chittagong University of Engineering and Technology , Bangladesh","institution_ids":["https://openalex.org/I102782458","https://openalex.org/I91090688"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063024687","display_name":"Sakibul Hasan","orcid":null},"institutions":[{"id":"https://openalex.org/I102782458","display_name":"Chittagong University of Engineering & Technology","ror":"https://ror.org/052qsay17","country_code":"BD","type":"education","lineage":["https://openalex.org/I102782458"]},{"id":"https://openalex.org/I91090688","display_name":"University of Science and Technology Chittagong","ror":"https://ror.org/00w9tx359","country_code":"BD","type":"education","lineage":["https://openalex.org/I91090688"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Sakibul Hasan","raw_affiliation_strings":["Department of Computer Science and Engineering Chittagong University of Engineering and Technology , Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering Chittagong University of Engineering and Technology , Bangladesh","institution_ids":["https://openalex.org/I102782458","https://openalex.org/I91090688"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5117862403","display_name":"Md. Tanvir Ahammed Shawon","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Md. Tanvir Ahammed Shawon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5037517844","display_name":"Muhammad Ibrahim Khan","orcid":"https://orcid.org/0000-0002-5734-3667"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Muhammad Ibrahim Khan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.37444811,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"414","last_page":"418"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9876000285148621,"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":0.9876000285148621,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0015999999595806003,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.0006000000284984708,"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":0.9047999978065491},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4851999878883362},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.3901999890804291},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.29179999232292175},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.2782999873161316}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9047999978065491},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6729000210762024},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5051000118255615},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4851999878883362},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4796999990940094},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.3901999890804291},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.29510000348091125},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.29269999265670776},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.29179999232292175},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2689000070095062},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.arabicnlp-sharedtasks.57","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.arabicnlp-sharedtasks.57","pdf_url":"https://aclanthology.org/2025.arabicnlp-sharedtasks.57.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 Third Arabic Natural Language Processing Conference: Shared Tasks","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.arabicnlp-sharedtasks.57","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.arabicnlp-sharedtasks.57","pdf_url":"https://aclanthology.org/2025.arabicnlp-sharedtasks.57.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 Third Arabic Natural Language Processing Conference: Shared Tasks","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416037792.pdf","grobid_xml":"https://content.openalex.org/works/W4416037792.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Generating":[0],"culturally":[1,153],"accurate":[2,39],"captions":[3,91],"for":[4,41,50,55],"images":[5,33],"in":[6,140],"Arabic":[7,51,90,100,155],"remains":[8],"a":[9,45,85,121,126],"challenging":[10],"task":[11],"due":[12],"to":[13,35,92,97,151],"the":[14,27,56,64,72,141,145],"language's":[15],"rich":[16],"morphology,":[17],"complex":[18],"syntax,":[19],"and":[20,29,113,131],"diverse":[21],"cultural":[22],"contexts.Cultural":[23],"preservation":[24],"involves":[25],"capturing":[26],"significance":[28],"emotional":[30],"resonance":[31],"of":[32,66,89,124,129,136,147],"related":[34],"Palestinian":[36],"heritage,":[37],"ensuring":[38],"representation":[40],"future":[42],"generations.We":[43],"present":[44],"translation-assisted,":[46],"instruction-tuned":[47,148],"multimodal":[48,149],"pipeline":[49,86],"image":[52,67],"captioning,":[53],"developed":[54],"ImageEval":[57],"2025":[58],"Shared":[59],"Task":[60],"Subtask":[61],"2:":[62],"on":[63],"evaluation":[65],"captioning":[68],"models.Our":[69],"approach":[70],"leverages":[71],"Qwen2.5-VL-7B-Instructmodel":[73],"with":[74,82],"4bit":[75],"quantization,":[76],"fine-tuned":[77],"using":[78],"Parameter-Efficient":[79],"Fine-Tuning":[80],"(PEFT)":[81],"LoRA.We":[83],"implemented":[84],"involving":[87],"translation":[88],"English,":[93],"followed":[94],"by":[95],"back-translation":[96],"generate":[98],"fluent":[99],"outputs.We":[101],"evaluated":[102],"several":[103],"vision-language":[104],"models,":[105],"including":[106],"Qwen2.5":[107,116],"VL":[108,117],"(7B),":[109],"Llama":[110],"3.2":[111],"(11B),":[112],"Pixtral":[114],"(12B).The":[115],"(7B)":[118],"model":[119],"achieved":[120],"BLEU-1":[122],"score":[123],"22.6,":[125],"Cosine":[127],"Similarity":[128],"57.48,":[130],"an":[132],"LLM":[133],"Judge":[134],"Score":[135],"31.43,securing":[137],"third":[138],"place":[139],"competition.These":[142],"results":[143],"underscore":[144],"potential":[146],"models":[150],"produce":[152],"sensitive":[154],"captions.":[156]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-08T00:00:00"}
