{"type":"ScholarlyArticle","title":"MELLA: Bridging Linguistic Capability and Cultural Groundedness for Low-Resource Language MLLMs","authors":[{"name":"Yufei Gao","slug":"yufei-gao","given":"Yufei","family":"Gao","affiliation":""},{"name":"Jiaying Fei","slug":"jiaying-fei","given":"Jiaying","family":"Fei","affiliation":""},{"name":"Nuo Chen","slug":"nuo-chen","given":"Nuo","family":"Chen","affiliation":""},{"name":"Ruirui Chen","slug":"ruirui-chen","given":"Ruirui","family":"Chen","affiliation":""},{"name":"Guohang Yan","slug":"guohang-yan","given":"Guohang","family":"Yan","affiliation":""},{"name":"Yunshi Lan","slug":"yunshi-lan","given":"Yunshi","family":"Lan","affiliation":""},{"name":"Botian Shi","slug":"botian-shi","given":"Botian","family":"Shi","affiliation":""}],"abstract":"Multimodal Large Language Models (MLLMs) perform strongly in high-resource languages, yet often produce fluent but culturally \"thin\" descriptions in low-resource settings. We argue that this failure is not merely a linguistic limitation: culture-specific visual knowledge depends on native visual-textual alignments that translation-centric pipelines rarely provide.\r\nWe present MELLA, a multimodal dataset across eight low-resource languages, designed to jointly support linguistic fluency and cultural groundedness. MELLA uses a dual-source strategy that combines native web image-alt-text pairs for culture-grounded supervision with generated-and-translated image descriptions for linguistically rich supervision, explicitly separating two learning signals often conflated in multilingual multimodal data.\r\nThrough controlled diagnostic fine-tuning on multiple MLLM backbones, we show that MELLA mitigates cultural hallucination by helping models recognize and articulate culturally specific entities overlooked by translation-based adaptation. Our findings highlight data alignment, rather than model modification alone, as a key path toward culturally grounded multimodal understanding in low-resource languages.","doi":"10.24963/ijcai.2026/125","url":"https://ijcai.org/proceedings/2026/125","pdf":"https://ijcai.org/proceedings/2026/0125.pdf","markdown":"https://ijcai.org/proceedings/2026/125.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/125","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"Computer Vision","track":"Main Track","number":125,"pages":{"first":1115,"last":1123},"keywords":["Computer Vision: Vision, language and reasoning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}