---
title: "MELLA: Bridging Linguistic Capability and Cultural Groundedness for Low-Resource Language MLLMs"
authors:
  - "Yufei Gao"
  - "Jiaying Fei"
  - "Nuo Chen"
  - "Ruirui Chen"
  - "Guohang Yan"
  - "Yunshi Lan"
  - "Botian Shi"
doi: "10.24963/ijcai.2026/125"
url: "https://ijcai.org/proceedings/2026/125"
pdf: "https://ijcai.org/proceedings/2026/0125.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "1115-1123"
track: "Main Track"
keywords:
  - "Computer Vision: Vision, language and reasoning"
---

# MELLA: Bridging Linguistic Capability and Cultural Groundedness for Low-Resource Language MLLMs

Yufei Gao, Jiaying Fei, Nuo Chen, Ruirui Chen, Guohang Yan, Yunshi Lan, Botian Shi

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 1115-1123. DOI: [10.24963/ijcai.2026/125](https://doi.org/10.24963/ijcai.2026/125)

## 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.
We 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.
Through 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.