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

· Source: cs.CL updates on arXiv.org · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Data Science & Analytics · Depth: Expert, extended

Summary

MELLA, a novel multimodal multilingual dataset, addresses the significant performance gap of Multimodal Large Language Models (MLLMs) in low-resource languages. Existing MLLMs often provide "thin descriptions" due to insufficient cultural groundedness and linguistic capability. This study introduces a dual-source data strategy, collecting 6.8 million image-text pairs across eight low-resource languages: Arabic, Czech, Hungarian, Korean, Russian, Serbian, Thai, and Vietnamese. MELLA comprises D_know (native web alt-text for cultural knowledge) and D_ling (MLLM-generated, translated captions for linguistic fluency). Experiments demonstrate that fine-tuning MLLM backbones like InternVL2-8B and QwenVL2-7B on MELLA significantly improves both cultural understanding (keyword accuracy) and linguistic skills (BLEU, ROUGE-L, METEOR), enabling "thick descriptions."

Key takeaway

For AI Scientists and Machine Learning Engineers expanding MLLM capabilities to low-resource languages, you should prioritize both linguistic fluency and cultural groundedness. Relying solely on machine translation for data will yield superficial outputs. Instead, adopt a dual-source data strategy, integrating native cultural context from sources like web alt-text with linguistically rich translated captions to build truly effective and inclusive multimodal AI systems.

Key insights

Effective low-resource MLLMs require both linguistic fluency and deep cultural understanding, beyond mere translation.

Principles

Method

A dual-source strategy collects native web alt-text for cultural knowledge (D_know) and MLLM-generated, translated captions for linguistic capability (D_ling), then combines them for unified fine-tuning.

In practice

Topics

Best for: Research Scientist, AI Scientist, Machine Learning Engineer, NLP Engineer

Related on AIssential

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by cs.CL updates on arXiv.org.