Large Multimodal Models for Low-Resource Languages: A Survey
It addresses the problem of making large multimodal models accessible for speakers of low-resource languages, though it is incremental as a survey rather than a novel method.
This survey analyzes techniques for adapting large multimodal models to low-resource languages, identifying visual information as a key bridge for performance improvement based on a review of 106 studies across 75 languages.
In this survey, we systematically analyze techniques used to adapt large multimodal models (LMMs) for low-resource (LR) languages, examining approaches ranging from visual enhancement and data creation to cross-modal transfer and fusion strategies. Through a comprehensive analysis of 106 studies across 75 LR languages, we identify key patterns in how researchers tackle the challenges of limited data and computational resources. We find that visual information often serves as a crucial bridge for improving model performance in LR settings, though significant challenges remain in areas such as hallucination mitigation and computational efficiency. We aim to provide researchers with a clear understanding of current approaches and remaining challenges in making LMMs more accessible to speakers of LR (understudied) languages. We complement our survey with an open-source repository available at: https://github.com/marianlupascu/LMM4LRL-Survey.