Multimodal Large Language Models for Low-Resource Languages: A Case Study for Basque
Abstract
Researchers developed a strong multimodal large language model for the low-resource Basque language using mixed training data and two different LLM backbones, demonstrating that minimal Basque multimodal data and a general-purpose LLM can achieve competitive performance.
Current Multimodal Large Language Models exhibit very strong performance for several demanding tasks. While commercial MLLMs deliver acceptable performance in low-resource languages, comparable results remain unattained within the open science community. In this paper, we aim to develop a strong MLLM for a low-resource language, namely Basque. For that purpose, we develop our own training and evaluation image-text datasets. Using two different Large Language Models as backbones, the Llama-3.1-Instruct model and a Basque-adapted variant called Latxa, we explore several data mixtures for training. We show that: i) low ratios of Basque multimodal data (around 20%) are already enough to obtain solid results on Basque benchmarks, and ii) contrary to expected, a Basque instructed backbone LLM is not required to obtain a strong MLLM in Basque. Our results pave the way to develop MLLMs for other low-resource languages by openly releasing our resources.
Models citing this paper 2
Datasets citing this paper 1
Spaces citing this paper 0
No Space linking this paper