Score: 1

Multimodal Large Language Models for Low-Resource Languages: A Case Study for Basque

Published: November 12, 2025 | arXiv ID: 2511.09396v1

By: Lukas Arana , Julen Etxaniz , Ander Salaberria and more

Potential Business Impact:

Creates smart computer vision for rare languages.

Business Areas:
Language Learning Education

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.

Country of Origin
🇪🇸 Spain

Repos / Data Links

Page Count
15 pages

Category
Computer Science:
Computation and Language