mlsanityData to 7 Oct 2026

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

arXiv 2511.09396 ↗First posted 12 Nov 2025cs.CL cs.AIcited by 0

On the map: Multimodal LLMs / vision-language models → MLLM training and visual instruction tuning

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in MLLM training and visual instruction tuning, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 8 of its 30 references that are in the map. First posted on arXiv 12 Nov 2025.

Builds on

8 of 30 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025Aya Vision: Advancing the Frontier of Multilingual Multimodality13 May
  2. 2024NVLM: Open Frontier-Class Multimodal LLMs17 Sep

Other references · 6

  1. 2024The Llama 3 Herd of Modelscited by 14,192
  2. 2025Qwen3 Technical Reportcited by 8,195
  3. 2024PaliGemma: A versatile 3B VLM for transfercited by 679
  4. 2024WildVision: Evaluating Vision-Language Models in the Wild with Human Preferencescited by 76
  5. 2023LEONARDO: A Pan-European Pre-Exascale Supercomputer for HPC and AI Applicationscited by 12
  6. 2025Instructing Large Language Models for Low-Resource Languages: A Systematic Study for Basquecited by 12

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Large Multimodal Models for Low-Resource Languages: A Survey
  2. 2024A Survey of Multimodal Large Language Model from A Data-centric Perspective
  3. 2024Pipeline Analysis for Developing Instruct LLMs in Low-Resource Languages: A Case Study on Basque
  4. 2024Amharic LLaMA and LLaVA: Multimodal LLMs for Low Resource Languages
  5. 2025Multimodal Large Language Models for Text-rich Image Understanding: A Comprehensive Review
  6. 2023SEED-Bench-2: Benchmarking Multimodal Large Language Models
  7. 2024Efficient Multimodal Learning from Data-centric Perspective
  8. 2026Multilingual and Multimodal LLMs in the Wild: Building for Low-Resource Languages