Annotation-Efficient Vision-Language Model Adaptation to the Polish Language Using the LLaVA Framework

TL;DR

This paper adapts vision-language models to Polish using automated translation and minimal manual effort, achieving significant performance improvements and high-quality outputs for low-resource language settings.

Contribution

It demonstrates that large-scale automated translation with filtering can effectively adapt multimodal models to low-resource languages like Polish.

Findings

+9.5% performance improvement on Polish MMBench

Higher-quality captions as rated by human annotators

Effective use of automated translation and filtering for low-resource language adaptation

Abstract

Most vision-language models (VLMs) are trained on English-centric data, limiting their performance in other languages and cultural contexts. This restricts their usability for non-English-speaking users and hinders the development of multimodal systems that reflect diverse linguistic and cultural realities. In this work, we reproduce and adapt the LLaVA-Next methodology to create a set of Polish VLMs. We rely on a fully automated pipeline for translating and filtering existing multimodal datasets, and complement this with synthetic Polish data for OCR and culturally specific tasks. Despite relying almost entirely on automatic translation and minimal manual intervention to the training data, our approach yields strong results: we observe a +9.5% improvement over LLaVA-1.6-Vicuna-13B on a Polish-adapted MMBench, along with higher-quality captions in generative evaluations, as measured by human annotators in terms of linguistic correctness. These findings highlight that large-scale automated translation, combined with lightweight filtering, can effectively bootstrap high-quality multimodal models for low-resource languages. Some challenges remain, particularly in cultural coverage and evaluation. To facilitate further research, we make our models and evaluation dataset publicly available.