Home/Journal of the Digital Humanities Association of Southern Africa/Article Record
Peer-Reviewed Article December 30, 2025

Multimodal Classification System for Hausa Using LLMs and Vision Transformers

Are you an author of this work?Link to your sovereign AfriScholar profile
Published in: Journal of the Digital Humanities Association of Southern Africa
Publisher: Digital Humanities Association of Southern Africa • South Africa • 3006-6492
DOI: https://doi.org/10.55492/dhasa.v6i02.6737

Abstract

This paper presents a classification-based Vi-sual Question Answering (VQA) system for theHausa language, integrating Large LanguageModels (LLMs) and vision transformers. Byfine-tuning LLMs on monolingual Hausa textand fusing their representations with those ofstate-of-the-art vision encoders, our system pre-dicts answers from a fixed vocabulary. Exper-iments conducted on the HaVQA dataset, un-der offline text–image augmentation regimes,tailored to the specificity of Hausa as a low-resource language, show that this augmentationstrategy yields the best performance over thebaseline, achieving 35.85% accuracy, 35.89%WuPalmer similarity, and 15.32% F1-score.

Download Full Text PDFView at PublisherCrossref RecordCrossref XML

Verified Citation Velocity

Recorded scholarly citations in African and international peer-reviewed literature

0
Total Citations

Citations are continuously tracked and harvested across continental OJS endpoints and OpenAlex feeds.