Visual Question Answering Using Multimodal Data Augmentation for Hausa
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
This paper introduces a multimodal Visual Question Answering (VQA) framework for Hausa, a low-resource African language, combining Large Language Models (LLMs) and vision transformers. We deliberately adopt a classification-based formulation to explore the non-generative potential of LLMs when fused with visual encoders. Three multimodal augmentation regimes: no augmentation, inline, and offline are evaluated using the HaVQA dataset (1), the only publicly available Hausa multimodal corpus. Results show that the offline augmentation strategy achieves the best performance, reaching 35.85% accuracy, 35.89 % WUPS, and <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$15.32 \% ~\mathrm{F} 1$</tex>-score, surpassing the baseline by over 5 %. These findings highlight the effectiveness of multimodal data enrichment and controlled LLM-ViT fusion for robust VQA in low-resource settings.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it