Evidence-Constrained Visual Question Answering: A Diagnostic Study of Grounding and Selective Prediction
Inspectable visual evidence does not necessarily indicate that an evidence-based acceptance rule is more reliable in prediction. The aim of this study is to measure that difference in binary object-presence visual question answering. It is accompanied with an independent object detector providing localized evidence for positive answers, and an open multimodal generator, SmolVLM-256M-Instruct. The number of positive candidates accepted depends on a development-selected threshold, while negative candidates abstain because lack of detection cannot establish absence. The exploratory pilot resulted in a new replication with 60 new COCO val2017 images and 360 new adversarial POPE questions, where the images were split into development/evaluation sets. 68.75% reference-label agreement on 240 evaluation questions was obtained using direct generation. The evidence gate accepted 39 answers at 16.25% coverage with 100.00% reference agreement, while positive-only confidence selection achieved 97.44% agreement at the same accepted count. The gate had a higher accepted-answer accuracy point estimate than positive-only confidence selection, but the exploratory difference interval included zero; superiority was not established. Also reported in this study are threshold sensitivity, positive-answer retention, image-cluster bootstrap intervals and checks on component training provenance. The results apply to just one backbone and a limited object-presence task, and do not establish semantic evidence sufficiency, causal visual dependence or general hallucination mitigation. The contribution is a reproducible diagnostic case study that demonstrates how answer-class composition and component training provenance should be controlled when assessing the evidence-constrained visual answering problem.
Authors
- Shokhan Albarzinji
- Hamsa Ahmed
Institutions
- Islamic Development Bank (SA)
- University of Anbar (IQ)
Publication Details
- Journal
- International Journal of Computers and Informatics
- Published
- 2026-11-16
- DOI
- https://doi.org/10.59992/ijci.2026.v5n11p6
- Primary Topic
- Multimodal Machine Learning Applications
- Type
- article
- Field-Weighted Citation Impact
- 0.00