Large Vision-Language Models (LVLMs) frequently hallucinate, limiting their safe deployment in real-world applications. Existing LLM self-evaluation methods rely on a model's ability to estimate the correctness of its own outputs, which can improve deployment reliability; however, they depend heavily on language priors and are therefore ill-suited for evaluating vision-conditioned predictions. We propose VAUQ, a vision-aware uncertainty quantification framework for LVLM self-evaluation that explicitly measures how strongly a model's output depends on visual evidence. VAUQ introduces the Image-Information Score (IS), which captures the reduction in predictive uncertainty attributable to visual input, and an unsupervised core-region masking strategy that amplifies the influence of salient regions. Combining predictive entropy with this core-masked IS yields a training-free scoring function that reliably reflects answer correctness. Comprehensive experiments show that VAUQ consistently outperforms existing self-evaluation methods across multiple datasets.
@article{arxiv.2602.21054,
title = {VAUQ: Vision-Aware Uncertainty Quantification for LVLM Self-Evaluation},
author = {Seongheon Park and Changdae Oh and Hyeong Kyu Choi and Sean Du and Sharon Li},
journal= {arXiv preprint arXiv:2602.21054},
year = {2026}
}