Uncertainty Gating for Cost-Aware Explainable Artificial Intelligence

ArXi:2603.29915v1 Announce Type: new Post-hoc explanation methods are widely used to interpret black-box predictions, but their generation is often computationally expensive and their reliability is not guaranteed. We propose epistemic uncertainty as a low-cost proxy for explanation reliability: high epistemic uncertainty identifies regions where the decision boundary is poorly defined and where explanations become unstable and unfaithful.