用不确定性判断解释可靠性，省钱又高效。
Uncertainty Gating for Cost-Aware Explainable Artificial Intelligence
- 用认知不确定性衡量解释可信度，低成本预判解释质量。
- 不确定性高时解释不稳定且不忠实，相关性显著（负相关）。
- 适合预算有限或需稳定解释的AI应用，如医疗、金融决策。
事后解释方法广泛用于解析黑箱模型预测，但其生成成本高且可靠性难以保证。本文提出将认知不确定性作为解释可靠性的低成本代理：高认知不确定性表明决策边界模糊，此时解释易失稳且不忠实。基于此思想，我们设计两种互补应用场景：一是根据预期解释可靠性，动态选择廉价或昂贵的XAI方法以优化最差情况下的解释质量；二是在预算受限时，对不确定性高的样本延迟生成解释。在四个表格数据集、五种不同架构及四种XAI方法上，我们观察到认知不确定性与解释稳定性之间存在强负相关。进一步分析表明，该指标不仅能区分稳定与不稳定解释，还能识别忠实与不忠实解释。图像分类实验验证了这些发现可推广至非表格数据。
原文摘要 · Abstract (English)
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. This insight enables two complementary use cases: `improving worst-case explanations' (routing samples to cheap or expensive XAI methods based on expected explanation reliability), and `recalling high-quality explanations' (deferring explanation generation for uncertain samples under constrained budget). Across four tabular datasets, five diverse architectures, and four XAI methods, we observe a strong negative correlation between epistemic uncertainty and explanation stability. Further analysis shows that epistemic uncertainty distinguishes not only stable from unstable explanations, but also faithful from unfaithful ones. Experiments on image classification confirm that our findings generalize beyond tabular data.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。