An Objective Metric for Explainable AI: How and Why to Estimate the Degree of Explainability

Explainable AI was born as a pathway to allow humans to explore and understand the inner working of complex systems. But establishing what is an explanation and objectively evaluating explainability, are not trivial tasks. With this paper, we present a new model-agnostic metric to measure the Degree of Explainability of information in an objective way, exploiting a specific theoretical model from Ordinary Language Philosophy called the Achinstein's Theory of Explanations, implemented with an algorithm relying on deep language models for knowledge graph extraction and information retrieval. In order to understand whether this metric is actually behaving as explainability is expected to, we devised a few experiments and user-studies involving more than 160 participants, evaluating two realistic AI-based systems for healthcare and finance using famous AI technology including Artificial Neural Networks and TreeSHAP. The results we obtained are statistically significant (with P values lower than 0.01), suggesting that our proposed metric for measuring the Degree of Explainability is robust on several scenarios and it aligns with concrete expectations.