Four principles of explainable artificial intelligence
We introduce four principles for explainable artiﬁcial intelligence (AI) that comprise fundamental properties for explainable AI systems. We propose that explainable AI systems deliver accompanying evidence or reasons for outcomes and processes; provide explanations that are understandable to individual users; provide explanations that correctly reﬂect the system’s process for generating the output; and that a system only operates under conditions for which it was designed and when it reaches sufﬁcient conﬁdence in its output. We have termed these four principles as explanation, meaningful, explanation accuracy, and knowledge limits, respectively. Through signiﬁcant stakeholder engagement, these four principles were developed to encompass the multidisciplinary nature of explainable AI, including the ﬁelds of computer science, engineering, and psychology. Because one-sizeﬁts-all explanations do not exist, different users will require different types of explanations. We present ﬁve categories of explanation and summarize theories of explainable AI. We give an overview of the algorithms in the ﬁeld that cover the major classes of explainable algorithms. As a baseline comparison, we assess how well explanations provided by people follow our four principles. This assessment provides insights to the challenges of designing explainable AI systems.