A Comprehensive Taxonomy for Explainable Artificial Intelligence: A Systematic Survey of Surveys on Methods and Concepts

In the meantime, a wide variety of terminologies, motivations, approaches and evaluation criteria have been developed within the research field of explainable artificial intelligence (XAI). With the amount of XAI methods vastly growing, a taxonomy of methods is needed by researchers as well as practitioners: To grasp the breadth of the topic, compare methods, and to select the right XAI method based on traits required by a specific use-case context. In the literature many taxonomies for XAI methods of varying level of detail and depth can be found. While they often have a different focus, they also exhibit many points of overlap. This paper unifies these efforts, and provides a taxonomy of XAI methods that is complete with respect to notions present in the current state-of-research. In a structured literature analysis and meta-study we identified and reviewed more than 50 of the most cited and current surveys on XAI methods, metrics, and method traits. After summarizing them in a survey of surveys, we merge terminologies and concepts of the articles into a unified structured taxonomy. Single concepts therein are illustrated by in total more than 50 diverse selected example methods, which we categorize accordingly. The taxonomy may serve both beginners, researchers, and practitioners as a reference and wide-ranging overview on XAI method traits and aspects. Hence, it provides foundations for targeted, use-case-oriented, and context-sensitive future research.