VitrAI. Applying Explainable AI in the Real World

With recent progress in the field of Explainable Artificial Intelligence (XAI) and increasing use in practice, the need for an evaluation of different XAI methods and their explanation quality in practical usage scenarios arises. For this purpose, we present VitrAI, which is a web-based service with the goal of uniformly demonstrating four different XAI algorithms in the context of three real life scenarios and evaluating their performance and comprehensibility for humans. This work highlights practical obstacles to the use of XAI methods, and also shows that various XAI algorithms are only partially consistent with each other and unsystematically meet human expectations.