Explaining explanation methods

The most effective Artificial Intelligence (AI) systems exploit complex machine learning models to fulfill their tasks due to their high performance. Unfortunately, the most effective machine learning models use for their decision processes a logic not understandable from humans that makes them real black-box models. The lack of transparency on how AI systems make decisions is a clear limitation in their adoption in safety-critical and socially sensitive contexts. Consequently, since the applications in which AI are employed are various, research in eXplainable AI (XAI) has recently caught much attention, with specific distinct requirements for different types of explanations for different users. In this paper, we briefly present the existing explanation problems, the main strategies adopted to solve them, and the desiderata for XAI methods. Finally, the most common types of explanations are illustrated with references to state-of-the-art explanation methods able to retrieve them.