Abstract: Explanations are important to people’s understanding of other agents (human or machine). But when an agent commits a norm-violating act, explanations are often insufficient. Justifications are needed. I will examine the cognitive and social nature of explanations, the cognitive, social, and normative nature of justifications, and probe what implications each of them has for trust in other agents (human or machine).

Abstract: Providing high-quality explanations for AI predictions is a challenging task. It requires, among other elements, selecting a proper level of generality/specificity of the explanation, referring to specific elements that have contributed to the decision, and providing evidence supporting negative hypothesis. In this talk, I will present some results achieved in the area of Argument Mining and Argument Generation and how these results can be exploited – in general and in legal applications – to generate high-quality explanatory dialogues crucially based on argumentation mechanisms.