Tailoring explanations through conversation

Abstract

The increasing applications of AI systems require personalized explanations for their behaviors to various stakeholders since the stakeholders may have various backgrounds. In general, a conversation between explainers and explainees not only allows explainers to obtain explainees’ background, but also allows explainers to tailor their explanations so that explainees can better understand the explanations. In this paper, we propose an approach for an explainer to tailor and communicate personalized explanations to an explainee through having consecutive conversations with the explainee. We prove that the conversation terminates due to the explainee’s justification of the initial claim as long as there exists an explanation for the initial claim that the explainee understands and the explainer is aware of.