Providing personalized Explanations: a Conversational Approach
This addresses the problem of providing tailored explanations to diverse stakeholders in AI, though it appears incremental as it builds on conversational methods without major new techniques.
The paper tackles the need for personalized explanations in AI systems by proposing a conversational approach, proving that conversations terminate when the explainee justifies the initial claim if a comprehensible explanation exists.
The increasing applications of AI systems require personalized explanations for their behaviors to various stakeholders since the stakeholders may have various knowledge and backgrounds. In general, a conversation between explainers and explainees not only allows explainers to obtain the explainees' background, but also allows explainees to better understand the explanations. In this paper, we propose an approach for an explainer to 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.