Providing personalized Explanations: a Conversational Approach
Jieting Luo, Thomas Studer, Mehdi Dastani

TL;DR
This paper introduces a conversational method for providing personalized AI explanations, enabling tailored communication through iterative dialogue that adapts to the explainee's background and understanding.
Contribution
It proposes a novel conversational approach for personalized explanations and proves the termination of such dialogues under certain conditions.
Findings
Conversation terminates when explainee justifies initial claim
Approach adapts explanations based on explainee's background
Ensures explanations are understandable and personalized
Abstract
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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsSemantic Web and Ontologies · Explainable Artificial Intelligence (XAI) · Scientific Computing and Data Management
MethodsAttentive Walk-Aggregating Graph Neural Network
