A practical exploration of the convergence of Case-Based Reasoning and Explainable Artificial Intelligence

As Artificial Intelligence (AI) systems become increasingly complex, ensuring their decisions are transparent and understandable to users has become paramount. This paper explores the integration of Case-Based Reasoning (CBR) with Explainable Artificial Intelligence (XAI) through a real-world example, which presents an innovative CBR-driven XAI platform. This study investigates how CBR, a method that solves new problems based on the solutions of similar past problems, can be harnessed to enhance the explainability of AI systems. Though the literature has few works on the synergy between CBR and XAI, exploring the principles for developing a CBR-driven XAI platform is necessary. This exploration outlines the key features and functionalities, examines the alignment of CBR principles with XAI goals to make AI reasoning more transparent to users, and discusses methodological strategies for integrating CBR into XAI frameworks. Through a case study of our CBR-driven XAI platform, iSee: Intelligent Sharing of Explanation Experience, we demonstrate the practical application of these principles, highlighting the enhancement of system transparency and user trust. The platform elucidates the decision-making processes of AI models and adapts to provide explanations tailored to diverse user needs. Our findings emphasize the importance of interdisciplinary approaches in AI research and the significant role CBR can play in advancing the goals of XAI.