A Multidisciplinary Survey and Framework for Design and Evaluation of Explainable AI Systems

The need for interpretable and accountable intelligent systems grows along with the prevalence of artificial intelligence applications used in everyday life. Explainable AI systems are intended to self-explain the reasoning behind system decisions and predictions. Researchers from different disciplines work together to define, design, and evaluate explainable systems. However, scholars from different disciplines focus on different objectives and fairly independent topics of Explainable AI research, which poses challenges for identifying appropriate design and evaluation methodology and consolidating knowledge across efforts. To this end, this paper presents a survey and framework intended to share knowledge and experiences of Explainable AI design and evaluation methods across multiple disciplines. Aiming to support diverse design goals and evaluation methods in XAI research, after a thorough review of Explainable AI related papers in the fields of machine learning, visualization, and human-computer interaction, we present a categorization of Explainable AI design goals and evaluation methods. Our categorization presents the mapping between design goals for different Explainable AI user groups and their evaluation methods. From our findings, we develop a framework with step-by-step design guidelines paired with evaluation methods to close the iterative design and evaluation cycles in multidisciplinary Explainable AI teams. Further, we provide summarized ready-to-use tables of evaluation methods and recommendations for different goals in Explainable AI research.