Reviewing the Need for Explainable Artificial Intelligence (xAI)
This paper addresses the problem of understanding the current state and future direction of xAI research for the AI community and organizations deploying AI.
This paper reviews the existing literature on Explainable Artificial Intelligence (xAI) to understand how current research addresses the need for explainability. It identifies four central thematic debates within xAI scholarship and synthesizes these findings into a future research agenda.
The diffusion of artificial intelligence (AI) applications in organizations and society has fueled research on explaining AI decisions. The explainable AI (xAI) field is rapidly expanding with numerous ways of extracting information and visualizing the output of AI technologies (e.g. deep neural networks). Yet, we have a limited understanding of how xAI research addresses the need for explainable AI. We conduct a systematic review of xAI literature on the topic and identify four thematic debates central to how xAI addresses the black-box problem. Based on this critical analysis of the xAI scholarship we synthesize the findings into a future research agenda to further the xAI body of knowledge.