Reviewing the Need for Explainable Artificial Intelligence (xAI)

TL;DR

This paper systematically reviews explainable AI (xAI) research, analyzing key debates and proposing a future agenda to enhance understanding of how xAI addresses AI decision transparency.

Contribution

It provides a comprehensive synthesis of xAI literature, identifying core debates and outlining future research directions in explainability.

Findings

Four thematic debates central to xAI are identified.

A critical analysis of current xAI research is presented.

A future research agenda for xAI is proposed.

Abstract

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.