A Roadmap of Explainable Artificial Intelligence: Explain to Whom, When, What and How?

What is it about?

Explainable artificial intelligence (XAI) has gained significant attention, especially in AI-powered autonomous and adaptive systems (AASs). However, a discernible disconnect exists among research efforts across different communities. The machine learning community often overlooks “explaining to whom,” while the human-computer interaction community has examined various stakeholders with diverse explanation needs without addressing which XAI methods meet these requirements. Currently, no clear guidance exists on which XAI methods suit which specific stakeholders and their distinct needs. This hinders the achievement of the goal of XAI: providing human users with understandable interpretations. To bridge this gap, this paper presents a comprehensive XAI roadmap. Based on an extensive literature review, the roadmap summarizes different stakeholders, their explanation needs at different stages of the AI system lifecycle, the questions they may pose, and existing XAI methods. Then, by utilizing stakeholders’ inquiries as a conduit, the roadmap connects their needs to prevailing XAI methods, providing a guideline to assist researchers and practitioners to determine more easily which XAI methodologies can meet the specific needs of stakeholders in AASs. Finally, the roadmap discusses the limitations of existing XAI methods and outlines directions for future research.

Featured Image

Photo by Igor Omilaev on Unsplash

Photo by Igor Omilaev on Unsplash

Why is it important?

Explainable Artificial Intelligence (XAI) is increasingly receiving widespread attention. However, it is unclear to whom, what, when, and how it should be explained. Therefore, this paper identifies who the stakeholders are, what their needs for explanation are at different stages, what questions they will ask, and what existing XAI approaches can answer these questions. Overall, this paper provides a guide to help researchers and practitioners more easily identify which XAI methods can fulfill the specific needs of stakeholders in AI systems.