Explainable Artificial Intelligence in education

TLDR

Emerging concerns about the fairness, accountability, transparency, and ethics of AI‑supported educational interventions have prompted interest in eXplainable AI as a means to increase trust. This paper argues that XAI in education shares commonalities with broader AI use while also requiring distinctive considerations. The authors introduce the XAI‑ED framework, outlining six key aspects—stakeholders, benefits, explanation approaches, AI model classes, human‑centered interface design, and potential pitfalls—and demonstrate its application through four detailed case studies. They conclude by outlining opportunities, challenges, and future research directions for effectively integrating XAI into educational contexts.

Abstract

There are emerging concerns about the Fairness, Accountability, Transparency, and Ethics (FATE) of educational interventions supported by the use of Artificial Intelligence (AI) algorithms. One of the emerging methods for increasing trust in AI systems is to use eXplainable AI (XAI), which promotes the use of methods that produce transparent explanations and reasons for decisions AI systems make. Considering the existing literature on XAI, this paper argues that XAI in education has commonalities with the broader use of AI but also has distinctive needs. Accordingly, we first present a framework, referred to as XAI-ED, that considers six key aspects in relation to explainability for studying, designing and developing educational AI tools. These key aspects focus on the stakeholders, benefits, approaches for presenting explanations, widely used classes of AI models, human-centred designs of the AI interfaces and potential pitfalls of providing explanations within education. We then present four comprehensive case studies that illustrate the application of XAI-ED in four different educational AI tools. The paper concludes by discussing opportunities, challenges and future research needs for the effective incorporation of XAI in education.