Using Learning Theories to Evolve Human-Centered XAI: Future Perspectives and Challenges

TL;DR

This paper explores how integrating learning theories into human-centered XAI can improve AI transparency, user understanding, and mitigate risks by fostering a learner-centered approach.

Contribution

It proposes infusing learning theories into the XAI lifecycle to enhance human agency and address challenges in complex AI systems.

Findings

Learning theories can be integrated into XAI to improve explanations.

A learner-centered approach enhances human agency in AI understanding.

Challenges include assessing and designing explanations for complex models.

Abstract

As Artificial Intelligence (AI) systems continue to grow in size and complexity, so does the difficulty of the quest for AI transparency. In a world of large models and complex AI systems, why do we explain AI and what should we explain? While explanations serve multiple functions, in the face of complexity humans have used and continue to use explanations to foster learning. In this position paper, we discuss how learning theories can be infused in the XAI lifecycle, as well as the key opportunities and challenges when adopting a learner-centered approach to assess, design and evaluate AI explanations. Building on past work, we argue that a learner-centered approach to Explainable AI (XAI) can enhance human agency and ease XAI risks mitigation, helping evolve the practice of human-centered XAI.