Beyond Technocratic XAI: The Who, What & How in Explanation Design

2025-08-12

AI Summary

Current XAI practices face a core challenge: explanation generation is inherently context-dependent, yet most technical approaches neglect user background, needs, and delivery modalities—undermining accessibility, transparency, and ethical accountability. This paper transcends the technology-centric paradigm by systematically integrating design thinking for the first time, proposing a triadic, context-aware explanation design framework grounded in “for whom,” “what to explain,” and “how to convey.” Drawing on human-computer interaction principles, socio-technical systems theory, and contextual analysis methods, the framework internalizes cognitive fairness, social justice, and accountable governance as core design dimensions. It provides practitioners with an actionable guide for developing XAI systems, significantly enhancing explanation comprehensibility, fairness, and responsibility. Ultimately, it advances XAI’s evolution from a technical artifact toward a responsible socio-technical practice. (149 words)

Technology Category

• Humans and AI: Explainable AI (XAI) for Human Understanding
• Philosophy and Ethics of AI: Accountability, Interpretability & Explainability
• Machine Learning: Ethics, Bias, and Fairness

Application Category

• User Modeling, Personalization and Recommendation: Accountability, Transparency, and Ethics for personalization
• Responsible Web: Algorithmic accountability and transparency on the web
• Economics, Online Markets and Human Computation: Fairness and ethical considerations in crowd work and in human-in-the-loop AI systems

Abstract

The field of Explainable AI (XAI) offers a wide range of techniques for making complex models interpretable. Yet, in practice, generating meaningful explanations is a context-dependent task that requires intentional design choices to ensure accessibility and transparency. This paper reframes explanation as a situated design process -- an approach particularly relevant for practitioners involved in building and deploying explainable systems. Drawing on prior research and principles from design thinking, we propose a three-part framework for explanation design in XAI: asking Who needs the explanation, What they need explained, and How that explanation should be delivered. We also emphasize the need for ethical considerations, including risks of epistemic inequality, reinforcing social inequities, and obscuring accountability and governance. By treating explanation as a sociotechnical design process, this framework encourages a context-aware approach to XAI that supports effective communication and the development of ethically responsible explanations.

Problem

• Addressing context-dependent meaningful explanations in XAI
• Proposing a framework for Who, What, How in explanation design
• Incorporating ethical considerations to avoid social inequities

Innovation

• Situated design process for XAI explanations
• Three-part framework: Who, What, How
• Ethical considerations in explanation design