From Explainable to Explanatory Artificial Intelligence: Toward a New Paradigm for Human-Centered Explanations through Generative AI

2025-08-08

AI Summary

Existing eXplainable AI (XAI) methods overemphasize algorithmic transparency, yielding abstract, static, and context-insensitive explanations that inadequately support effective human decision-making. Method: This paper introduces “explanatory AI” (xAI)—a novel paradigm positioning generative AI as a collaborative partner in human understanding. It employs narrative expression, adaptive personalization, and progressive disclosure to deliver contextualized, multimodal, and dynamic explanations. Grounded in human-centered cognitive principles, we systematically formulate an eight-dimensional conceptual model and implement a user-driven system via rapid contextual design, integrating generative AI, narrative generation, multimodal interaction, and adaptive recommendation. Contribution/Results: The framework enables a paradigm shift from algorithmic transparency to human-centered understanding. Empirical evaluation with healthcare professionals demonstrates significantly higher preference for its context-sensitive explanations, validating both efficacy and practical necessity.

Technology Category

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

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications

Abstract

Current explainable AI (XAI) approaches prioritize algorithmic transparency and present explanations in abstract, non-adaptive formats that often fail to support meaningful end-user understanding. This paper introduces "Explanatory AI" as a complementary paradigm that leverages generative AI capabilities to serve as explanatory partners for human understanding rather than providers of algorithmic transparency. While XAI reveals algorithmic decision processes for model validation, Explanatory AI addresses contextual reasoning to support human decision-making in sociotechnical contexts. We develop a definition and systematic eight-dimensional conceptual model distinguishing Explanatory AI through narrative communication, adaptive personalization, and progressive disclosure principles. Empirical validation through Rapid Contextual Design methodology with healthcare professionals demonstrates that users consistently prefer context-sensitive, multimodal explanations over technical transparency. Our findings reveal the practical urgency for AI systems designed for human comprehension rather than algorithmic introspection, establishing a comprehensive research agenda for advancing user-centered AI explanation approaches across diverse domains and cultural contexts.

Problem

• Shifting from algorithmic transparency to human-centered explanations using generative AI
• Addressing contextual reasoning for better human decision-making in sociotechnical settings
• Developing adaptive, narrative-driven explanations preferred over technical transparency

Innovation

• Generative AI for human-centered explanations
• Narrative communication and adaptive personalization
• Context-sensitive multimodal explanation design