Leveraging Generative AI for Human Understanding: Meta-Requirements and Design Principles for Explanatory AI as a new Paradigm

TL;DR

This paper proposes Explanatory AI as a new paradigm that uses generative and multimodal capabilities to enhance human understanding, addressing limitations of traditional explainable AI by focusing on interpretive sense-making and personalized communication.

Contribution

It introduces a novel framework for Explanatory AI, synthesizing multidisciplinary insights and empirical evidence to define meta-requirements and design principles for human-centered explanations.

Findings

Identifies five key dimensions differentiating Explanatory AI from traditional XAI.

Synthesizes theory and empirical data to establish design principles.

Proposes five meta-requirements for effective Explanatory AI systems.

Abstract

Artificial intelligence (AI) systems increasingly support decision-making across critical domains, yet current explainable AI (XAI) approaches prioritize algorithmic transparency over human comprehension. While XAI methods reveal computational processes for model validation and audit, end users require explanations integrating domain knowledge, contextual reasoning, and professional frameworks. This disconnect reveals a fundamental design challenge: existing AI explanation approaches fail to address how practitioners actually need to understand and act upon recommendations. This paper introduces Explanatory AI as a complementary paradigm where AI systems leverage generative and multimodal capabilities to serve as explanatory partners for human understanding. Unlike traditional XAI that answers "How did the algorithm decide?" for validation purposes, Explanatory AI addresses "Why does this make sense?" for practitioners making informed decisions. Through theory-informed design, we synthesize multidisciplinary perspectives on explanation from cognitive science, communication research, and education with empirical evidence from healthcare contexts and AI expert interviews. Our analysis identifies five dimensions distinguishing Explanatory AI from traditional XAI: explanatory purpose (from diagnostic to interpretive sense-making), communication mode (from static technical to dynamic narrative interaction), epistemic stance (from algorithmic correspondence to contextual plausibility), adaptivity (from uniform design to personalized accessibility), and cognitive design (from information overload to cognitively aligned delivery). We derive five meta-requirements specifying what systems must achieve and formulate ten design principles prescribing how to build them.