Beyond Explainable AI (XAI): An Overdue Paradigm Shift and Post-XAI Research Directions

TL;DR

This paper critically examines current XAI approaches, identifies fundamental flaws, and proposes a new paradigm shift emphasizing verification, epistemology, user context, and model-centered interpretability for reliable AI development.

Contribution

It introduces a synthesized paradigm shift with four components to address limitations of current XAI and guide future post-XAI research directions.

Findings

XAI exhibits significant flaws experimentally.

Current XAI is paradoxical conceptually.

Further reform efforts may worsen confusion.

Abstract

This study provides a cross-disciplinary examination of Explainable Artificial Intelligence (XAI) approaches-focusing on deep neural networks (DNNs) and large language models (LLMs)-and identifies empirical and conceptual limitations in current XAI. We discuss critical symptoms that stem from deeper root causes (i.e., two paradoxes, two conceptual confusions, and five false assumptions). These fundamental problems within the current XAI research field reveal three insights: experimentally, XAI exhibits significant flaws; conceptually, it is paradoxical; and pragmatically, further attempts to reform the paradoxical XAI might exacerbate its confusion-demanding fundamental shifts and new research directions. To move beyond XAI's limitations, we propose a four-pronged synthesized paradigm shift toward reliable and certified AI development. These four components include: verification-focused Interactive AI (IAI) to establish scientific community protocols for certifying AI system performance rather than attempting post-hoc explanations, AI Epistemology for rigorous scientific foundations, User-Sensible AI to create context-aware systems tailored to specific user communities, and Model-Centered Interpretability for faithful technical analysis-together offering comprehensive post-XAI research directions.