Beyond Explainable AI (XAI): An Overdue Paradigm Shift and Post-XAI Research Directions
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.
Keywords
Cite
@article{arxiv.2602.24176,
title = {Beyond Explainable AI (XAI): An Overdue Paradigm Shift and Post-XAI Research Directions},
author = {Saleh Afroogh and Syed Ishtiaque Ahmed and Petra Ahrweiler and David Alvarez-Melis and Mansur Maturidi Arief and Emilia Barakova and Falco J. Bargagli-Stoffi and Erdem Biyik and Hanjie Chen and Xiang 'Anthony' Chen and Robert Alan Clements and Keeley Crockett and Amit Dhurandhar and Fethiye Irmak Dogan and Mollie Dollinger and Motahhare Eslami and Aldo A Faisal and Arya Farahi and Melanie F. Pradier and Saadia Gabriel and Diego Garcia-Olano and Marzyeh Ghassemi and Shaona Ghosh and Hatice Gunes and Ehsan Hajiramezanali and Stefan Haufe and Biwei Huang and Angel Hwang and Md Tauhidul Islam and Junfeng Jiao and Amir-Hossein Karimi and Saber Kazeminasab and Anastasia Kuzminykh and William La Cava and Brian Y. Lim and Xiaofeng Liu and Mohammad R. K. Mofrad and Alicia Parrish and Maria Perez-Ortiz and Shriti Raj and Swabha Swayamdipta and Salmonn Talebi and Kush R. Varshney and Mihaela Vorvoreanu and Lily Weng and Alice Xiang and Yiming Xu and Ding Zhao and Jieyu Zhao},
journal= {arXiv preprint arXiv:2602.24176},
year = {2026}
}