Despite the increasing number of Explainable AI (XAI) techniques, from feature attributions to sparse autoencoders, explanations rarely influence real-world workflows. In practice, they are often generated and discarded without guiding meaningful action. This gap reflects foundational shortcomings: research has not yet established methodologies for integrating explanations into end-to-end, human-in-the-loop systems.
This position paper argues that the machine learning community must pivot from ad-hoc XAI methods toward addressing foundational and structural challenges, including unclear problem formulations, underspecified evaluation objectives, and the absence of pipelines for explanation-driven feedback. We support this claim through an analysis of recent ICML, NeurIPS, and ICLR papers and a survey of XAI practitioners, revealing recurring issues that limit cumulative progress.
We conclude by outlining a practical checklist designed to shift XAI toward a more human-centered, action-oriented paradigm. By emphasizing foundational clarity over the development of ad-hoc methods, we hope to provide a roadmap for integrating explanations into actionable, feedback-driven AI systems.
Blogger's Review: This paper highlights the foundational issues in explainable AI, pointing out the limitations of current XAI methods. Promoting a more structured and human-centered approach can significantly enhance the practical value and impact of XAI. It is crucial for more researchers to focus on this important area, driving the integration of theory and practice.