Position: Explainability Research Must Prioritize Foundations over Ad-hoc Methods

Researchers argue that the field of Explainable AI (XAI) must shift focus from developing ad-hoc methods to addressing foundational challenges such as unclear problem formulations and lack of evaluation standards. A position paper analyzing recent conference papers and a practitioner survey finds that explanations rarely influence real-world workflows due to these structural gaps. The authors propose a checklist to guide XAI toward human-centered, action-oriented systems.

arXiv:2607.14123v1 Announce Type: new Abstract: Despite the proliferation 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 & 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.