Dear XAI Community, We Need to Talk! Fundamental Misconceptions in Current XAI Research

TL;DR

This paper critically examines misconceptions in current Explainable AI research, highlighting issues with purpose clarity, ethical foundations, and methodological rigor, and suggests steps for more substantive future work.

Contribution

It identifies key misconceptions in XAI, critiques current practices, and proposes directions to improve the scientific rigor and ethical grounding of the field.

Findings

Many explanation techniques lack clear purpose

Current benchmarks may be misleading or superficial

Misguided goals like trust may hinder genuine understanding

Abstract

Despite progress in the field, significant parts of current XAI research are still not on solid conceptual, ethical, or methodological grounds. Unfortunately, these unfounded parts are not on the decline but continue to grow. Many explanation techniques are still proposed without clarifying their purpose. Instead, they are advertised with ever more fancy-looking heatmaps or only seemingly relevant benchmarks. Moreover, explanation techniques are motivated with questionable goals, such as building trust, or rely on strong assumptions about the 'concepts' that deep learning algorithms learn. In this paper, we highlight and discuss these and other misconceptions in current XAI research. We also suggest steps to make XAI a more substantive area of research.