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.
@article{arxiv.2306.04292,
title = {Dear XAI Community, We Need to Talk! Fundamental Misconceptions in Current XAI Research},
author = {Timo Freiesleben and Gunnar König},
journal= {arXiv preprint arXiv:2306.04292},
year = {2023}
}
Comments
A revised version of this preprint has been accepted at the World XAI Conference. It will be referenced as soon as it is published