Explanation Hacking: The perils of algorithmic recourse
Computers and Society
2024-06-19 v1 Artificial Intelligence
Abstract
We argue that the trend toward providing users with feasible and actionable explanations of AI decisions, known as recourse explanations, comes with ethical downsides. Specifically, we argue that recourse explanations face several conceptual pitfalls and can lead to problematic explanation hacking, which undermines their ethical status. As an alternative, we advocate that explanations of AI decisions should aim at understanding.
Cite
@article{arxiv.2406.11843,
title = {Explanation Hacking: The perils of algorithmic recourse},
author = {Emily Sullivan and Atoosa Kasirzadeh},
journal= {arXiv preprint arXiv:2406.11843},
year = {2024}
}