March 22, 2024Open Access

Explanation Hacking: The perils of algorithmic recourse

Key Points

Key points are not available for this paper at this time.

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.

Read Full Paperexternally

Bookmark

View Full Paper

Cite This Study

Sullivan et al. (Fri,) studied this question.

synapsesocial.com/papers/68e72f5cb6db6435876a90b3 https://doi.org/https://doi.org/10.48550/arxiv.2406.11843

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

1Algorithmic Recourse2025
2Counterfactual Explanations via Locally-guided Sequential Algorithmic Recourse2025
3The Accuracy-Explainability Trade-off, the Right to Explanation, and the Implications for Organisations2026
4Accuracy is not all you need! The Reasons to Require AI Explainability2026
5Human-Centered Evaluation of Explanations in AI-Assisted Decision-Making2024 · 3 citations

Bookmark

View Full Paper