Explanation Hacking: The perils of algorithmic recourse

2024/03/22 by Emily Sullivan, Atoosa Kasirzadeh, Sullivan, Emily +1 · 1 citation
Social Sciences · #Ethics and Social Impacts of AI

paper · pdf · doi:10.48550/arxiv.2406.11843

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.

Cited by

• Algorithmic Fairness amid Social Determinants: Reflection, Characterization, and Approach

Related

• Beware of "Explanations" of AI
• On the Impact of Explanations on Understanding of Algorithmic Decision-Making
• Some Critical and Ethical Perspectives on the Empirical Turn of AI Interpretability
• A Survey of Algorithmic Recourse: Contrastive Explanations and Consequential Recommendations
• Manipulation Risks in Explainable AI: The Implications of the Disagreement Problem