Explanation Hacking: The perils of algorithmic recourse

In Juan Manuel Durán & Giorgia Pozzi (eds.), Philosophy of science for machine learning: Core issues and new perspectives. Springer (forthcoming)
  Copy   BIBTEX

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.

Author Profiles

Atoosa Kasirzadeh
University of Toronto, St. George Campus (PhD)
Emily Sullivan
Utrecht University

Analytics

Added to PP
2024-03-22

Downloads
169 (#77,130)

6 months
169 (#18,543)

Historical graph of downloads since first upload
This graph includes both downloads from PhilArchive and clicks on external links on PhilPapers.
How can I increase my downloads?