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


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.



External links

  • This entry has no external links. Add one.
Setup an account with your affiliations in order to access resources via your University's proxy server

Through your library

Similar books and articles

From Explanation to Recommendation: Ethical Standards for Algorithmic Recourse.Emily Sullivan & Philippe Verreault-Julien - forthcoming - Proceedings of the 2022 AAAI/ACM Conference on AI, Ethics, and Society (AIES’22).
The philosophical basis of algorithmic recourse.Suresh Venkatasubramanian & Mark Alfano - forthcoming - Fairness, Accountability, and Transparency Conference 2020.
Micro-level model explanation and counterfactual constraint.Samuel Schindler - 2022 - European Journal for Philosophy of Science 12 (2):1-27.
Towards a Monist Theory of Explanation.Carsten Held - 2019 - Journal for General Philosophy of Science / Zeitschrift für Allgemeine Wissenschaftstheorie 50 (4):447-475.
The Circumstances of Civil Recourse.Rebecca Stone - 2021 - Law and Philosophy 41 (1):39-62.


Added to PP

169 (#115,277)

6 months
169 (#18,871)

Historical graph of downloads
How can I increase my downloads?

Author Profiles

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

Citations of this work

No citations found.

Add more citations

References found in this work

What is a (social) structural explanation?Sally Haslanger - 2016 - Philosophical Studies 173 (1):113-130.
Understanding, Explanation, and Scientific Knowledge.Kareem Khalifa - 2017 - Cambridge, UK: Cambridge University Press.
Explaining Explanations in AI.Brent Mittelstadt - forthcoming - FAT* 2019 Proceedings 1.

View all 30 references / Add more references