Explanation Hacking: The perils of algorithmic recourse

Emily Sullivan, Atoosa Kasirzadeh
3/22/2024
cs.CYcs.AI

No confident code implementation found for this paper.

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Explainable AI Isn't Enough! Rethinking Algorithmic Contestability

82% match2026

Performative Validity of Recourse Explanations

82% match2025

We Need Explanation Cards to Connect Explanation Algorithms to the Real World

81% match2026

Does Explainable AI Have Moral Value?

80% match2023

Can AI Explanations Make You Change Your Mind?

80% match2025

From Universal to Individualized Actionability: Revisiting Personalization in Algorithmic Recourse

80% match2026

Cite this paper

@article{sullivan2024explanation,
  title  = {Explanation Hacking: The perils of algorithmic recourse},
  author = {Emily Sullivan and Atoosa Kasirzadeh},
  year   = {2024},
  eprint = {2406.11843},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2406.11843v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2406.11843.svg)](https://codeofpaper.com/paper/2406.11843)

Discussion