Sullivan, Emily and Kasirzadeh, Atoosa (2024) Explanation Hacking: The perils of algorithmic recourse. [Preprint]

Preview

Text Explanation_hacking_Sullivan_Kasirzadeh.pdf Download (421kB) | Preview

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.

---

Export/Citation:

EndNote | BibTeX | Dublin Core | ASCII/Text Citation (Chicago) | HTML Citation | OpenURL

Social Networking:

Share |

---

Item Type:	Preprint
Creators:	Creators Email ORCID Sullivan, Emily eesullivan29@gmail.com 0000-0002-2073-5384 Kasirzadeh, Atoosa atoosa.kasirzadeh@mail.utoronto.ca
Keywords:	counterfactual explanation; algorithmic recourse, understanding, ethics of AI
Subjects:	Specific Sciences > Artificial Intelligence > AI and Ethics General Issues > Ethical Issues General Issues > Explanation Specific Sciences > Artificial Intelligence > Machine Learning General Issues > Technology
Depositing User:	Dr. Emily Sullivan
Date Deposited:	22 Mar 2024 16:46
Last Modified:	22 Mar 2024 16:46
Item ID:	23215
Subjects:	Specific Sciences > Artificial Intelligence > AI and Ethics General Issues > Ethical Issues General Issues > Explanation Specific Sciences > Artificial Intelligence > Machine Learning General Issues > Technology
Date:	2024
URI:	https://philsci-archive.pitt.edu/id/eprint/23215

Monthly Views for the past 3 years

Monthly Downloads for the past 3 years

Plum Analytics

Actions (login required)

View Item