arXiv Open Access 2024

Explanation Hacking: The perils of algorithmic recourse

Emily Sullivan Atoosa Kasirzadeh

Lihat Sumber

Abstrak

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.

Topik & Kata Kunci

cs.CY cs.AI

Penulis (2)

Emily Sullivan

Atoosa Kasirzadeh

Format Sitasi

APA MLA BibTeX

Sullivan, E., Kasirzadeh, A. (2024). Explanation Hacking: The perils of algorithmic recourse. https://arxiv.org/abs/2406.11843

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2024
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓