Formalising trade-offs beyond algorithmic fairness: lessons from ethical philosophy and welfare economics

Journal article

The widespread use of artificial intelligence (AI) systems across various domains is increasingly surfacing issues related to algorithmic fairness, especially in high-stakes scenarios. Thus, critical considerations of how fairness in AI systems might be improved -- and what measures are available to aid this process -- are overdue. Many researchers and policymakers see explainable AI (XAI) as a promising way to increase fairness in AI systems. However, there is a wide variety of XAI methods and fairness conceptions expressing different desiderata, and the precise connections between XAI and fairness remain largely nebulous. Besides, different measures to increase algorithmic fairness might be applicable at different points throughout an AI system's lifecycle. Yet, there currently is no coherent mapping of fairness desiderata along the AI lifecycle. In this paper, we we distill eight fairness desiderata, map them along the AI lifecycle, and discuss how XAI could help address each of them. We hope to provide orientation for practical applications and to inspire XAI research specifically focused on these fairness desiderata

Authors: Lee, MSA; Floridi, L; Singh, J

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: Springer Nature
• Journal: AI and Ethics
• Volume: 1
• Issue: 4
• Pages: 529-544
• Publication date: 2021-06-12
• DOI: 10.1007/s43681-021-00067-y
• ISSN: 2730-5953
• Language: English
• Keywords: Autonomy; Reductionism; Epistemology; Fairness measure; Welfare; Management science; Mathematics; Computer science; Economics; Psychology; Inequality; Computer security; Law; Social psychology; Sociology; Decision maker; Political science; Key (lock); Capability approach