Kantian Deontology Meets AI Alignment: Towards Morally Grounded Fairness Metrics

TL;DR

This paper explores integrating Kantian deontological ethics into AI fairness metrics to promote morally grounded and principle-based approaches, addressing the current utilitarian dominance in AI fairness.

Contribution

It introduces a novel framework combining Kantian ethics with AI fairness metrics, emphasizing duties and principles over consequences for more morally aligned AI systems.

Findings

Kantian ethics can be effectively incorporated into AI fairness metrics.

The framework promotes fairness based on moral duties rather than solely outcomes.

It offers a new perspective for balancing justice and utility in AI systems.

Abstract

Deontological ethics, specifically understood through Immanuel Kant, provides a moral framework that emphasizes the importance of duties and principles, rather than the consequences of action. Understanding that despite the prominence of deontology, it is currently an overlooked approach in fairness metrics, this paper explores the compatibility of a Kantian deontological framework in fairness metrics, part of the AI alignment field. We revisit Kant's critique of utilitarianism, which is the primary approach in AI fairness metrics and argue that fairness principles should align with the Kantian deontological framework. By integrating Kantian ethics into AI alignment, we not only bring in a widely-accepted prominent moral theory but also strive for a more morally grounded AI landscape that better balances outcomes and procedures in pursuit of fairness and justice.