Expected Moral Shortfall for Ethical Competence in Decision-making Models

TL;DR

This paper introduces a new approach to embedding ethical competence in AI decision-making by modeling moral risk as an Expected Moral Shortfall, and compares various techniques for ethical integration.

Contribution

It presents a novel mathematical discretization of morality, introduces the concept of Expected Moral Shortfall, and evaluates techniques for ethical competence in AI models.

Findings

The proposed EMS metric effectively quantifies moral risk in AI decisions.

The new discretization technique outperforms existing methods on tested datasets.

Tradeoffs between model performance and ethical competence are analyzed.

Abstract

Moral cognition is a crucial yet underexplored aspect of decision-making in AI models. Regardless of the application domain, it should be a consideration that allows for ethically aligned decision-making. This paper presents a multifaceted contribution to this research space. Firstly, a comparative analysis of techniques to instill ethical competence into AI models has been presented to gauge them on multiple performance metrics. Second, a novel mathematical discretization of morality and a demonstration of its real-life application have been conveyed and tested against other techniques on two datasets. This value is modeled as the risk of loss incurred by the least moral cases, or an Expected Moral Shortfall (EMS), which we direct the AI model to minimize in order to maximize its performance while retaining ethical competence. Lastly, the paper discusses the tradeoff between preliminary AI decision-making metrics such as model performance, complexity, and scale of ethical competence to recognize the true extent of practical social impact.