Classes of Aggregation Rules for Ethical Decision Making in Automated Systems

TL;DR

This paper explores aggregation rules for ethical decision-making in autonomous AI systems, focusing on preference representations and stability of the decision process to ensure socially acceptable outcomes.

Contribution

It introduces new aggregation rules based on preference profiles and analyzes their stability, aiding AI designers in justifying autonomous decisions.

Findings

Multiple aggregation rules satisfying ethical properties identified

Preference stability under variable information analyzed

Guidelines for designing ethically aligned autonomous systems provided

Abstract

We study a class of {\em aggregation rules} that could be applied to ethical AI decision-making. These rules yield the decisions to be made by automated systems based on the information of profiles of preferences over possible choices. We consider two different but very intuitive notions of preferences of an alternative over another one, namely {\it pairwise majority} and {\it position} dominance. Preferences are represented by permutation processes over alternatives and aggregation rules are applied to obtain results that are socially considered to be ethically correct. In this setting, we find many aggregation rules that satisfy desirable properties for an autonomous system. We also address the problem of the stability of the aggregation process, which is important when the information is variable. These results are a contribution for an AI designer that wants to justify the decisions made by an autonomous system.\\ \textit{Keywords:} Aggregation Operators; Permutation Process; Decision Analysis.