Towards Theory-based Moral AI: Moral AI with Aggregating Models Based on Normative Ethical Theory

TL;DR

This paper introduces MEC, an algorithm that aggregates models based on normative ethical theories to improve moral decision-making in AI under moral uncertainty, showing promising alignment with commonsense morality.

Contribution

It proposes the MEC algorithm that combines outputs from multiple normative ethical models to address moral uncertainty in AI.

Findings

MEC outputs correlate with commonsense morality.

MEC produces equal or more appropriate moral judgments than existing methods.

Experimental results validate MEC's effectiveness.

Abstract

Moral AI has been studied in the fields of philosophy and artificial intelligence. Although most existing studies are only theoretical, recent developments in AI have made it increasingly necessary to implement AI with morality. On the other hand, humans are under the moral uncertainty of not knowing what is morally right. In this paper, we implement the Maximizing Expected Choiceworthiness (MEC) algorithm, which aggregates outputs of models based on three normative theories of normative ethics to generate the most appropriate output. MEC is a method for making appropriate moral judgments under moral uncertainty. Our experimental results suggest that the output of MEC correlates to some extent with commonsense morality and that MEC can produce equally or more appropriate output than existing methods.