Tag
The paper introduces VirtueMap, a framework that profiles large language models by evaluating their rankings of ethical dilemma responses through an Aristotelian virtue ethics lens, using a validated common-sense ground truth.
This paper introduces a multi-agent environment based on the board game Fog of Love to evaluate affinity-based reinforcement learning for instilling virtuous behavior in AI agents. The authors demonstrate that localized affinities improve agent performance in both competitive and cooperative objectives, advancing machine ethics research beyond simple grid-world environments.