Beyond Fairness and Explanation

摘要

The topics of fairness and explainability have dominated recent discussions of ethical AI. However, these are only two criteria that would make artificial agents anywhere close to ethical. I frame the question of ethical AI, and especially ethical social robots, as the question of what would make them worthy of human trust and actually eliciting human trust. Relying on a recent investigation of the multi-dimensionality of human trust, I lay out five criteria of trustworthiness-being competent, reliable, transparent, benevolent, and having ethical integrity. I will argue that an essential ingredient of such trustworthiness is norm competence-the ability to represent, comply with, and learn relevant social-moral norms (including fairness as one among many). I discuss the challenges to implementing norm competence and the critical role that justification, not just explanation, will play in providing evidence for such competence.