From Algorithmic Black Boxes to Adaptive White Boxes: Declarative Decision-Theoretic Ethical Programs as Codes of Ethics

TL;DR

This paper proposes using declarative decision-theoretic ethical programs to formalize and implement codes of ethics in AI, enhancing transparency and accountability in machine ethical reasoning.

Contribution

It introduces a novel approach to formalize professional codes of ethics as declarative decision-theoretic programs for AI systems.

Findings

Proof-of-concept examples demonstrate the approach on toy dilemmas.

Application to gatekeeping domains shows potential for real-world use.

Enhances transparency and accountability in machine ethics.

Abstract

Ethics of algorithms is an emerging topic in various disciplines such as social science, law, and philosophy, but also artificial intelligence (AI). The value alignment problem expresses the challenge of (machine) learning values that are, in some way, aligned with human requirements or values. In this paper I argue for looking at how humans have formalized and communicated values, in professional codes of ethics, and for exploring declarative decision-theoretic ethical programs (DDTEP) to formalize codes of ethics. This renders machine ethical reasoning and decision-making, as well as learning, more transparent and hopefully more accountable. The paper includes proof-of-concept examples of known toy dilemmas and gatekeeping domains such as archives and libraries.