Embedding Values in Artificial Intelligence (AI) Systems

TLDR

Ethical principles such as autonomy, non‑maleficence, fairness, transparency, explainability, and accountability have been proposed by bodies like the EU High‑Level Expert Group and IEEE for AI design and deployment, framing AI as a sociotechnical system of artifacts, agents, and norms. The study seeks to determine how to ensure and verify that AI systems respect the proposed ethical values. The authors propose an account that defines embodied values as the outcome of design activities intended to embed those values into AI systems. The paper discusses challenges and opportunities in embedding values and offers lessons for improving value embedding in AI systems.

Abstract

Abstract Organizations such as the EU High-Level Expert Group on AI and the IEEE have recently formulated ethical principles and (moral) values that should be adhered to in the design and deployment of artificial intelligence (AI). These include respect for autonomy, non-maleficence, fairness, transparency, explainability, and accountability. But how can we ensure and verify that an AI system actually respects these values? To help answer this question, I propose an account for determining when an AI system can be said to embody certain values. This account understands embodied values as the result of design activities intended to embed those values in such systems. AI systems are here understood as a special kind of sociotechnical system that, like traditional sociotechnical systems, are composed of technical artifacts, human agents, and institutions but—in addition—contain artificial agents and certain technical norms that regulate interactions between artificial agents and other elements of the system. The specific challenges and opportunities of embedding values in AI systems are discussed, and some lessons for better embedding values in AI systems are drawn.