A computational framework for human values

TL;DR

This paper introduces a formal computational framework based on social sciences to systematically understand and incorporate human values into ethical AI design, addressing a key gap in value alignment research.

Contribution

It proposes the first formal, computational definition of human values rooted in social sciences, enabling interdisciplinary investigation for ethical AI development.

Findings

Provides a foundational formal framework for human values

Facilitates systematic investigation into value-based AI ethics

Supports development of AI aligned with human values

Abstract

In the diverse array of work investigating the nature of human values from psychology, philosophy and social sciences, there is a clear consensus that values guide behaviour. More recently, a recognition that values provide a means to engineer ethical AI has emerged. Indeed, Stuart Russell proposed shifting AI's focus away from simply ``intelligence'' towards intelligence ``provably aligned with human values''. This challenge -- the value alignment problem -- with others including an AI's learning of human values, aggregating individual values to groups, and designing computational mechanisms to reason over values, has energised a sustained research effort. Despite this, no formal, computational definition of values has yet been proposed. We address this through a formal conceptual framework rooted in the social sciences, that provides a foundation for the systematic, integrated and interdisciplinary investigation into how human values can support designing ethical AI.