Learning the Value Systems of Societies from Preferences

TL;DR

This paper introduces a method to learn societal value systems by clustering individual preferences, capturing diverse group values rather than aggregating individual ones, with a real-world travel decision case study.

Contribution

It formalizes the problem of societal value system learning and proposes a deep clustering approach to identify shared and diverse societal values.

Findings

Successfully learned multiple societal value systems from preference data

Captured diverse group values rather than simple aggregation

Demonstrated effectiveness on real travel decision data

Abstract

Aligning AI systems with human values and the value-based preferences of various stakeholders (their value systems) is key in ethical AI. In value-aware AI systems, decision-making draws upon explicit computational representations of individual values (groundings) and their aggregation into value systems. As these are notoriously difficult to elicit and calibrate manually, value learning approaches aim to automatically derive computational models of an agent's values and value system from demonstrations of human behaviour. Nonetheless, social science and humanities literature suggest that it is more adequate to conceive the value system of a society as a set of value systems of different groups, rather than as the simple aggregation of individual value systems. Accordingly, here we formalize the problem of learning the value systems of societies and propose a method to address it based on heuristic deep clustering. The method learns socially shared value groundings and a set of diverse value systems representing a given society by observing qualitative value-based preferences from a sample of agents. We evaluate the proposal in a use case with real data about travelling decisions.