A Computational Framework of Human Values

Tools

Osman, Nardine and d'Inverno, Mark. 2024. 'A Computational Framework of Human Values'. In: AAMAS '23: International Conference on Autonomous Agents and Multiagent Systems. Auckland, New Zealand 6 - 10 May 2024. [Conference or Workshop Item]

Preview

Text
3635637.3663013.pdf - Published Version
Available under License Creative Commons Attribution.
Download (1MB) | Preview

Official URL: https://dl.acm.org/doi/10.5555/3635637.3663013

Abstract or Description

There is an increasing recognition of the need to engineer AI that respects and embodies human values. The value alignment problem, which identifies that need, has led to a growing body of research that investigates value learning, the aggregation of individual values into the values of groups, the alignment of norms with values, and the design of other computational mechanisms that reason over values in general. Yet despite these efforts, no foundational, computational model of human values has been proposed. In response, we propose a model for the computational representation of human values that builds upon a sustained body of research from social psychology.

Item Type:

Conference or Workshop Item (Paper)

Identification Number (DOI):

https://doi.org/10.5555/3635637.3663013

Additional Information:

This work has been supported by the EU-funded VALAWAI (# 101070930) project and the Spanish-funded VAE (# TED2021- 131295B-C31) and Rhymas (# PID2020-113594RB-100) projects.

Keywords:

formal modelling, human values, value representation

Departments, Centres and Research Units:

Computing

Dates: