What values should an agent align with?

An empirical comparison of general and context-specific values

Journal Article (2022)
Author(s)

E. Liscio (TU Delft - Interactive Intelligence)

Michiel Van Der Meer (TU Delft - Interactive Intelligence, Universiteit Leiden)

Luciano Siebert (TU Delft - Interactive Intelligence)

Catholijn M. Jonker (TU Delft - Interactive Intelligence, Universiteit Leiden)

Pradeep K. Murukannaiah (TU Delft - Interactive Intelligence)

Research Group
Interactive Intelligence
Copyright
© 2022 E. Liscio, M.T. van der Meer, L. Cavalcante Siebert, C.M. Jonker, P.K. Murukannaiah
DOI related publication
https://doi.org/10.1007/s10458-022-09550-0
More Info
expand_more
Publication Year
2022
Language
English
Copyright
© 2022 E. Liscio, M.T. van der Meer, L. Cavalcante Siebert, C.M. Jonker, P.K. Murukannaiah
Research Group
Interactive Intelligence
Issue number
1
Volume number
36
Pages (from-to)
1-32
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

The pursuit of values drives human behavior and promotes cooperation. Existing research is focused on general values (e.g., Schwartz) that transcend contexts. However, context-specific values are necessary to (1) understand human decisions, and (2) engineer intelligent agents that can elicit and align with human values. We propose Axies, a hybrid (human and AI) methodology to identify context-specific values. Axies simplifies the abstract task of value identification as a guided value annotation process involving human annotators. Axies exploits the growing availability of value-laden text corpora and Natural Language Processing to assist the annotators in systematically identifying context-specific values. We evaluate Axies in a user study involving 80 human subjects. In our study, six annotators generate value lists for two timely and important contexts: Covid-19 measures and sustainable Energy. We employ two policy experts and 72 crowd workers to evaluate Axies value lists and compare them to a list of general (Schwartz) values. We find that Axies yields values that are (1) more context-specific than general values, (2) more suitable for value annotation than general values, and (3) independent of the people applying the methodology.

Files

S10458_022_09550_0.pdf
(pdf | 2.22 Mb)
License info not available