What values should an agent align with? An empirical comparison of general and context-specific values

• Published in: Autonomous agents and multi-agent systems Vol. 36; no. 1; p. 23
• Main Authors: Liscio, Enrico, van der Meer, Michiel, Siebert, Luciano C., Jonker, Catholijn M., Murukannaiah, Pradeep K.
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.04.2022
• Subjects: Artificial Intelligence; Computer Science; Computer Systems Organization and Communication Networks; Software Engineering/Programming and Operating Systems; User Interfaces and Human Computer Interaction; Context; Values; Ethics; NLP; Schwartz; Axies
• ISSN: 1387-2532; 1573-7454
• DOI: 10.1007/s10458-022-09550-0

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.