Print Email Facebook Twitter What values should an agent align with? Title What values should an agent align with?: An empirical comparison of general and context-specific values Author Liscio, E. (TU Delft Interactive Intelligence) van der Meer, M.T. (TU Delft Interactive Intelligence; Universiteit Leiden) Cavalcante Siebert, L. (TU Delft Interactive Intelligence) Jonker, C.M. (TU Delft Interactive Intelligence; Universiteit Leiden) Murukannaiah, P.K. (TU Delft Interactive Intelligence) Date 2022 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. Subject ValuesEthicsSchwartzContextAxiesNLP To reference this document use: http://resolver.tudelft.nl/uuid:d8b33c63-d4ee-4c70-b00d-a9fde78e5136 DOI https://doi.org/10.1007/s10458-022-09550-0 ISSN 1387-2532 Source Autonomous Agents and Multi-Agent Systems, 36 (1), 1-32 Part of collection Institutional Repository Document type journal article Rights © 2022 E. Liscio, M.T. van der Meer, L. Cavalcante Siebert, C.M. Jonker, P.K. Murukannaiah Files PDF s10458_022_09550_0.pdf 2.22 MB Close viewer /islandora/object/uuid:d8b33c63-d4ee-4c70-b00d-a9fde78e5136/datastream/OBJ/view