TY - JOUR
T1 - What values should an agent align with?
T2 - An empirical comparison of general and context-specific values
AU - Liscio, E.
AU - van der Meer, M.T.
AU - Cavalcante Siebert, L.
AU - Jonker, C.M.
AU - Murukannaiah, P.K.
PY - 2022
Y1 - 2022
N2 - 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.
AB - 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.
KW - Values
KW - Ethics
KW - Schwartz
KW - Context
KW - Axies
KW - NLP
UR - http://www.scopus.com/inward/record.url?scp=85127238838&partnerID=8YFLogxK
U2 - 10.1007/s10458-022-09550-0
DO - 10.1007/s10458-022-09550-0
M3 - Article
SN - 1387-2532
VL - 36
SP - 1
EP - 32
JO - Autonomous Agents and Multi-Agent Systems
JF - Autonomous Agents and Multi-Agent Systems
IS - 1
M1 - 23
ER -