TY - GEN
T1 - Estimating Value Preferences in a Hybrid Participatory System
AU - Siebert, Luciano C.
AU - Liscio, Enrico
AU - Murukannaiah, Pradeep K.
AU - Kaptein, Lionel
AU - Spruit, Shannon
AU - Van Den Hoven, Jeroen
AU - Jonker, Catholijn
PY - 2022
Y1 - 2022
N2 - We propose methods for an AI agent to estimate the value preferences of individuals in a hybrid participatory system, considering a setting where participants make choices and provide textual motivations for those choices. We focus on situations where there is a conflict between participants' choices and motivations, and operationalize the philosophical stance that 'valuing is deliberatively consequential.' That is, if a user's choice is based on a deliberation of value preferences, the value preferences can be observed in the motivation the user provides for the choice. Thus, we prioritize the value preferences estimated from motivations over the value preferences estimated from choices alone. We evaluate the proposed methods on a dataset of a large-scale survey on energy transition. The results show that explicitly addressing inconsistencies between choices and motivations improves the estimation of an individual's value preferences. The proposed methods can be integrated in a hybrid participatory system, where artificial agents ought to estimate humans' value preferences to pursue value alignment.
AB - We propose methods for an AI agent to estimate the value preferences of individuals in a hybrid participatory system, considering a setting where participants make choices and provide textual motivations for those choices. We focus on situations where there is a conflict between participants' choices and motivations, and operationalize the philosophical stance that 'valuing is deliberatively consequential.' That is, if a user's choice is based on a deliberation of value preferences, the value preferences can be observed in the motivation the user provides for the choice. Thus, we prioritize the value preferences estimated from motivations over the value preferences estimated from choices alone. We evaluate the proposed methods on a dataset of a large-scale survey on energy transition. The results show that explicitly addressing inconsistencies between choices and motivations improves the estimation of an individual's value preferences. The proposed methods can be integrated in a hybrid participatory system, where artificial agents ought to estimate humans' value preferences to pursue value alignment.
UR - https://www.scopus.com/pages/publications/85142156279
UR - https://www.scopus.com/pages/publications/85142156279#tab=citedBy
U2 - 10.3233/FAIA220193
DO - 10.3233/FAIA220193
M3 - Conference contribution
T3 - Frontiers in Artificial Intelligence and Applications
SP - 114
EP - 127
BT - HHAI2022: Augmenting Human Intellect
A2 - Schlobach, Stefan
A2 - Perez-Ortiz, Maria
A2 - Tielman, Myrthe
PB - IOS Press BV
T2 - 1st International Conference on Hybrid Human-Artificial Intelligence, HHAI 2022
Y2 - 13 June 2022 through 17 June 2022
ER -