Inferring Values via Hybrid Intelligence

Enrico Liscio, Roger Lera-Leri, Filippo Bistaffa, Roel I. J. Dobbe, Catholijn M. Jonker, Maite López-Sánchez, Juan A. Rodríguez-Aguilar, Pradeep K. Murukannaiah

Abstract: Values, such as freedom and safety, are the core motivations that guide us humans. A prerequisite for creating value-aligned multiagent systems that involve humans and artificial agents is value inference, the process of identifying values and reasoning about human value preferences. We introduce a framework that connects the value inference steps, and motivate why a hybrid intelligence approach is instrumental for its success. We also highlight the multidisciplinary research challenges that hybrid value inference entails.