The dominant practice of AI alignment assumes (1) that preferences are an adequate
representation of human values,(2) that human rationality can be understood in terms of …

Constraining the actions of AI systems is one promising way to ensure that these systems
behave in a way that is morally acceptable to humans. But constraints alone come with …

If we want people to trust AI systems, we need to provide the systems we create with the
ability to discriminate between what humans would consider good and bad decisions. The …

Abstract We introduce Flexible Representative Democracy (FRD), a novel hybrid of
Representative Democracy and Direct Democracy in which voters can alter the issue …

In order to represent the preferences of a group of individuals, we introduce Probabilistic CP-
nets (PCP-nets). PCP-nets provide a compact language for representing probability …

Preference elicitation is an important component in many AI applications, including decision
support and recommender systems. Such systems must assess user preferences, based on …

In many scenarios including multi-agent systems and recommender systems, user
preference play a key role in driving the decisions the system makes. Thus it is important to …

We introduce PCP-nets, a formalism to model qualitative conditional preferences with
probabilistic uncertainty. PCP-nets generalise CP-nets by allowing for uncertainty over the …

ABSTRACT PCP-nets generalize CP-nets to model conditional preferences with
probabilistic uncertainty. In this paper we use PCP-nets in a multiagent context to compactly …

The generation of preferences represented as CP-nets for experiments and empirical testing
has typically been done in an ad hoc manner that may have introduced a large statistical …