Modeling and Reasoning with Preferences and Ethical Priorities in AI Systems

Abstract

Whatever we do in our everyday life, be it at work or in our personal activities, we need to make decisions. What to eat, where to go on vacation, what car to buy, which route to take to work, what job to choose, and many more. Some of these decisions are made in isolation, without any consultation with other individuals. But many of them are collective decisions that we make together with others. To make all these decisions, we usually rely on our subjective preferences over the possible options. If we need to buy a car, we may have preferences regarding its color, its maker, its engine type, and many other features. If we need to decide which restaurant to go for dinner, we may have preferences of location, facilities, food, drinks, and many other features.