Human-aware AI —A foundational framework for human–AI interaction

Abstract

We are living through a revolutionary moment in AI history. Users from diverse walks of life are adopting and using AI systems for their everyday use cases at a pace that has never been seen before. However, with this proliferation, there is also a growing recognition that many of the central open problems within AI are connected to how the user interacts with these systems. To name two prominent examples, consider the problems of explainability and value alignment. Each problem has received considerable attention within the wider AI community, and much promising progress has been made in addressing each of these individual problems. However, each of these problems tends to be studied in isolation, using very different theoretical frameworks, while a closer look at each easily reveals striking similarities between the two problems. In this article, I wish to discuss the framework of human-aware AI (HAAI) that aims to provide a unified formal framework to understand and evaluate human–AI interaction. We will see how this framework can be used to both understand explainability and value alignment and how the framework also lays out potential novel avenues to address these problems.