Machine Theory of Mind and the Structure of Human Values
This addresses the challenge of learning comprehensive human values for safe and ethical AI, though it appears incremental as it builds on existing theory of mind approaches.
The paper tackles the value generalization problem in AI by proposing that human values have a generative rational structure, enabling inference of values not just from behavior but also from other values using Bayesian Theory of Mind models.
Value learning is a crucial aspect of safe and ethical AI. This is primarily pursued by methods inferring human values from behaviour. However, humans care about much more than we are able to demonstrate through our actions. Consequently, an AI must predict the rest of our seemingly complex values from a limited sample. I call this the value generalization problem. In this paper, I argue that human values have a generative rational structure and that this allows us to solve the value generalization problem. In particular, we can use Bayesian Theory of Mind models to infer human values not only from behaviour, but also from other values. This has been obscured by the widespread use of simple utility functions to represent human values. I conclude that developing generative value-to-value inference is a crucial component of achieving a scalable machine theory of mind.