Quantifying Uncertainty in Machine Theory of Mind Across Time

Abstract

As intelligent interactive technologies advance, ensuring alignment with user preferences is critical. Machine theory of mind enablessystems to infer latent mental states from observed behaviors, similarly to humans. Currently, there is no formal mechanism for integrating multiple observations over time and quantifying the uncertainty of inferences as the function of accumulated evidence in a provably human-like way. This paper addresses the issue through Bayesian inference, proposing a model that maintains a posterior belief about mental states as a probability distribution, updated with observational data. The advantage of Bayesian statistics lies in the possibility of evaluating the certainty of these inferences. We validate the model’s human-like mental inference capabilities through an experiment.