A Review on Machine Theory of Mind

TL;DR

This paper reviews recent advances in machine Theory of Mind, focusing on beliefs, desires, and intentions, highlighting datasets, methods, and challenges in standard evaluation and comparison.

Contribution

It provides a comprehensive overview of recent progress, compares models, and proposes the need for standardized datasets and assessment criteria in machine ToM research.

Findings

Summarizes recent datasets and methods for machine ToM

Highlights advantages and limitations of current models

Proposes standard evaluation criteria and large-scale datasets

Abstract

Theory of Mind (ToM) is the ability to attribute mental states to others, the basis of human cognition. At present, there has been growing interest in the AI with cognitive abilities, for example in healthcare and the motoring industry. Beliefs, desires, and intentions are the early abilities of infants and the foundation of human cognitive ability, as well as for machine with ToM. In this paper, we review recent progress in machine ToM on beliefs, desires, and intentions. And we shall introduce the experiments, datasets and methods of machine ToM on these three aspects, summarize the development of different tasks and datasets in recent years, and compare well-behaved models in aspects of advantages, limitations and applicable conditions, hoping that this study can guide researchers to quickly keep up with latest trend in this field. Unlike other domains with a specific task and resolution framework, machine ToM lacks a unified instruction and a series of standard evaluation tasks, which make it difficult to formally compare the proposed models. We argue that, one method to address this difficulty is now to present a standard assessment criteria and dataset, better a large-scale dataset covered multiple aspects of ToM.