Zero, Finite, and Infinite Belief History of Theory of Mind Reasoning in Large Language Models

TL;DR

This paper introduces a new framework and benchmark for evaluating Theory of Mind reasoning in Large Language Models across different belief history complexities, revealing surprising performance patterns and potential for future AI development.

Contribution

It proposes a novel taxonomy and multi-round game benchmark to assess ToM reasoning in LLMs, highlighting performance differences and unexpected model strengths.

Findings

Zero Belief History performance exceeds Finite Belief History.

Small models outperform large models on some ToM tasks.

The benchmark encourages development of more complex ToM-capable AI systems.

Abstract

Large Language Models (LLMs) have recently shown a promise and emergence of Theory of Mind (ToM) ability and even outperform humans in certain ToM tasks. To evaluate and extend the boundaries of the ToM reasoning ability of LLMs, we propose a novel concept, taxonomy, and framework, the ToM reasoning with Zero, Finite, and Infinite Belief History and develop a multi-round text-based game, called $\textit{Pick the Right Stuff}$, as a benchmark. We have evaluated six LLMs with this game and found their performance on Zero Belief History is consistently better than on Finite Belief History. In addition, we have found two of the models with small parameter sizes outperform all the evaluated models with large parameter sizes. We expect this work to pave the way for future ToM benchmark development and also for the promotion and development of more complex AI agents or systems which are required to be equipped with more complex ToM reasoning ability.