Towards Machine Theory of Mind with Large Language Model-Augmented Inverse Planning

TL;DR

This paper introduces a hybrid approach combining large language models and Bayesian inverse planning to improve machine Theory of Mind, enabling better mental state prediction and reasoning in complex scenarios.

Contribution

It presents a novel hybrid method that leverages LLMs and inverse planning, enhancing ToM prediction accuracy and scalability over existing models.

Findings

Achieves near-optimal results on ToM tasks inspired by inverse planning.

Outperforms LLM-only models on reasoning tasks, even with smaller LLMs.

Demonstrates potential for predicting mental states in open-ended scenarios.

Abstract

We propose a hybrid approach to machine Theory of Mind (ToM) that uses large language models (LLMs) as a mechanism for generating hypotheses and likelihood functions with a Bayesian inverse planning model that computes posterior probabilities for an agent's likely mental states given its actions. Bayesian inverse planning models can accurately predict human reasoning on a variety of ToM tasks, but these models are constrained in their ability to scale these predictions to scenarios with a large number of possible hypotheses and actions. Conversely, LLM-based approaches have recently demonstrated promise in solving ToM benchmarks, but can exhibit brittleness and failures on reasoning tasks even when they pass otherwise structurally identical versions. By combining these two methods, this approach leverages the strengths of each component, closely matching optimal results on a task inspired by prior inverse planning models and improving performance relative to models that utilize LLMs alone or with chain-of-thought prompting, even with smaller LLMs that typically perform poorly on ToM tasks. We also exhibit the model's potential to predict mental states on open-ended tasks, offering a promising direction for future development of ToM models and the creation of socially intelligent generative agents.