ToM-LM: Delegating Theory of Mind Reasoning to External Symbolic Executors in Large Language Models

TL;DR

This paper introduces ToM-LM, a method that enhances large language models' theory of mind reasoning by delegating complex belief reasoning to an external symbolic model checker, resulting in improved accuracy and transparency.

Contribution

It proposes a novel approach combining fine-tuned LLMs with external symbolic executors for better ToM reasoning, especially in belief attribution tasks.

Findings

Significant improvement over baselines in ToM tasks

Enhanced transparency and verifiability of reasoning process

Potential to generalize to other ToM aspects

Abstract

Theory of Mind (ToM) refers to the ability of individuals to attribute mental states to others. While Large Language Models (LLMs) have shown some promise with ToM ability, they still struggle with complex ToM reasoning. Our approach leverages an external symbolic executor, specifically the SMCDEL model checker, and fine-tuning to improve the ToM reasoning ability of LLMs. In our approach, an LLM is first fine-tuned through pairs of natural language and symbolic formulation representation of ToM problems and is then instructed to generate the symbolic formulation with a one-shot in-context example. The generated symbolic formulation is then executed by the SMCDEL model checker to perform transparent and verifiable ToM reasoning and give the final result. We demonstrate that our approach, ToM-LM, shows a significant improvement over all the constructed baselines. Our study proposes a novel view about externalizing a particular component of ToM reasoning, mainly reasoning about beliefs, and suggests generalizing it to other aspects of ToM reasoning.