Large Language Models as Theory of Mind Aware Generative Agents with Counterfactual Reflection

TL;DR

This paper introduces ToM-agent, a novel framework enabling large language models to simulate theory of mind in open-domain conversations, improving understanding of mental states and enhancing social behavior modeling.

Contribution

The study presents a new paradigm for LLM-based agents to dynamically infer and reflect on mental states, incorporating counterfactual reflection to improve social interaction capabilities.

Findings

ToM-agent effectively models beliefs, desires, and intentions in conversations.

Counterfactual reflection enhances the accuracy of mental state inference.

The approach improves performance in first- and second-order theory of mind tasks.

Abstract

Recent studies have increasingly demonstrated that large language models (LLMs) possess significant theory of mind (ToM) capabilities, showing the potential for simulating the tracking of mental states in generative agents. In this study, we propose a novel paradigm called ToM-agent, designed to empower LLMs-based generative agents to simulate ToM in open-domain conversational interactions. ToM-agent disentangles the confidence from mental states, facilitating the emulation of an agent's perception of its counterpart's mental states, such as beliefs, desires, and intentions (BDIs). Using past conversation history and verbal reflections, ToM-Agent can dynamically adjust counterparts' inferred BDIs, along with related confidence levels. We further put forth a counterfactual intervention method that reflects on the gap between the predicted responses of counterparts and their real utterances, thereby enhancing the efficiency of reflection. Leveraging empathetic and persuasion dialogue datasets, we assess the advantages of implementing the ToM-agent with downstream tasks, as well as its performance in both the first-order and the \textit{second-order} ToM. Our findings indicate that the ToM-agent can grasp the underlying reasons for their counterpart's behaviors beyond mere semantic-emotional supporting or decision-making based on common sense, providing new insights for studying large-scale LLMs-based simulation of human social behaviors.