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.

翻译：心理理论（ToM）指个体推断他人心理状态的能力。尽管大型语言模型（LLMs）已展现出一定的ToM能力，但在复杂ToM推理中仍存在不足。本研究提出一种方法，利用外部符号执行器（具体为SMCDEL模型检查器）并结合微调技术，以提升LLMs的ToM推理能力。具体而言，我们首先通过ToM问题的自然语言与符号化表示配对数据对LLM进行微调，随后通过单样本上下文示例引导其生成符号化表示。生成的符号化表示由SMCDEL模型检查器执行，实现透明且可验证的ToM推理并输出最终结果。实验表明，我们提出的ToM-LM方法在所有构建基线中均展现出显著优势。本研究为将ToM推理中特定组件（主要是信念推理）外部化提供了新思路，并提出该方法可推广至ToM推理的其他方面。