Think Twice: Perspective-Taking Improves Large Language Models' Theory-of-Mind Capabilities
This addresses the problem of enhancing LLMs' ability to understand mental states for applications in human-like interactions, representing a novel but incremental advancement in prompting techniques.
The paper tackled the challenge of improving Large Language Models' Theory-of-Mind capabilities by introducing SimToM, a two-stage prompting framework inspired by Simulation Theory, which achieved substantial improvement over existing methods on ToM benchmarks without additional training.
Human interactions are deeply rooted in the interplay of thoughts, beliefs, and desires made possible by Theory of Mind (ToM): our cognitive ability to understand the mental states of ourselves and others. Although ToM may come naturally to us, emulating it presents a challenge to even the most advanced Large Language Models (LLMs). Recent improvements to LLMs' reasoning capabilities from simple yet effective prompting techniques such as Chain-of-Thought have seen limited applicability to ToM. In this paper, we turn to the prominent cognitive science theory "Simulation Theory" to bridge this gap. We introduce SimToM, a novel two-stage prompting framework inspired by Simulation Theory's notion of perspective-taking. To implement this idea on current ToM benchmarks, SimToM first filters context based on what the character in question knows before answering a question about their mental state. Our approach, which requires no additional training and minimal prompt-tuning, shows substantial improvement over existing methods, and our analysis reveals the importance of perspective-taking to Theory-of-Mind capabilities. Our findings suggest perspective-taking as a promising direction for future research into improving LLMs' ToM capabilities.