Think Twice: Perspective-Taking Improves Large Language Models’ Theory-of-Mind Capabilities
Alex Wilf, Sihyun Lee, Paul Pu Liang, Louis-Philippe Morency
Abstract
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 (CoT) 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.- Anthology ID:
- 2024.acl-long.451
- Volume:
- Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- August
- Year:
- 2024
- Address:
- Bangkok, Thailand
- Editors:
- Lun-Wei Ku, Andre Martins, Vivek Srikumar
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 8292–8308
- Language:
- URL:
- https://aclanthology.org/2024.acl-long.451
- DOI:
- Cite (ACL):
- Alex Wilf, Sihyun Lee, Paul Pu Liang, and Louis-Philippe Morency. 2024. Think Twice: Perspective-Taking Improves Large Language Models’ Theory-of-Mind Capabilities. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 8292–8308, Bangkok, Thailand. Association for Computational Linguistics.
- Cite (Informal):
- Think Twice: Perspective-Taking Improves Large Language Models’ Theory-of-Mind Capabilities (Wilf et al., ACL 2024)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2024.acl-long.451.pdf