reference
Sneheel Sarangi, Maha Elgarf, and Hanan Salam introduced 'Decompose-ToM', a method for enhancing theory of mind reasoning in large language models through simulation and task decomposition, in a 2025 paper presented at the 31st International Conference on Computational Linguistics.
Authors
Sources
- A Survey of Incorporating Psychological Theories in LLMs - arXiv arxiv.org via serper