Visualization-of-Thought Elicits Spatial Reasoning in Large Language Models

arXiv:2404.03622v1 Announce Type: new
Abstract: Large language models (LLMs) have exhibited impressive performance in language comprehension and various reasoning tasks. However, their abilities in spatial reasoning, a crucial aspect of human cognition, remain relatively unexplored. Human possess a remarkable ability to create mental images of unseen objects and actions through a process known as \textbf{the Mind's Eye}, enabling the imagination of the unseen world. Inspired by this cognitive capacity, we propose Visualization-of-Thought (\textbf{VoT}) prompting. VoT aims to elicit spatial reasoning …

abstract arxiv cognition cs.cl however human images language language models large language large language models llms objects performance process reasoning spatial tasks thought through type visualization