paper-with-me

Papers

Mind's Eye of LLMs: Visualization-of-Thought Elicits Spatial Reasoning in Large Language Models

2024-04-04 · Wenshan Wu, Shaoguang Mao, Yadong Zhang, Yan Xia, Li Dong, Lei Cui, Furu Wei

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 the Mind's Eye, enabling the imagination of the unseen world. Inspired by this cognitive capacity, we propose Visualization-of-Thought (VoT) prompting. VoT aims to elicit spatial reasoning of LLMs by visualizing their reasoning traces, thereby guiding subsequent reasoning steps. We employed VoT for multi-hop spatial reasoning tasks, including natural language navigation, visual navigation, and visual tiling in 2D grid worlds. Experimental results demonstrated that VoT significantly enhances the spatial reasoning abilities of LLMs. Notably, VoT outperformed existing multimodal large language models (MLLMs) in these tasks. While VoT works surprisingly well on LLMs, the ability to generate mental images to facilitate spatial reasoning resembles the mind's eye process, suggesting its potential viability in MLLMs. Please find the dataset and codes at https://microsoft.github.io/visualization-of-thought

📄 PDF Abstract BibTeX arXiv:2404.03622

Code (1)

sitloboi2012/Visualization-of-Thought

Tasks

Spatial ReasoningVisual Navigation

Similar Papers 제목 키워드 기반

MindMap: Knowledge Graph Prompting Sparks Graph of Thoughts in Large Language Models

2023-08-17 · Yilin Wen, Zifeng Wang, Jimeng Sun

Large language models (LLMs) have achieved remarkable performance in natural language understanding and generation tasks. However, they often suffer from limitations such as difficulty in incorporating new knowledge, gen…

Decision MakingHallucinationHallucination EvaluationKnowledge Graphs+4

Imagine while Reasoning in Space: Multimodal Visualization-of-Thought

2025-01-13 · Chengzu Li, Wenshan Wu, Huanyu Zhang, Yan Xia 외

Chain-of-Thought (CoT) prompting has proven highly effective for enhancing complex reasoning in Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs). Yet, it struggles in complex spatial reasoning ta…

Spatial Reasoning

EgoMind: Activating Spatial Cognition through Linguistic Reasoning in MLLMs

2026-04-01 · Zhenghao Chen, Huiqun Wang, Di Huang arxiv

Multimodal large language models (MLLMs) are increasingly being applied to spatial cognition tasks, where they are expected to understand and interact with complex environments. Most existing works improve spatial reason…

Spatial Reasoning

EnigmaToM: Improve LLMs' Theory-of-Mind Reasoning Capabilities with Neural Knowledge Base of Entity States

2025-03-05 · Hainiu Xu, Siya Qi, Jiazheng Li, Yuxiang Zhou 외

Theory-of-Mind (ToM), the ability to infer others' perceptions and mental states, is fundamental to human interaction but remains a challenging task for Large Language Models (LLMs). While existing ToM reasoning methods …

Inductive Bias

SpatialViz-Bench: A Cognitively-Grounded Benchmark for Diagnosing Spatial Visualization in MLLMs

2025-07-10 · Siting Wang, Minnan Pei, Luoyang Sun, Cheng Deng 외 arxiv

Humans can imagine and manipulate visual images mentally, a capability known as spatial visualization. While many multi-modal benchmarks assess reasoning on visible visual information, the ability to infer unseen relatio…