Table as Thought: Exploring Structured Thoughts in LLM Reasoning

TL;DR

This paper introduces 'Table as Thought', a novel framework that structures LLM reasoning within a tabular schema to improve reasoning accuracy and planning, inspired by cognitive neuroscience.

Contribution

It proposes a new method that organizes reasoning steps in a table, enhancing LLM performance in complex tasks like planning and mathematical reasoning.

Findings

Outperforms unstructured reasoning baselines in planning tasks

Shows improved mathematical reasoning capabilities

Demonstrates the effectiveness of structured thought in LLMs

Abstract

Large language models' reasoning abilities benefit from methods that organize their thought processes, such as chain-of-thought prompting, which employs a sequential structure to guide the reasoning process step-by-step. However, existing approaches focus primarily on organizing the sequence of thoughts, leaving structure in individual thought steps underexplored. To address this gap, we propose Table as Thought, a framework inspired by cognitive neuroscience theories on human thought. Table as Thought organizes reasoning within a tabular schema, where rows represent sequential thought steps and columns capture critical constraints and contextual information to enhance reasoning. The reasoning process iteratively populates the table until self-verification ensures completeness and correctness. Our experiments show that Table as Thought excels in planning tasks and demonstrates a strong potential for enhancing LLM performance in mathematical reasoning compared to unstructured thought baselines. This work provides a novel exploration of refining thought representation within LLMs, paving the way for advancements in reasoning and AI cognition.