Table as Thought: Exploring Structured Thoughts in LLM Reasoning
This work addresses the need for more structured reasoning in LLMs, offering a novel approach that could advance AI cognition, though it appears incremental in refining existing thought representation methods.
The paper tackles the problem of underexplored structure in individual thought steps in LLM reasoning by proposing Table as Thought, a framework that organizes reasoning in a tabular schema, and shows it excels in planning tasks and enhances mathematical reasoning compared to unstructured baselines.
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.