用表格结构组织大模型推理，提升思维清晰度与准确性。
Table as Thought: Exploring Structured Thoughts in LLM Reasoning
- 将推理过程构建成表格，行代表步骤，列包含约束和上下文信息。
- 在规划和数学推理任务中表现优于无结构思维基线。
- 适合需要严谨逻辑推演的场景，如AI认知研究与复杂决策系统。
大型语言模型的推理能力依赖于组织化思考方法，例如链式思维提示，通过序列结构逐步引导推理过程。然而，现有方法主要关注思维步骤的顺序组织，忽视了单个思维步骤内部的结构设计。为弥补这一空白，我们提出「表作为思维」（Table as Thought）框架，灵感来自人类认知神经科学理论。该框架以表格形式组织推理：行表示顺序思维步骤，列表示关键约束与上下文信息，以增强推理效果。推理过程迭代填充表格，直至自验证机制确保完整性和正确性。实验表明，该方法在规划任务中表现优异，并显著优于无结构思维基线，在数学推理方面展现出强大潜力。本工作为改进大模型内部思维表征提供了新视角，推动推理能力与人工智能认知的发展。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。