分析大模型推理链结构，找出影响答案正确性的关键模式。
What Makes a Good Reasoning Chain? Uncovering Structural Patterns in Long Chain-of-Thought Reasoning
- 将推理链转为树结构，用图神经网络挖掘内部模式。
- 发现探索、回溯和验证是预测正确率的关键结构特征。
- 可诊断错误原因并提升多候选生成的效率，适合模型优化者使用。
大语言模型的长链推理（LCoT）虽在复杂任务中表现优异，但其内部结构如何影响最终答案的正确性仍不明确。本文提出LCoT2Tree框架，将序列式推理链自动转换为层次化树结构，实现对推理过程的深度结构分析。利用图神经网络，我们发现包括探索、回溯和验证在内的结构模式，能更准确预测多种任务与模型下的性能表现。通过可解释性技术，进一步识别出过度分支等导致失败的关键思维模式。该框架不仅提供诊断洞察，还可提升Best-of-N解码的有效性。结果表明，推理链的内部结构至关重要，LCoT2Tree为诊断、解释和改进大模型推理提供了有力工具。
原文摘要 · Abstract (English)
Recent advances in reasoning with large language models (LLMs) have popularized Long Chain-of-Thought (LCoT), a strategy that encourages deliberate and step-by-step reasoning before producing a final answer. While LCoTs have enabled expert-level performance in complex tasks, how the internal structures of their reasoning chains drive, or even predict, the correctness of final answers remains a critical yet underexplored question. In this work, we present LCoT2Tree, an automated framework that converts sequential LCoTs into hierarchical tree structures and thus enables deeper structural analysis of LLM reasoning. Using graph neural networks (GNNs), we reveal that structural patterns extracted by LCoT2Tree, including exploration, backtracking, and verification, serve as stronger predictors of final performance across a wide range of tasks and models. Leveraging an explainability technique, we further identify critical thought patterns such as over-branching that account for failures. Beyond diagnostic insights, the structural patterns by LCoT2Tree support practical applications, including improving Best-of-N decoding effectiveness. Overall, our results underscore the critical role of internal structures of reasoning chains, positioning LCoT2Tree as a powerful tool for diagnosing, interpreting, and improving reasoning in LLMs.
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。