ThoughtProbe：利用LLM内在推理的分类器引导思维空间探索
ThoughtProbe: Classifier-Guided Thought Space Exploration Leveraging LLM Intrinsic Reasoning
AI总结：
本文提出ThoughtProbe框架，发现线性分类器可检测LLM内在推理能力，并通过分类器引导的树搜索与分支聚合选择方法，在多个算术推理基准上取得显著提升。
摘要：
预训练大语言模型（LLMs）已被证明具备内在推理能力，这种能力在扩展响应空间时可以自然涌现。然而，这些内在能力背后的神经表征机制及其最优利用方法仍未得到充分理解。在本工作中，我们做出了一个关键发现：一个简单的线性分类器能够有效检测LLMs激活空间中的内在推理能力，尤其是在特定的表征类型和网络层中。基于这一发现，我们提出了一种分类器引导的搜索框架，该框架对树结构响应空间进行策略性探索。在每次节点扩展中，分类器充当评分和排序机制，通过识别并优先选择更具思考深度的推理方向进行延续，从而高效分配计算资源。完成树扩展后，我们从所有分支收集答案以形成候选答案池。我们提出了一种分支聚合选择方法，通过聚合所有支持分支的思考深度分数对其进行边缘化处理，从而从答案池中识别出最优答案。实验结果表明，我们框架的全面探索不仅覆盖了有效的推理链，而且能够有效识别它们，在多个算术推理基准上取得了显著提升。
英文摘要：
Pre-trained large language models (LLMs) have been demonstrated to possess intrinsic reasoning capabilities that can emerge naturally when expanding the response space. However, the neural representation mechanisms underlying these intrinsic capabilities and approaches for their optimal utilization remain inadequately understood. In this work, we make the key discovery that a simple linear classifier can effectively detect intrinsic reasoning capabilities in LLMs' activation space, particularly within specific representation types and network layers. Based on this finding, we propose a classifier-guided search framework that strategically explore a tree-structured response space. In each node expansion, the classifier serves as a scoring and ranking mechanism that efficiently allocates computational resources by identifying and prioritizing more thoughtful reasoning directions for continuation. After completing the tree expansion, we collect answers from all branches to form a candidate answer pool. We propose a branch-aggregation selection method that marginalizes over all supporting branches by aggregating their thoughtfulness scores, thereby identifying the optimal answer from the pool. Experimental results show that our framework's comprehensive exploration not only covers valid reasoning chains but also effectively identifies them, achieving significant improvements across multiple arithmetic reasoning benchmarks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
