通过探测模型隐含思维路径，提升大模型推理准确性。
ThoughtProbe: Classifier-Guided LLM Thought Space Exploration via Probing Representations
- 用分类器评估隐藏表示，动态筛选高潜力推理路径
- 在多个数学推理数据集上显著提升准确率，最高达12.3%提升
- 适合需要高可靠推理的场景，如科学计算与复杂决策
本文提出ThoughtProbe，一种新型推理阶段框架，利用大语言模型的隐藏推理特征来增强其推理能力。不同于以往通过操纵隐藏表示引导生成的方法，本工作将其作为判别信号，指导树状响应空间的探索。在每个节点扩展时，分类器充当评分与排序机制，高效分配计算资源，优先继续高分候选路径。完成树结构扩展后，从所有分支收集答案形成候选池，并提出一种分支聚合方法，通过整合各支持分支的链式思考（CoT）得分，对候选答案进行边际化处理，从而选出最优解。实验表明，该框架的全面探索不仅能覆盖有效推理路径，还能精准识别，显著提升多个算术推理基准上的表现。
原文摘要 · Abstract (English)
This paper introduces ThoughtProbe, a novel inference time framework that leverages the hidden reasoning features of Large Language Models (LLMs) to improve their reasoning performance. Unlike previous works that manipulate the hidden representations to steer LLM generation, we harness them as discriminative signals to guide the tree structured response space exploration. In each node expansion, a classifier serves as a scoring and ranking mechanism that efficiently allocates computational resources by prioritizing higher score candidates for continuation. After completing the tree expansion, we collect answers from all branches to form a candidate answer pool. We then propose a branch aggregation method that marginalizes over all supporting branches by aggregating their CoT 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.
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。