先思而后言：一种主动式测试时扩展方法
Thinking Before You Speak: A Proactive Test-time Scaling Approach
AI总结：
针对LLMs在复杂推理中缺乏人类式内在思考的问题，本文提出TBYS框架，通过在推理步骤间主动生成“洞察”来引导推理，并设计了自动构建示例的流程，在数学数据集上验证了有效性。
摘要：
大型语言模型（LLMs）在数学等复杂推理任务中常常表现不佳，我们将此归因于人类推理模式与LLMs训练数据中所呈现模式之间的差异。在处理复杂问题时，人类倾向于在表达解决方案之前仔细思考。然而，他们通常不会明确表达自己的内在思考，包括其意图和所选择的方法论。因此，在从人类来源收集的训练数据中，可能缺少对于衔接推理步骤至关重要的关键见解。为了弥合这一差距，我们提出在连续的推理步骤之间插入“洞察（insight）”，用于审视当前状态并启动下一步推理。与以往依赖单一静态提示或静态提示工作流来促进推理的提示策略不同，“洞察”是主动生成的，用以引导推理过程。我们将这一想法实现为一个名为“先思而后言（Thinking Before You Speak，TBYS）”的推理框架，并设计了一套自动收集和过滤上下文示例的流程，用于生成“洞察”，从而减轻人工标注负担并降低微调开销。在具有挑战性的数学数据集上的实验验证了TBYS的有效性。项目网站：https://gitee.com/jswrt/TBYS
英文摘要：
Large Language Models (LLMs) often exhibit deficiencies with complex reasoning tasks, such as maths, which we attribute to the discrepancy between human reasoning patterns and those presented in the LLMs' training data. When dealing with complex problems, humans tend to think carefully before expressing solutions. However, they often do not articulate their inner thoughts, including their intentions and chosen methodologies. Consequently, critical insights essential for bridging reasoning steps may be absent in training data collected from human sources. To bridge this gap, we proposes inserting \emph{insight}s between consecutive reasoning steps, which review the status and initiate the next reasoning steps. Unlike prior prompting strategies that rely on a single or a workflow of static prompts to facilitate reasoning, \emph{insight}s are \emph{proactively} generated to guide reasoning processes. We implement our idea as a reasoning framework, named \emph{Thinking Before You Speak} (TBYS), and design a pipeline for automatically collecting and filtering in-context examples for the generation of \emph{insight}s, which alleviates human labeling efforts and fine-tuning overheads. Experiments on challenging mathematical datasets verify the effectiveness of TBYS. Project website: https://gitee.com/jswrt/TBYS
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。
