让大模型先提炼关键信息，再推理，准确率提升7.1%
Understanding Before Reasoning: Enhancing Chain-of-Thought with Iterative Summarization Pre-Prompting
- 先提取实体与描述，迭代合并低可信度对，生成唯一关键信息对
- 在多个数据集上比现有方法准确率提升7.1%，最高达24.3%绝对提升
- 适合信息隐含的复杂推理任务，可无缝接入各类推理框架
链式思维（CoT）提示是增强大语言模型复杂推理能力的主要范式，引导模型分步推理而非直接输出答案。然而当推理所需的关键信息隐含或缺失时，CoT效果受限，因其过于关注推理步骤顺序，而忽视早期关键信息提取。为此，我们提出一种预提示方法——迭代摘要预提示（ISP^2），在关键信息未明确时提升模型推理能力。首先，从输入中提取实体及其对应描述，形成潜在的关键信息对；接着，通过可靠性评分评估这些对，将两个最低评分的对合并为新实体描述；该过程重复进行，直至生成唯一的关键信息对；最后，将该对与原始问题一同输入大模型以生成答案。大量实验表明，相比现有方法，准确率平均提升7.1%。不同于传统提示策略，ISP^2采用归纳式预提示机制，具备灵活集成到多种推理框架的优势。代码已开源：https://github.com/zdhgreat/ISP-2。
原文摘要 · Abstract (English)
Chain-of-Thought (CoT) Prompting is a dominant paradigm in Large Language Models (LLMs) to enhance complex reasoning. It guides LLMs to present multi-step reasoning, rather than generating the final answer directly. However, CoT encounters difficulties when key information required for reasoning is implicit or missing. This occurs because CoT emphasizes the sequence of reasoning steps while overlooking the early extraction of essential information. We propose a pre-prompting method called Iterative Summarization Pre-Prompting (ISP^2) to refine LLM reasoning when key information is not explicitly provided. First, entities and their corresponding descriptions are extracted to form potential key information pairs. Next, we use a reliability rating to assess these pairs, then merge the two lowest-ranked pairs into a new entity description. This process is repeated until a unique key information pair is obtained. Finally, that pair, along with the original question, is fed into LLMs to produce the answer. Extensive experiments demonstrate a 7.1% improvement compared to existing methods. Unlike traditional prompting, ISP^2 adopts an inductive approach with pre-prompting, offering flexible integration into diverse reasoning frameworks. The code is available at https://github.com/zdhgreat/ISP-2.
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。