用故事结构引导大模型思考，提升解题能力
Can Stories Help LLMs Reason? Curating Information Space Through Narrative
- 将问题转化为叙事框架，系统组织关键信息
- 在GPQA和JEEBench上表现优于传统提示方法
- 适合需要逻辑推理与知识整合的任务
叙事被广泛认为是组织信息、促进复杂概念理解的有效工具。本文探究在大语言模型（LLMs）解决复杂问题时，融入叙事元素是否能提升效果。提出一种名为思维故事（Story of Thought, SoT）的新方法，通过在问题陈述周围构建叙事，并建立框架以识别和组织相关信息。实验表明，在物理、化学、数学和生物类问题上，使用SoT的LLMs在GPQA和JEEBench数据集上均显著优于其他提示技术。基于叙事的信息整理过程通过嵌入领域内关键信息并凸显问题空间中的因果关系，增强了对问题的理解。
原文摘要 · Abstract (English)
Narratives are widely recognized as a powerful tool for structuring information and facilitating comprehension of complex ideas in various domains such as science communication. This paper investigates whether incorporating narrative elements can assist Large Language Models (LLMs) in solving complex problems more effectively. We propose a novel approach, Story of Thought (SoT), integrating narrative structures into prompting techniques for problem-solving. This approach involves constructing narratives around problem statements and creating a framework to identify and organize relevant information. Our experiments show that using various LLMs with SoT consistently surpasses using them with other techniques on physics, chemistry, math, and biology questions in both the GPQA and JEEBench datasets. The narrative-based information curation process in SoT enhances problem comprehension by contextualizing critical in-domain information and highlighting causal relationships within the problem space.
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。