用相似解题结构的题目作类比，提升大模型解数学应用题能力
Learning by Analogy: Enhancing Few-Shot Prompting for Math Word Problem Solving with Computational Graph-Based Retrieval
- 通过计算图检索相似题目作为提示示例
- 在6个数据集上平均准确率提升6.7个百分点
- 适合需要复杂推理的数学问题求解场景
大语言模型在复杂推理任务如数学应用题上表现不佳。本文提出利用结构相似的问题作为类比，通过检索具有相似计算图的题目作为提示中的示例，为生成模型提供正确的推理路径。在六个数学应用题数据集上的实验表明，该方法相比基线模型平均绝对提升6.7个百分点，验证了其在增强大模型推理能力方面的有效性。
原文摘要 · Abstract (English)
Large language models (LLMs) are known to struggle with complicated reasoning tasks such as math word problems (MWPs). In this paper, we present how analogy from similarly structured questions can improve LLMs' problem-solving capabilities for MWPs. Specifically, we rely on the retrieval of problems with similar computational graphs to the given question to serve as exemplars in the prompt, providing the correct reasoning path for the generation model to refer to. Empirical results across six math word problem datasets demonstrate the effectiveness of our proposed method, which achieves a significant improvement of up to 6.7 percent on average in absolute value, compared to baseline methods. These results highlight our method's potential in addressing the reasoning challenges in current LLMs.
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。