SBI-RAG：通过基于模式的教学和检索增强生成提升学生数学应用问题解决能力

SBI-RAG: Enhancing Math Word Problem Solving for Students through Schema-Based Instruction and Retrieval-Augmented Generation

October 17, 2024

作者: Prakhar Dixit, Tim Oates

cs.AI

摘要

许多学生在数学文字问题（MWPs）上感到困难，常常难以识别关键信息并选择适当的数学运算。基于模式的教学（SBI）是一种基于证据的策略，可以帮助学生根据问题结构对问题进行分类，提高解决问题的准确性。在此基础上，我们提出了一种基于模式的教学检索增强生成（SBI-RAG）框架，其中整合了大型语言模型（LLM）。我们的方法强调通过利用模式引导解决方案生成的逐步推理。我们在GSM8K数据集上评估其性能，将其与GPT-4和GPT-3.5 Turbo进行比较，并引入“推理得分”指标来评估解决方案的质量。我们的研究结果表明，SBI-RAG提升了推理清晰度和问题解决准确性，可能为学生提供教育上的益处。

English

Many students struggle with math word problems (MWPs), often finding it difficult to identify key information and select the appropriate mathematical operations.Schema-based instruction (SBI) is an evidence-based strategy that helps students categorize problems based on their structure, improving problem-solving accuracy. Building on this, we propose a Schema-Based Instruction Retrieval-Augmented Generation (SBI-RAG) framework that incorporates a large language model (LLM).Our approach emphasizes step-by-step reasoning by leveraging schemas to guide solution generation. We evaluate its performance on the GSM8K dataset, comparing it with GPT-4 and GPT-3.5 Turbo, and introduce a "reasoning score" metric to assess solution quality. Our findings suggest that SBI-RAG enhances reasoning clarity and problem-solving accuracy, potentially providing educational benefits for students