用大模型自动生成符合年级和题型的数学应用题，无需额外输入。
Elementary Math Word Problem Generation using Large Language Models
- 仅需指定数量、年级和题型，即可生成数学应用题。
- 生成题目语法正确，质量高，但对题型匹配仍有不足。
- 结合人类反馈与多种提示策略，提升题目多样性和实用性。
数学常被学生视为复杂学科，导致考试失败率高。为提升解题能力，提供练习题至关重要。手动编写数学应用题（MWP）耗时且需符合语言规范。早期基于预训练语言模型的方法需用户提供题干或方程等额外信息。本文提出基于大语言模型（LLM）的自动生成系统MathWiz，仅需输入所需题目数量、年级及题型（如加法、减法），即可生成自然语言问题。我们对比了多种LLM、提示策略，并引入提升多样性及结合人类反馈的技术。人工与自动评估均显示生成题目质量高，几乎无拼写和语法错误。然而，模型仍难以精准满足指定年级和题型要求。
原文摘要 · Abstract (English)
Mathematics is often perceived as a complex subject by students, leading to high failure rates in exams. To improve Mathematics skills, it is important to provide sample questions for students to practice problem-solving. Manually creating Math Word Problems (MWPs) is time consuming for tutors, because they have to type in natural language while adhering to grammar and spelling rules of the language. Early techniques that use pre-trained Language Models for MWP generation either require a tutor to provide the initial portion of the MWP, and/or additional information such as an equation. In this paper, we present an MWP generation system (MathWiz) based on Large Language Models (LLMs) that overcomes the need for additional input - the only input to our system is the number of MWPs needed, the grade and the type of question (e.g.~addition, subtraction). Unlike the existing LLM-based solutions for MWP generation, we carried out an extensive set of experiments involving different LLMs, prompting strategies, techniques to improve the diversity of MWPs, as well as techniques that employ human feedback to improve LLM performance. Human and automated evaluations confirmed that the generated MWPs are high in quality, with minimal spelling and grammar issues. However, LLMs still struggle to generate questions that adhere to the specified grade and question type requirements.
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。