用微调大模型自动生成教学问答，提升出题效率。
Automatic Question & Answer Generation Using Generative Large Language Model (LLM)
- 用提示工程定制题目风格，适配不同需求。
- 基于RACE数据集微调Meta-Llama 2-7B模型，支持自动生成。
- 适合教师、教育工作者快速构建文本测评题库。
在教育领域，学生评估与知识传授同样重要。为进行评估，学生通常需完成基于文本的学业考核。教师需设计多样且公平的试题以检验学生对特定主题的掌握程度，但手动从多份讲义中筛选或生成题目极为耗时。本文旨在通过使用微调的生成式大语言模型实现自动问答生成（AQAG），以简化该流程。为匹配教师偏好的题型（选择题、概念题或事实题），采用提示工程（PE）进行定制。研究聚焦于英语语境下的无监督学习方法，利用RACE数据集对基础模型Meta-Llama 2-7B进行微调，构建可高效生成问题与答案的定制化模型，为教育者及文本评估参与者提供可靠工具，显著节省时间与资源，优化评估流程。
原文摘要 · Abstract (English)
In the realm of education, student evaluation holds equal significance to imparting knowledge. To be evaluated, students usually need to go through text-based academic assessment methods. Instructors need to make a diverse set of questions that need to be fair for all students to prove their adequacy over a particular topic. This can prove to be quite challenging as they may need to manually go through several different lecture materials. Our objective is to make this whole process much easier by implementing Automatic Question Answer Generation(AQAG), using a fine-tuned generative LLM. For tailoring the instructor's preferred question style (MCQ, conceptual, or factual questions), Prompt Engineering (PE) is being utilized. In this research, we propose to leverage unsupervised learning methods in NLP, primarily focusing on the English language. This approach empowers the base Meta-Llama 2-7B model to integrate the RACE dataset as training data for the fine-tuning process. Creating a customized model that will offer efficient solutions for educators, instructors, and individuals engaged in text-based evaluations. A reliable and efficient tool for generating questions and answers can free up valuable time and resources, thus streamlining their evaluation processes.
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。