We introduce a multi-stage prompting approach (MSP) for the generation of
multiple choice questions (MCQs), harnessing the capabilities of GPT models
such as text-davinci-003 and GPT-4, renowned for their excellence across
various NLP tasks. Our approach incorporates the innovative concept of
chain-of-thought prompting, a progressive technique in which the GPT model is
provided with a series of interconnected cues to guide the MCQ generation
process. Automated evaluations consistently demonstrate the superiority of our
proposed MSP method over the traditional single-stage prompting (SSP) baseline,
resulting in the production of high-quality distractors. Furthermore, the
one-shot MSP technique enhances automatic evaluation results, contributing to
improved distractor generation in multiple languages, including English,
German, Bengali, and Hindi. In human evaluations, questions generated using our
approach exhibit superior levels of grammaticality, answerability, and
difficulty, highlighting its efficacy in various languages.

我们引入了一种多阶段提示方法（MSP）用于生成多项选择题（MCQs），借助于文本戴文西 - 003 和 GPT-4 等 GPT 模型的能力，这些模型在各种自然语言处理任务中表现出色。我们的方法融合了连贯思维提示的创新概念，这是一种渐进式技术，通过一系列相互连接的提示引导 MCQ 生成过程。自动评估一致展示出我们提出的 MSP 方法在传统的单阶段提示（SSP）基线之上的优越性，从而生成高质量的干扰项。此外，一次性的 MSP 技术提高了自动评估结果，在包括英语、德语、孟加拉语和印地语在内的多种语言中改善了干扰项生成。在人工评估中，使用我们的方法生成的问题展现出更高水平的语法正确性、可答性和难度，突显了它在各种语言中的有效性。