arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2304.04616cs.CLcs.AI
收藏

使用 OpenAI 大型语言模型自动生成阅读文章

Automated Reading Passage Generation with OpenAI's Large Language Model

Boston College(波士顿学院)

Ummugul Bezirhan, Matthias von Davier

AI总结:

本文利用 OpenAI 的 GPT-3 模型生成阅读文章,通过精心设计提示词和 Lexile 分数筛选,并结合人类编辑修订与人工评估,验证了 AI 生成文章在连贯性、适宜性和可读性上与原文相当。

摘要:

基于计算机的评估和个性化学习平台的广泛使用,导致对快速生产高质量题目的需求增加。自动题目生成(Automated Item Generation, AIG)是在计算机技术的帮助下使用题目模型生成新题目的过程,旨在减少在流程每个步骤中对人类学科专家依赖。AIG 在测试开发中使用已有一段时间。尽管如此,机器学习算法的引入带来了极大提高该流程效率和效果的潜力。本文提出的方法利用 OpenAI 最新的基于 transformer 的语言模型 GPT-3 来生成阅读文章。现有的阅读文章被用于精心设计的提示词中,以确保 AI 生成的文本与四年级阅读文章具有相似的内容和结构。对于每个提示词,我们生成了多篇文章,最终文章根据与原始文章的 Lexile 分数一致性进行选择。在最后一轮中,所选文章由人类编辑者进行简单修订,以确保文本没有任何语法和事实错误。所有 AI 生成的文章连同原始文章一起由人类评委根据其连贯性、对四年级学生的适宜性和可读性进行评估。

英文摘要:

The widespread usage of computer-based assessments and individualized learning platforms has resulted in an increased demand for the rapid production of high-quality items. Automated item generation (AIG), the process of using item models to generate new items with the help of computer technology, was proposed to reduce reliance on human subject experts at each step of the process. AIG has been used in test development for some time. Still, the use of machine learning algorithms has introduced the potential to improve the efficiency and effectiveness of the process greatly. The approach presented in this paper utilizes OpenAI's latest transformer-based language model, GPT-3, to generate reading passages. Existing reading passages were used in carefully engineered prompts to ensure the AI-generated text has similar content and structure to a fourth-grade reading passage. For each prompt, we generated multiple passages, the final passage was selected according to the Lexile score agreement with the original passage. In the final round, the selected passage went through a simple revision by a human editor to ensure the text was free of any grammatical and factual errors. All AI-generated passages, along with original passages were evaluated by human judges according to their coherence, appropriateness to fourth graders, and readability.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑