校准生成式AI以生成真实论文用于数据增强
Calibrating Generative AI to Produce Realistic Essays for Data Augmentation
AI总结：
本研究通过比较三种提示方法，发现预测下文和25个示例策略在生成真实论文用于数据增强方面效果最佳。
摘要：
数据增强可以缓解机器学习自动评分引擎在构建设想响应项目中训练数据有限的问题。本研究旨在确定三种大型语言模型提示方法生成的论文在保持原论文写作质量并产生真实文本以增强ASE训练数据集方面的效果。我们创建了学生论文的模拟版本，人类评分者对它们进行了评分并评估了生成文本的真实性。研究结果表明，预测下文的提示策略在人类评分者对模拟论文评分的一致性方面最高，预测下文和句子策略在模拟论文中最好地保持了评分的原始质量，而预测下文和25个示例策略生成的文本在人类评分者判断下最真实。
英文摘要：
Data augmentation can mitigate limited training data in machine-learning automated scoring engines for constructed response items. This study seeks to determine how well three approaches to large language model prompting produce essays that preserve the writing quality of the original essays and produce realistic text for augmenting ASE training datasets. We created simulated versions of student essays, and human raters assigned scores to them and rated the realism of the generated text. The results of the study indicate that the predict next prompting strategy produces the highest level of agreement between human raters regarding simulated essay scores, predict next and sentence strategies best preserve the rated quality of the original essay in the simulated essays, and predict next and 25 examples strategies produce the most realistic text as judged by human raters.
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。
