arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2306.16639cs.HCcs.AIcs.CY
收藏

评估 ChatGPT 在数字学习游戏中的小数技能和反馈生成

Evaluating ChatGPT's Decimal Skills and Feedback Generation in a Digital Learning Game

Carnegie Mellon University(卡内基梅隆大学);University of Michigan(密歇根大学)

Huy A. Nguyen, Hayden Stec, Xinying Hou, Sarah Di, Bruce M. McLaren

AI总结:

本研究调查了 ChatGPT 在学习游戏 Decimal Point 中解决小数练习、评估学生答案正确性及生成反馈的能力,发现其擅长概念性问题但在小数位值和数轴问题上表现不佳,且能准确评估 75% 的答案并生成类似人类教师的高质量反馈。

摘要:

虽然开放式自我解释在多项研究中被证明能促进稳健学习,但由于学生输入的无限制性,它们对技术增强学习中的自动评分和反馈提出了重大挑战。我们的工作调查了大型语言模型的最新进展,特别是 ChatGPT,能否解决这一问题。使用来自先前一项关于学习游戏 Decimal Point 研究的小数练习和学生数据,包含超过 5,000 条开放式自我解释回答,我们调查了 ChatGPT 在以下方面的能力:(1) 解决游戏内练习,(2) 判断学生答案的正确性,以及 (3) 为错误答案提供有意义的反馈。我们的结果显示,ChatGPT 能很好地回答概念性问题,但在小数位值和数轴问题上存在困难。此外,它能准确评估 75% 的学生答案的正确性,并生成了类似于人类教师的高质量反馈。我们最后讨论了 ChatGPT 的优势和劣势,并提出了几个扩展其在数字教学中用例的方向。

英文摘要:

While open-ended self-explanations have been shown to promote robust learning in multiple studies, they pose significant challenges to automated grading and feedback in technology-enhanced learning, due to the unconstrained nature of the students' input. Our work investigates whether recent advances in Large Language Models, and in particular ChatGPT, can address this issue. Using decimal exercises and student data from a prior study of the learning game Decimal Point, with more than 5,000 open-ended self-explanation responses, we investigate ChatGPT's capability in (1) solving the in-game exercises, (2) determining the correctness of students' answers, and (3) providing meaningful feedback to incorrect answers. Our results showed that ChatGPT can respond well to conceptual questions, but struggled with decimal place values and number line problems. In addition, it was able to accurately assess the correctness of 75% of the students' answers and generated generally high-quality feedback, similar to human instructors. We conclude with a discussion of ChatGPT's strengths and weaknesses and suggest several venues for extending its use cases in digital teaching and learning.

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。

↑