arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2406.17859physics.ed-ph
收藏

使用人工智能辅助手写热力学考试评分:一项探索性研究

Grading Assistance for a Handwritten Thermodynamics Exam using Artificial Intelligence: An Exploratory Study

Gerd Kortemeyer, Julian Nöhl, Daria Onishchuk

AI总结:

本研究以高风险热力学考试为样本,探讨了四种AI辅助手写解答评分工作流的可行性,发现手写识别、评分粒度与图形评分是主要挑战,不及格考试仍需人工干预,并提出了改进建议。

摘要:

以一场高风险热力学考试为样本(252名学生,四道多部分问题),我们研究了四种AI辅助手写学生解答评分工作流的可行性。发现最大挑战在于将手写答案转换为机器可读格式。评分标准的粒度也影响评分表现:对整个问题采用细粒度评分标准常导致记录错误和评分失败,而分部分评分更可靠但易遗漏细微差别。我们还发现,由于难以区分关键细节与无关信息,评分手绘图形(如过程图)不如数学推导可靠。尽管系统在识别符合通过标准的考试时很精确,但不及格的考试仍需人工评分。最后,我们提出了克服部分已遇挑战的建议。

英文摘要:

Using a high-stakes thermodynamics exam as sample (252~students, four multipart problems), we investigate the viability of four workflows for AI-assisted grading of handwritten student solutions. We find that the greatest challenge lies in converting handwritten answers into a machine-readable format. The granularity of grading criteria also influences grading performance: employing a fine-grained rubric for entire problems often leads to bookkeeping errors and grading failures, while grading problems in parts is more reliable but tends to miss nuances. We also found that grading hand-drawn graphics, such as process diagrams, is less reliable than mathematical derivations due to the difficulty in differentiating essential details from extraneous information. Although the system is precise in identifying exams that meet passing criteria, exams with failing grades still require human grading. We conclude with recommendations to overcome some of the encountered challenges.

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。

↑