作弊的自动简答题评分：关于形容词和连词的对抗性使用
Cheating Automatic Short Answer Grading: On the Adversarial Usage of Adjectives and Adverbs
摘要：
自动评分模型的价值在于在大型学生团体的教学过程中节省的时间和精力。特别是随着教育数字化程度的提高和对大规模标准化考试的兴趣，自动评分的普及程度已经上升到商业解决方案广泛可用和使用的程度。然而，对于简答格式，由于自然语言的模糊性和通用性，自动评分是具有挑战性的。虽然自动简答题评分模型开始在某些数据集上与人类表现进行比较，但它们的鲁棒性，特别是对不利操纵的数据的鲁棒性，是值得怀疑的。评分模型中可利用的漏洞可能会产生深远的后果，从欺骗学生获得不应得的学分到完全破坏自动评分-即使大多数预测都是有效的。在本文中，我们设计了一个黑盒对抗攻击适合于教育简答题评分的情况下，研究评分模型的鲁棒性。在我们的攻击中，我们将形容词和副词插入错误学生答案的自然位置，欺骗模型预测它们是正确的。我们观察到使用最先进的模型BERT和T5的预测准确性损失了10到22个百分点。虽然在我们的实验中，我们的攻击使答案对人类来说显得不那么自然，但它并没有显著增加评分者对作弊的怀疑。基于我们的实验，我们提供了建议，在实践中更安全地利用自动评分系统。
英文摘要：
Automatic grading models are valued for the time and effort saved during the instruction of large student bodies. Especially with the increasing digitization of education and interest in large-scale standardized testing, the popularity of automatic grading has risen to the point where commercial solutions are widely available and used. However, for short answer formats, automatic grading is challenging due to natural language ambiguity and versatility. While automatic short answer grading models are beginning to compare to human performance on some datasets, their robustness, especially to adversarially manipulated data, is questionable. Exploitable vulnerabilities in grading models can have far-reaching consequences ranging from cheating students receiving undeserved credit to undermining automatic grading altogether - even when most predictions are valid. In this paper, we devise a black-box adversarial attack tailored to the educational short answer grading scenario to investigate the grading models' robustness. In our attack, we insert adjectives and adverbs into natural places of incorrect student answers, fooling the model into predicting them as correct. We observed a loss of prediction accuracy between 10 and 22 percentage points using the state-of-the-art models BERT and T5. While our attack made answers appear less natural to humans in our experiments, it did not significantly increase the graders' suspicions of cheating. Based on our experiments, we provide recommendations for utilizing automatic grading systems more safely in practice.
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。
