Evaluation Toolkit For Robustness Testing Of Automatic Essay Scoring Systems
This addresses a critical gap in evaluating AES systems for educational testing, revealing vulnerabilities that could impact millions of test-takers, though it is incremental in providing new testing tools rather than a scoring method.
The authors tackled the lack of holistic robustness testing in Automatic Essay Scoring (AES) systems by proposing a model-agnostic adversarial evaluation scheme, finding that current models are highly overstable, with 25% irrelevant content not decreasing scores and even increasing them on average.
Automatic scoring engines have been used for scoring approximately fifteen million test-takers in just the last three years. This number is increasing further due to COVID-19 and the associated automation of education and testing. Despite such wide usage, the AI-based testing literature of these "intelligent" models is highly lacking. Most of the papers proposing new models rely only on quadratic weighted kappa (QWK) based agreement with human raters for showing model efficacy. However, this effectively ignores the highly multi-feature nature of essay scoring. Essay scoring depends on features like coherence, grammar, relevance, sufficiency and, vocabulary. To date, there has been no study testing Automated Essay Scoring: AES systems holistically on all these features. With this motivation, we propose a model agnostic adversarial evaluation scheme and associated metrics for AES systems to test their natural language understanding capabilities and overall robustness. We evaluate the current state-of-the-art AES models using the proposed scheme and report the results on five recent models. These models range from feature-engineering-based approaches to the latest deep learning algorithms. We find that AES models are highly overstable. Even heavy modifications(as much as 25%) with content unrelated to the topic of the questions do not decrease the score produced by the models. On the other hand, irrelevant content, on average, increases the scores, thus showing that the model evaluation strategy and rubrics should be reconsidered. We also ask 200 human raters to score both an original and adversarial response to seeing if humans can detect differences between the two and whether they agree with the scores assigned by auto scores.