Cheating Automatic Short Answer Grading: On the Adversarial Usage of Adjectives and Adverbs

1 code implementation • 20 Jan 2022 • Anna Filighera, Sebastian Ochs, Tim Steuer, Thomas Tregel

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.

Adversarial Attack valid