“…However, since they are trained using negative samples obtained from random contexts, they are also prone to the spurious pattern of content similarity. Adversarial or counterfactual data creation techniques have been proposed for applications such as evaluation (Gardner et al, 2020;Madaan et al, 2020), attacks (Ebrahimi et al, 2018;Wallace et al, 2019;Jin et al, 2020), explanations (Goodwin et al, 2020;Ross et al, 2020) or training models to be robust against spurious patterns and biases (Garg et al, 2019;Huang et al, 2020). Adversarial examples are crafted through operations such as adding noisy characters (Ebrahimi et al, 2018;Pruthi et al, 2019), paraphrasing (Iyyer et al, 2018), replacing with synonyms (Alzantot et al, 2018;Jin et al, 2020), rule based token-level transformations (Kryscinski et al, 2020), or inserting words relevant to the context (Zhang et al, 2019).…”