Synthetic Typo Augmentation for Adversarial Robustness in Dense Retrievers via Zero-Shot Adversarial NLI Evaluation

Dense retrieval has become the new paradigm in passage retrieval. Despite its effectiveness on typo-free queries, it is not robust when dealing with queries that contain typos. Current works on improving the typo-robustness of dense retrievers combine (i) data augmentation to obtain the typoed queries during training time with (ii) additional robustifying subtasks that aim to align the original, typo-free queries with their typoed variants. Even though multiple typoed variants are available as positive samples per query, some methods assume a single positive sample and a set of negative ones p

Research goal: To what extent does synthetic typo augmentation during contrastive learning improve robustness to adversarial perturbations in dense retrievers, as measured by zero-shot accuracy on the Adversarial NLI benchmark?

Autonomous synthesis report generated by SOVEREIGN Research Kernel. Tribunal consensus score: 8.7/10.