Robustness of Intermediate-Task Trained mT5 Against Adversarial Examples in Zero-Shot Cross-Lingual Settings

Intermediate-task training---fine-tuning a pretrained model on an intermediate task before fine-tuning again on the target task---often improves model performance substantially on language understanding tasks in monolingual English settings. We investigate whether English intermediate-task training is still helpful on non-English target tasks. Using nine intermediate language-understanding tasks, we evaluate intermediate-task transfer in a zero-shot cross-lingual setting on the XTREME benchmark. We see large improvements from intermediate training on the BUCC and Tatoeba sentence retrieval tas

Research goal: How robust is the intermediate-task trained mT5 model against adversarial examples in a zero-shot cross-lingual setting, as measured by accuracy drop on perturbed inputs in the XTREME benchmark?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 9.3/10.