Intermediate-Task Difficulty and Robustness in Zero-Shot Cross-Lingual Transfer on XTREME-R

Abstract

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 does the selection of English intermediate-task difficulty influence the robustness of zero-shot cross-lingual transfer on XTREME-R when evaluated under adversarial perturbations (e.g., typos, paraphrasing) in target languages, measured by accuracy degradation rates? Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 9.3/10.