Pre-trained multilingual language encoders, such as multilingual BERT and XLM-R, show great potential for zero-shot cross-lingual transfer. However, these multilingual encoders do not precisely align words and phrases across languages. Especially, learning alignments in the multilingual embedding space usually requires sentence-level or word-level parallel corpora, which are expensive to be obtained for low-resource languages. An alternative is to make the multilingual encoders more robust; when fine-tuning the encoder using downstream task, we train the encoder to tolerate noise in the contexResearch goal: How does the choice of intermediate task difficulty (easy vs. hard) affect the robustness of zero-shot cross-lingual transfer performance when evaluated on adversarial or low-resource languages in the XTREME benchmark?Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.5/10.