Recently, although pre-trained language models have achieved great success on multilingual NLP (Natural Language Processing) tasks, the lack of training data on many tasks in low-resource languages still limits their performance. One effective way of solving that problem is to transfer knowledge from rich-resource languages to low-resource languages. However, many previous works on cross-lingual transfer rely heavily on the parallel corpus or translation models, which are often difficult to obtain. We propose a novel approach to conduct zero-shot cross-lingual transfer with a pre-trained modelResearch goal: What is the impact of increasing the size of intermediate-task training data on XLM-R-base's zero-shot cross-lingual performance, benchmarked by F1 score stability across low-resource languages in XTREME-R?Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.5/10.