Instruction tuning has emerged as a powerful technique, significantly boosting zero-shot performance on unseen tasks. While recent work has explored cross-lingual generalization by applying instruction tuning to multilingual models, previous studies have primarily focused on English, with a limited exploration of non-English tasks. For an in-depth exploration of cross-lingual generalization in instruction tuning, we perform instruction tuning individually for two distinct language meta-datasets. Subsequently, we assess the performance on unseen tasks in a language different from the one used fResearch goal: Can combining instruction tuning with multilingual intermediate tasks improve zero-shot cross-lingual performance on HellaSwag compared to English-only intermediate-task fine-tuning, measured by accuracy?Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.5/10.