**Cross-lingual Transfer Performance with Multilingual Intermediate Tasks in 1B--10B Parameter Models**

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: What is the impact of combining multiple non-English intermediate tasks from diverse languages on zero-shot cross-lingual transfer performance in the XTREME benchmark for models between 1B and 10B parameters, compared to using only English intermediate tasks?

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