Scaling Zero-Shot Cross-Lingual Transfer Performance with Model Size and Intermediate Task Training

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 performance of zero-shot cross-lingual transfer scale with model size (e.g., 7B vs. 13B vs. 30B parameters) when trained on varying numbers of English intermediate tasks, evaluated using XTREME benchmark metrics like XCOPA accuracy and TYDI-QA EM/F1?

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