Impact of Intermediate-Task Training on Zero-Shot Cross-Lingual Transfer Across Model Sizes

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 impact of intermediate-task training on zero-shot cross-lingual transfer (XTREME-R) vary across model sizes (175B vs. 7B vs. 1.3B), and is the performance gain proportional to model scale, measurable via rank correlation (Spearman's rho) between model size and accuracy improvement?

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