Model Size Scaling and Performance Gaps in Zero-Shot Transfer on XTREME PAWS-X

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 scaling model size from base to large variants on the performance gap between English and multilingual intermediate-task training for zero-shot transfer on the XTREME PAWS-X dataset?

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