Scaling Intermediate-Task Transfer Performance on XTREME-R with Pretrained Multilingual 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 intermediate-task transfer performance on XTREME-R benchmark scale with different sizes of pretrained multilingual models (e.g., comparing 7B, 13B, and 30B parameter models) when fine-tuned on English intermediate tasks?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 9.2/10.