Scaling Laws for English Intermediate-Task Transfer to Typologically Distant Languages in the XTREME Benchmark

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 model size (1B–13B parameters) on the generalization of English intermediate-task training benefits to non-English XTREME tasks, and does this scaling behavior differ for typologically distant languages?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.7/10.