Zero-shot cross-lingual transfer performance of multilingual vs. English-trained 7B-70B models on XTREME-R

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 zero-shot cross-lingual transfer performance of 7B, 13B, and 70B models trained on English intermediate tasks compare to models trained on mixed English and multilingual intermediate tasks, as measured by accuracy on the XTREME-R benchmark?

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