Intermediate-Task Training Effects on Zero-Shot XTREME-R Performance Across LLaMA Scales

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: Does intermediate-task training on non-English tasks improve zero-shot performance on the XTREME-R benchmark when scaling from LLaMA-7B to LLaMA-70B, and how does this compare to English intermediate-task training?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 9.0/10.