Intermediate-Task Fine-Tuning Effects on Zero-Shot Cross-Lingual Task Efficiency in 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: Does intermediate-task fine-tuning on English improve inference efficiency (e.g., latency, throughput) for zero-shot cross-lingual tasks on XTREME-R compared to direct fine-tuning, and how does this vary across task types (e.g., classification vs. generation)?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.5/10.