Performance of FLAN-T5 Models Fine-Tuned on Intermediate-Task Examples in Zero-Shot Cross-Lingual NLI 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 performance of FLAN-T5 models fine-tuned on 100K English intermediate-task examples compare to models fine-tuned on 1M examples in zero-shot cross-lingual NLI tasks on XTREME-R when measured by EM and F1 scores?

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