Impact of Multilingual Intermediate-Task Training on Zero-Shot Cross-Lingual Code Generation Accuracy

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 intermediate-task training with multilingual code datasets (e.g., MultiPL-E) affect the accuracy of zero-shot cross-lingual code generation models compared to monolingual English models on the MBXP benchmark, measured by execution rate and exact match accuracy?

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