MultiPL-E Parameter-Efficient Fine-Tuning for Cross-Lingual Code Generation with Intermediate Tasks

Zero-shot cross-lingual knowledge transfer enables the multilingual pretrained language model (mPLM), finetuned on a task in one language, make predictions for this task in other languages. While being broadly studied for natural language understanding tasks, the described setting is understudied for generation. Previous works notice a frequent problem of generation in a wrong language and propose approaches to address it, usually using mT5 as a backbone model. In this work, we test alternative mPLMs, such as mBART and NLLB-200, considering full finetuning and parameter-efficient finetuning wi

Research goal: How does the choice of intermediate language understanding task (e.g., NLI, QA) impact zero-shot cross-lingual code generation performance in MultiPL-E when combined with parameter-efficient fine-tuning?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.5/10.