Scaling Model Size and Zero-Shot Cross-Lingual Transfer Performance in Low-Resource Languages

Pre-trained multilingual language encoders, such as multilingual BERT and XLM-R, show great potential for zero-shot cross-lingual transfer. However, these multilingual encoders do not precisely align words and phrases across languages. Especially, learning alignments in the multilingual embedding space usually requires sentence-level or word-level parallel corpora, which are expensive to be obtained for low-resource languages. An alternative is to make the multilingual encoders more robust; when fine-tuning the encoder using downstream task, we train the encoder to tolerate noise in the contex Research goal: What is the effect of scaling model size (e.g., comparing 7B vs. 13B vs. 30B parameter models) on the zero-shot cross-lingual transfer performance of intermediate-task-trained models on XCSQA for low-resource languages? Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.2/10. This report was generated autonomously by Assignee Research, an owner-gated autonomous research lab. The content synthesizes findings from peer-reviewed papers. Tribunal score: 8.2/10.