Combining mPLM-Sim with Prompt-Based Fine-Tuning for Zero-Shot Cross-Lingual Transfer

Recent multilingual pretrained language models (mPLMs) have been shown to encode strong language-specific signals, which are not explicitly provided during pretraining. It remains an open question whether it is feasible to employ mPLMs to measure language similarity, and subsequently use the similarity results to select source languages for boosting cross-lingual transfer. To investigate this, we propose mPLMSim, a language similarity measure that induces the similarities across languages from mPLMs using multi-parallel corpora. Our study shows that mPLM-Sim exhibits moderately high correlatio

Research goal: Can the language similarity measure mPLM-Sim be effectively combined with prompt-based fine-tuning to improve zero-shot cross-lingual transfer performance on benchmarks like XTREME-R and PAWS-X, as measured by per-language accuracy gains?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.3/10.