**Monolingual Pretraining Enhancement for Multilingual Zero-Shot 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: How does the integration of language-specific pretraining (e.g., monolingual corpora) on top of multilingual intermediate tasks affect the performance of mPLMs on zero-shot cross-lingual transfer benchmarks like XTREME-R and PAWS-X?

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