Layer-wise Feature Aggregation and Fine-tuning for Zero-shot Cross-lingual Performance in XTREME-R

Euphemisms are culturally variable and often ambiguous, posing challenges for language models, especially in low-resource settings. This paper investigates how cross-lingual transfer via sequential fine-tuning affects euphemism detection across five languages: English, Spanish, Chinese, Turkish, and Yoruba. We compare sequential fine-tuning with monolingual and simultaneous fine-tuning using XLM-R and mBERT, analyzing how performance is shaped by language pairings, typological features, and pretraining coverage. Results show that sequential fine-tuning with a high-resource L1 improves L2 perfo

Research goal: How does the combination of layer-wise feature aggregation and fine-tuning on a high-resource language (e.g., English) affect zero-shot cross-lingual performance on low-resource languages in XTREME-R, compared to using only the last layer?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.7/10.