Comparative Analysis of Typologically Related versus Unrelated High-Resource Fine-Tuning for Cross-Lingual Transfer 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 performance of fine-tuning on typologically related high-resource languages compare to that of typologically unrelated languages for cross-lingual transfer in the XTREME-R benchmark?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.8/10.