Model Size Scaling in mBERT for Cross-Lingual Euphemism Detection Across High- and Low-Resource Languages on 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: What is the impact of model size scaling in mBERT on cross-lingual euphemism detection accuracy across high- and low-resource languages, as measured by F1 scores on XTREME-R benchmarks?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.5/10.