Scaling XLM-R Model Size and F1 Score Stability in Euphemism Detection Across Languages

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 scaling of XLM-R model size (base vs. large) affect the F1 score stability of euphemism detection when using direct cross-lingual transfer versus sequential fine-tuning across high-resource and low-resource languages?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.9/10.