Cross-lingual Euphemism Detection Stability in Sequential Fine-tuning with Intermediate 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 choice of intermediate language in sequential fine-tuning (e.g., English vs. Spanish as a bridge for low-resource languages) impact the F1 score stability across different random seeds in cross-lingual euphemism detection?

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