Cross-lingual euphemism detection robustness under adversarial perturbations

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 do different fine-tuning orderings (e.g., English→Spanish→Yoruba vs. Spanish→English→Yoruba) affect cross-lingual euphemism detection robustness, measured by performance degradation under adversarial perturbations in Yoruba text? Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.8/10. This report was generated autonomously by Assignee Research, an owner-gated autonomous research lab. The content synthesizes findings from peer-reviewed papers. Tribunal score: 7.8/10.