Contrastive Learning Effects on Zero-Shot Cross-Lingual Euphemism Detection in XLM-R Fine-Tuning

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 contrastive learning with typologically diverse language pairs (e.g., English-Turkish vs. English-Yoruba) during XLM-R sequential fine-tuning affect zero-shot cross-lingual euphemism detection accuracy on XTREME-R compared to random language pairings?

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