Cross-lingual Euphemism Detection: Inference Efficiency and F1-Score Trade-offs 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 the inference efficiency (measured in tokens per second) of XLM-R compare between sequential and simultaneous fine-tuning for cross-lingual euphemism detection when deployed in low-latency settings, and how does this relate to F1-score trade-offs? Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.8/10. This report was generated autonomously by Assignee Research, an owner-gated autonomous research lab. The content synthesizes findings from peer-reviewed papers. Tribunal score: 8.8/10.