Impact of Model Scaling on Cross-Lingual Euphemism Detection in Low-Resource 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: What is the impact of scaling model size (e.g., XLM-R vs. larger multilingual models like Bloom or LLaMA) on cross-lingual euphemism detection accuracy in low-resource languages (e.g., Yoruba) when using sequential fine-tuning with English as an intermediate language?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 9.2/10.