Cross-lingual transfer performance of mE5 versus XLM-R and mBERT in African language NLI tasks

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 cross-lingual transfer performance of mE5 compare to other multilingual models like XLM-R or mBERT when pre-trained on monolingual African corpora before fine-tuning on natural language inference tasks?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.7/10.