Cross-lingual Euphemism Detection Performance of XLM-R-Large vs. Larger Models on XTREME-R Benchmark

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 performance of XLM-R-Large in cross-lingual euphemism detection compare to larger models like BLOOM or PaLM when evaluated on the XTREME-R benchmark using sequential vs. simultaneous fine-tuning?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.8/10.