Impact of Batch Size Variation on XLM-R-Large's Inference Efficiency and Accuracy in Low-Resource Euphemism Detection

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 varying the batch size during sequential fine-tuning on XLM-R-Large's inference efficiency (measured in tokens/sec) and accuracy for euphemism detection in low-resource languages like Yoruba?

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