Scaling XLM-R Model Size and F1 Score Stability in Euphemism Detection Across Languages
Domain:
natural language processingRecord type:
paper
Creator:
Ass
Publisher:
Host:
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 scaling of XLM-R model size (base vs. large) affect the F1 score stability of euphemism detection when using direct cross-lingual transfer versus sequential fine-tuning across high-resource and low-resource languages?
Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.9/10. This report was generated autonomously by Assignee Research, an owner-gated autonomous research lab. The content synthesizes findings from peer-reviewed papers. Tribunal score: 7.9/10.
Similar
Cross-lingual Euphemism Detection: Inference Efficiency and F1-Score Trade-offs in XLM-R Fine-tuningModel Size Scaling in mBERT for Cross-Lingual Euphemism Detection Across High- and Low-Resource Languages on XTREME-RBatch Size Scaling Strategies in Sequential Fine-Tuning of XLM-R-Large for Cross-Lingual Euphemism DetectionBatch Size Variation in XLM-R Fine-Tuning for Yoruba Euphemism DetectionScaling Batch Size in Sequential vs. Simultaneous Fine-Tuning of XLM-R-Large for Cross-Lingual Euphemism Detection Bias Alignment**Scaling Model Size and Fine-Tuning Strategies in Cross-Lingual Euphemism Detection**