Logo Lanfrica
  • Home
  • Atlas
  • Insights
  • Docs
  • Sign in

© 2026 Lanfrica. All rights reserved. All copyrights of the resources shown on the Lanfrica website belong to the original copyright holders, unless explicitly stated otherwise.

Contrastive-Adversarial Fine-Tuning for Zero-Shot Cross-Lingual Performance in XLM-R

Domain:

natural language processing

Record type:

paper
Creator:
Ass
Publisher:
Zenodo
Host:avatar
Pre-trained multilingual language encoders, such as multilingual BERT and XLM-R, show great potential for zero-shot cross-lingual transfer. However, these multilingual encoders do not precisely align words and phrases across languages. Especially, learning alignments in the multilingual embedding space usually requires sentence-level or word-level parallel corpora, which are expensive to be obtained for low-resource languages. An alternative is to make the multilingual encoders more robust; when fine-tuning the encoder using downstream task, we train the encoder to tolerate noise in the contex Research goal: How does the combination of contrastive learning and adversarial training during XLM-R fine-tuning impact zero-shot cross-lingual performance on XTREME-R when evaluated with macro-F1 score, compared to vanilla adversarial training, and does this improvement scale with the number of languages included in training? Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.2/10. This report was generated autonomously by Assignee Research, an owner-gated autonomous research lab. The content synthesizes findings from peer-reviewed papers. Tribunal score: 8.2/10.

Visit

doi.org

Tasks

transfer learning

Tags

combinationcontrastivelearningadversarialtrainingduringXLM-Rfine-tuning

Licenses

Creative Commons Attribution 4.0 Internationalhttps://creativecommons.org/licenses/by/4.0/legalcode

Similar

Gradient-based adversarial fine-tuning for XLM-R robustness in zero-shot cross-lingual classificationContrastive Learning Effects on Zero-Shot Cross-Lingual Euphemism Detection in XLM-R Fine-TuningGradient Clipping Thresholds in XLM-R Fine-Tuning for Zero-Shot Cross-Lingual TransferContrastive Learning and Adversarial Training Effects on XLM-R Robustness in Zero-Shot Cross-Lingual TasksSequence of Intermediate-Task Fine-Tuning and Zero-Shot Cross-Lingual Performance on XTREME-R with Adversarial PerturbationsLayer-wise Feature Aggregation and Fine-tuning for Zero-shot Cross-lingual Performance in XTREME-R

Gradient-based adversarial fine-tuning for XLM-R robustness in zero-shot cross-lingual classification

Pre-trained multilingual language encoders, such as multilingual BERT and XLM-R, show great potentia

Contrastive Learning Effects on Zero-Shot Cross-Lingual Euphemism Detection in XLM-R Fine-Tuning

Euphemisms are culturally variable and often ambiguous, posing challenges for language models, espec

Gradient Clipping Thresholds in XLM-R Fine-Tuning for Zero-Shot Cross-Lingual Transfer

Pre-trained multilingual language encoders, such as multilingual BERT and XLM-R, show great potentia

Contrastive Learning and Adversarial Training Effects on XLM-R Robustness in Zero-Shot Cross-Lingual Tasks

Pre-trained multilingual language encoders, such as multilingual BERT and XLM-R, show great potentia

Sequence of Intermediate-Task Fine-Tuning and Zero-Shot Cross-Lingual Performance on XTREME-R with Adversarial Perturbations

Pre-trained multilingual language encoders, such as multilingual BERT and XLM-R, show great potentia

Layer-wise Feature Aggregation and Fine-tuning for Zero-shot Cross-lingual Performance in XTREME-R

Euphemisms are culturally variable and often ambiguous, posing challenges for language models, espec