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

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: What is the effect of incorporating contrastive learning with adversarial training on XLM-R's robustness to adversarial attacks in zero-shot cross-lingual tasks, as measured by accuracy drop on the XTREME-R benchmark for low-resource languages? Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.8/10. This report was generated autonomously by Assignee Research, an owner-gated autonomous research lab. The content synthesizes findings from peer-reviewed papers. Tribunal score: 7.8/10.

Visit

doi.org

Tasks

transfer learning

Tags

effectincorporatingcontrastivelearningadversarialtrainingXLM-Rrobustness

Licenses

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

Similar

Adversarial Training Effects on Zero-Shot Cross-Lingual Transfer Robustness in XLM-R ModelsAdversarial Pre-training Effects on XLM-R Zero-Shot Cross-Lingual Transfer in XTREME-RHybrid Batch Training Effects on XLM-R Robustness in Zero-Shot Cross-Lingual RetrievalAdversarial Training Impact on Zero-Shot Cross-Lingual Robustness in XTREME-RContrastive-Adversarial Fine-Tuning for Zero-Shot Cross-Lingual Performance in XLM-RContrastive Learning Effects on Zero-Shot Cross-Lingual Euphemism Detection in XLM-R Fine-Tuning

Adversarial Training Effects on Zero-Shot Cross-Lingual Transfer Robustness in XLM-R Models

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

Adversarial Pre-training Effects on XLM-R Zero-Shot Cross-Lingual Transfer in XTREME-R

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

Hybrid Batch Training Effects on XLM-R Robustness in Zero-Shot Cross-Lingual Retrieval

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

Adversarial Training Impact on Zero-Shot Cross-Lingual Robustness in XTREME-R

Intermediate-task training---fine-tuning a pretrained model on an intermediate task before fine-tuni

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

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