Logo Lanfrica
  • Accueil
  • Atlas
  • Analyses
  • Documentation
  • Sign in

© 2026 Lanfrica. Tous droits réservés. Tous les droits d'auteur des ressources affichées sur le site Web Lanfrica appartiennent aux détenteurs de droits d'auteur d'origine, sauf indication contraire explicite.

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

Domaine:

natural language processing

Type de record:

paper
Créateur:
Ass
Éditeur:
Zenodo
Hôte: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 sequence of intermediate-task fine-tuning in multilingual models affect the zero-shot cross-lingual performance on the XTREME-R benchmark when evaluated on adversarial perturbations? Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.6/10. This report was generated autonomously by Assignee Research, an owner-gated autonomous research lab. The content synthesizes findings from peer-reviewed papers. Tribunal score: 7.6/10.

Visit

doi.org

Tasks

transfer learning

Tags

sequenceintermediate-taskfine-tuningmultilingualmodelsaffectzero-shotcross-lingual

Licenses

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

Similaires

Intermediate-Task Training for Robust Zero-Shot Cross-Lingual Transfer on Adversarial XTREME-R SamplesSequential Fine-Tuning Task Quantity and Zero-Shot Cross-Lingual Transfer in XTREME-RImpact of Intermediate Task Difficulty on Zero-Shot Cross-Lingual Performance in XTREME-RZero-Shot Cross-Lingual Transfer Performance Variations with Intermediate Task Difficulty in XTREME-RZero-Shot Cross-Lingual Transfer of Intermediate-Task-Trained Models versus Direct Fine-Tuning on XTREME-R for Low-ResourceContrastive-Adversarial Fine-Tuning for Zero-Shot Cross-Lingual Performance in XLM-R

Intermediate-Task Training for Robust Zero-Shot Cross-Lingual Transfer on Adversarial XTREME-R Samples

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

Sequential Fine-Tuning Task Quantity and Zero-Shot Cross-Lingual Transfer in XTREME-R

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

Impact of Intermediate Task Difficulty on Zero-Shot Cross-Lingual Performance in XTREME-R

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

Zero-Shot Cross-Lingual Transfer Performance Variations with Intermediate Task Difficulty in XTREME-R

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

Zero-Shot Cross-Lingual Transfer of Intermediate-Task-Trained Models versus Direct Fine-Tuning on XTREME-R for Low-Resource

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