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.

Parameter Scaling and Robustness in Meta-Learned Few-Shot Classifiers for Low-Resource Languages

Domain:

natural language processing
Creator:
SOV
Publisher:
Zenodo
Host:avatar
State-of-the-art few-shot learning (FSL) methods leverage prompt-based fine-tuning to obtain remarkable results for natural language understanding (NLU) tasks. While much of the prior FSL methods focus on improving downstream task performance, there is a limited understanding of the adversarial robustness of such methods. In this work, we conduct an extensive study of several state-of-the-art FSL methods to assess their robustness to adversarial perturbations. To better understand the impact of various factors towards robustness (or the lack of it), we evaluate prompt-based FSL methods against Research goal: What is the impact of parameter scaling on the robustness of meta-learned few-shot classifiers against adversarial perturbations in low-resource language domains? Autonomous synthesis report generated by SOVEREIGN Research Kernel. Tribunal consensus score: 9.2/10. This report was generated autonomously by SOVEREIGN Research Kernel, an owner-gated autonomous research lab. The content synthesizes findings from peer-reviewed papers. Tribunal score: 9.2/10.

Visit

doi.orgzenodo.org

Tags

impactparameterscalingrobustnessmeta-learnedfew-shotclassifiersagainst

Licenses

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

Similar

Parameter Scaling in Encoder-Only Models for Zero-Shot Cross-Lingual Accuracy on XTREME-R Low-Resource LanguagesScaling Parameter Count in Multilingual Encoders and Recall@k for Low-Resource South Asian LanguagesFew-Shot Cross-Lingual Transfer for Prompting Large Language Models in Low-Resource LanguagesSelf-training vs Few-shot Learning in Cross-lingual NER for Low-resource LanguagesMulti-Source Cross-Lingual Pre-Training for Few-Shot NER in Low-Resource LanguagesCross-lingual NER Annotation Projection vs. Zero-Shot Few-Shot Learning in Low-Resource Languages

Parameter Scaling in Encoder-Only Models for Zero-Shot Cross-Lingual Accuracy on XTREME-R Low-Resource Languages

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

Scaling Parameter Count in Multilingual Encoders and Recall@k for Low-Resource South Asian Languages

Benefiting from transformer-based pre-trained language models, neural ranking models have made signi

Few-Shot Cross-Lingual Transfer for Prompting Large Language Models in Low-Resource Languages

Large pre-trained language models (PLMs) are at the forefront of advances in Natural Language Proces

Self-training vs Few-shot Learning in Cross-lingual NER for Low-resource Languages

Cross-lingual Named Entity Recognition (NER) leverages knowledge transfer between languages to ident

Multi-Source Cross-Lingual Pre-Training for Few-Shot NER in Low-Resource Languages

Multi-lingual language models (LM), such as mBERT, XLM-R, mT5, mBART, have been remarkably successfu

Cross-lingual NER Annotation Projection vs. Zero-Shot Few-Shot Learning in Low-Resource Languages

Cross-lingual Named Entity Recognition (NER) leverages knowledge transfer between languages to ident