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.

Impact of Sparsity Levels in Composable Sparse Fine-Tuning on Zero-Shot Cross-Lingual Transfer for Morphologically Complex

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 varying the sparsity level in composable sparse fine-tuning affect zero-shot cross-lingual transfer performance on mXGLUE for morphologically complex languages when evaluated using XNLI accuracy? Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.5/10. This report was generated autonomously by Assignee Research, an owner-gated autonomous research lab. The content synthesizes findings from peer-reviewed papers. Tribunal score: 7.5/10.

Visit

doi.org

Tasks

transfer learning

Tags

varyingsparsitylevelcomposablesparsefine-tuningaffectzero-shot

Licenses

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

Similar

Gradient Clipping Thresholds in XLM-R Fine-Tuning for Zero-Shot Cross-Lingual TransferSequential Fine-Tuning Task Quantity and Zero-Shot Cross-Lingual Transfer in XTREME-RSequential vs. Simultaneous Fine-Tuning in XTREME-R: Zero-Shot Accuracy Degradation on Morphologically Complex LanguagesComparative Analysis of Multilingual and English-Only Intermediate Fine-Tuning for Zero-Shot Cross-Lingual Transfer on XTREME-RMuCoT contrastive training vs. standard fine-tuning for zero-shot cross-lingual transfer in low-resource languagesEarly-Layer LoRA Fine-Tuning for Lexical Alignment in Lugha-Llama: Zero-Shot Cross-Lingual Transfer Accuracy on XNLI for

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

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

Sequential vs. Simultaneous Fine-Tuning in XTREME-R: Zero-Shot Accuracy Degradation on Morphologically Complex Languages

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

Comparative Analysis of Multilingual and English-Only Intermediate Fine-Tuning for Zero-Shot Cross-Lingual Transfer on XTREME-R

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

MuCoT contrastive training vs. standard fine-tuning for zero-shot cross-lingual transfer in low-resource languages

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

Early-Layer LoRA Fine-Tuning for Lexical Alignment in Lugha-Llama: Zero-Shot Cross-Lingual Transfer Accuracy on XNLI for

Large Language Models (LLMs) have demonstrated remarkable capabilities, yet their performance in low