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.

Rethinking what Matters: Effective and Robust Multilingual Realignment for Low-Resource Languages

Domaine:

natural language processing

Type de record:

paper
Créateur:
NguAnuGasChe
Hôte:avatar
Realignment is a promising strategy to improve cross-lingual transfer in multilingual language models. However, empirical results are mixed and often unreliable, particularly for typologically distant or low-resource languages (LRLs) compared to English. Moreover, word realignment tools often rely on high-quality parallel data, which can be scarce or noisy for many LRLs. In this work, we conduct an extensive empirical study to investigate whether realignment truly benefits from using all available languages, or if strategically selected subsets can offer comparable or even improved cross-lingual transfer, and study the impact on LRLs. Our controlled experiments show that realignment can be particularly effective for LRLs and that using carefully selected, linguistically diverse subsets can match full multilingual alignment, and even outperform it for unseen LRLs. This indicates that effective realignment does not require exhaustive language coverage and can reduce data collection overhead, while remaining both efficient and robust when guided by informed language selection. Accepted to IJCNLP-AACL 2025

Visit

arxiv.org

Tasks

transfer learning

Tags

Computation and LanguageArtificial Intelligence

Similaires

Toward Robust Multilingual Adaptation of LLMs for Low-Resource LanguagesEffective vocabulary expansion of multilingual language models for extremely low-resource languagesRobust speech recognition for low-resource languagesMultilingual Adversarial Training for Robust Zero-Shot Cross-Lingual Transfer in Low-Resource LanguagesMultilingual Contrastive Learning for Robust Zero-Shot Cross-Lingual Retrieval in Low-Resource LanguagesRobust Multilingual Encoder Training for Low-Resource Language Alignment

Toward Robust Multilingual Adaptation of LLMs for Low-Resource Languages

Large language models (LLMs) continue to struggle with low-resource languages, primarily due to limi

Effective vocabulary expansion of multilingual language models for extremely low-resource languages

Multilingual pre-trained language models(mPLMs) offer significant benefits for many low-resource lan

Robust speech recognition for low-resource languages

Process of human-machine interaction is an integral part of everyday human life in a modern world. T

Multilingual Adversarial Training for Robust Zero-Shot Cross-Lingual Transfer in Low-Resource Languages

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

Multilingual Contrastive Learning for Robust Zero-Shot Cross-Lingual Retrieval in Low-Resource Languages

Information retrieval across different languages is an increasingly important challenge in natural l

Robust Multilingual Encoder Training for Low-Resource Language Alignment

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