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.

Parameter-Efficient Tuning vs. Full Fine-Tuning in Cross-Lingual Dense Retrieval for Low-Resource Languages

Domaine:

natural language processing

Type de record:

paper
Créateur:
Ass
Éditeur:
Zenodo
Hôte:avatar
Effective cross-lingual dense retrieval methods that rely on multilingual pre-trained language models (PLMs) need to be trained to encompass both the relevance matching task and the cross-language alignment task. However, cross-lingual data for training is often scarcely available. In this paper, rather than using more cross-lingual data for training, we propose to use cross-lingual query generation to augment passage representations with queries in languages other than the original passage language. These augmented representations are used at inference time so that the representation can enco Research goal: What is the impact of parameter-efficient tuning methods versus full fine-tuning on cross-lingual dense retrieval robustness for unseen low-resource languages? Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.7/10. This report was generated autonomously by Assignee Research, an owner-gated autonomous research lab. The content synthesizes findings from peer-reviewed papers. Tribunal score: 8.7/10.

Visit

doi.orgzenodo.org

Tasks

information retrievaltransfer learning

Tags

impactparameter-efficienttuningmethodsversusfullfine-tuningcross-lingual

Licenses

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

Similaires

Early-Layer LoRA Fine-Tuning vs Full-Parameter Tuning for Zero-Shot Cross-Lingual Retrieval in Low-Resource LanguagesTargeted Lexical Injection vs Full-Fine-Tuning for Cross-Lingual Representation Robustness in Low-Resource LanguagesEarly-Layer LoRA Versus Full-Parameter Fine-Tuning for Cross-Lingual Lexical Alignment in Low-Resource African Languages onFull Fine-Tuning vs. Parameter-Efficient Adaptation for Low-Resource African ASR: A Controlled Study with Whisper-SmallEarly-Layer LoRA Adaptation vs Full Fine-Tuning for Zero-Shot Cross-Lingual Transfer in Low-Resource African LanguagesDomain-Adaptive Fine-Tuning vs. Hybrid Batch Training in Zero-Shot Cross-Lingual Retrieval for Low-Resource XQuAD Languages

Early-Layer LoRA Fine-Tuning vs Full-Parameter Tuning for Zero-Shot Cross-Lingual Retrieval in Low-Resource Languages

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

Targeted Lexical Injection vs Full-Fine-Tuning for Cross-Lingual Representation Robustness in Low-Resource Languages

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

Early-Layer LoRA Versus Full-Parameter Fine-Tuning for Cross-Lingual Lexical Alignment in Low-Resource African Languages on

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

Full Fine-Tuning vs. Parameter-Efficient Adaptation for Low-Resource African ASR: A Controlled Study with Whisper-Small

Early-Layer LoRA Adaptation vs Full Fine-Tuning for Zero-Shot Cross-Lingual Transfer in Low-Resource African Languages

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

Domain-Adaptive Fine-Tuning vs. Hybrid Batch Training in Zero-Shot Cross-Lingual Retrieval for Low-Resource XQuAD Languages

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