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.

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

Domaine:

natural language processing

Type de record:

paper
Créateur:
Ass
Éditeur:
Zenodo
Hôte:avatar
Large Language Models (LLMs) have demonstrated remarkable capabilities, yet their performance in low-resource languages (LRLs), such as Swahili, often lags due to data scarcity and underrepresentation in pre-training. A key challenge is achieving robust cross-lingual lexical alignment, crucial for tasks like translation and cross-lingual information retrieval. This paper introduces Targeted Lexical Injection (TLI), a novel and efficient fine-tuning approach. We first demonstrate that Lugha-Llama-8B-wura, a Swahili-centric LLM, exhibits strong, near-perfect lexical alignment for Swahili-English Research goal: How does early-layer LoRA fine-tuning compare to full-parameter fine-tuning in improving cross-lingual lexical alignment accuracy for low-resource African languages on the FLORES-200 benchmark? 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.orgzenodo.org

Tasks

transfer learning

Languages

Swahili

Tags

early-layerLoRAfine-tuningfull-parameterimprovingcross-linguallexicalalignment

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 LanguagesEarly-Layer LoRA Fine-Tuning for Cross-Lingual Lexical Alignment in Zero-Shot Translation of Low-Resource African LanguagesEarly-Layer LoRA Fine-Tuning for Lexical Alignment in Low-Resource African Languages on XNLI AccuracyLoRA Rank Variation in Early-Layer Fine-Tuning and Cross-Lingual Alignment for Low-Resource African LanguagesEarly-Layer LoRA Adaptation vs Full Fine-Tuning for Zero-Shot Cross-Lingual Transfer in Low-Resource African LanguagesEarly-Layer LoRA Fine-Tuning vs Full-Parameter Tuning for Cross-Lingual Alignment in Lugha-Llama on XNLI Accuracy in Yoruba and

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

Early-Layer LoRA Fine-Tuning for Cross-Lingual Lexical Alignment in Zero-Shot Translation of Low-Resource African Languages

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

Early-Layer LoRA Fine-Tuning for Lexical Alignment in Low-Resource African Languages on XNLI Accuracy

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

LoRA Rank Variation in Early-Layer Fine-Tuning and Cross-Lingual Alignment for Low-Resource African Languages

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

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

Early-Layer LoRA Fine-Tuning vs Full-Parameter Tuning for Cross-Lingual Alignment in Lugha-Llama on XNLI Accuracy in Yoruba and

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