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.

Impact of LoRA Layer Variation on Cross-Lingual Lexical Alignment in Lugha-Llama for African Languages

Domaine:

natural language processing

Type de record:

paper

Créateur:

SOV

Éditeur:

Zenodo

Hôte:

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: What is the impact of varying the number of LoRA layers on cross-lingual lexical alignment in Lugha-Llama when benchmarked against the FLORES-200 evaluation suite for diverse African languages? Autonomous synthesis report generated by SOVEREIGN Research Kernel. Tribunal consensus score: 7.6/10. 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: 7.6/10.

Visit

Tasks

transfer learning

Languages

Tags

impact varying number LoRA layers cross-lingual lexical alignment

Licenses

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

Similaires

Early-Layer LoRA Fine-Tuning for Lexical Alignment in Lugha-Llama and Cross-Lingual Retrieval Accuracy on Swahili BenchmarksEarly-Layer LoRA Fine-Tuning for Lexical Alignment in Lugha-Llama: Zero-Shot Cross-Lingual Transfer Accuracy on XNLI forTargeted Lexical Injection: Unlocking Latent Cross-Lingual Alignment in Lugha-Llama via Early-Layer LoRA Fine-TuningEarly-Layer LoRA for Lexical Alignment in Lugha-Llama: Zero-Shot Translation on Morphologically Rich Bantu LanguagesLatent Cross-Lingual Alignment in Lugha-Llama for Unseen African LanguagesCross-Lingual Alignment of Lugha-Llama with Early-Layer LoRA on Bantu NLI Tasks Versus AfricanLM and MasakhaneLM

Early-Layer LoRA Fine-Tuning for Lexical Alignment in Lugha-Llama and Cross-Lingual Retrieval Accuracy on Swahili Benchmarks

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

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

Targeted Lexical Injection: Unlocking Latent Cross-Lingual Alignment in Lugha-Llama via Early-Layer LoRA Fine-Tuning

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

Early-Layer LoRA for Lexical Alignment in Lugha-Llama: Zero-Shot Translation on Morphologically Rich Bantu Languages

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

Latent Cross-Lingual Alignment in Lugha-Llama for Unseen African Languages

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

Cross-Lingual Alignment of Lugha-Llama with Early-Layer LoRA on Bantu NLI Tasks Versus AfricanLM and MasakhaneLM

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