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 Fine-Tuning Depth in TLI and Cross-Lingual Lexical Alignment via LAS Scores

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: To what extent does the depth of early-layer LoRA fine-tuning in TLI affect cross-lingual lexical alignment, as measured by LAS scores across different language pairs? 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.orgzenodo.org

Languages

Swahili

Tags

extentdepthearly-layerLoRAfine-tuningTLIaffectcross-lingual

Licenses

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

Similaires

Targeted Lexical Injection: Unlocking Latent Cross-Lingual Alignment in Lugha-Llama via Early-Layer LoRA Fine-TuningEarly-Layer LoRA Fine-Tuning for Swahili-English Lexical Alignment and Zero-Shot Cross-Lingual Transfer AccuracyEarly-Layer LoRA Fine-Tuning for Lexical Alignment in Lugha-Llama and Cross-Lingual Retrieval Accuracy on Swahili BenchmarksEarly-Layer LoRA Versus Full-Parameter Fine-Tuning for Cross-Lingual Lexical Alignment in Low-Resource African Languages onEarly-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 Lugha-Llama: Zero-Shot Cross-Lingual Transfer Accuracy on XNLI for

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 Fine-Tuning for Swahili-English Lexical Alignment and Zero-Shot Cross-Lingual Transfer Accuracy

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

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 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

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 Lugha-Llama: Zero-Shot Cross-Lingual Transfer Accuracy on XNLI for

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