LoRA Rank Variation in Early-Layer Fine-Tuning and Cross-Lingual Alignment for Low-Resource African Languages
Domaine:
natural language processingType de record:
paper
Créateur:
Ass
Éditeur:
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: How does varying LoRA rank in early-layer fine-tuning affect cross-lingual alignment accuracy on XNLI for other low-resource African languages compared to Swahili?
Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.5/10. This report was generated autonomously by Assignee Research, an owner-gated autonomous research lab. The content synthesizes findings from peer-reviewed papers. Tribunal score: 8.5/10.
Similaires
LoRA Rank Variation in Middle-Layer vs. Late-Layer Fine-Tuning for Swahili-English Cross-Lingual AlignmentEarly-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 vs. Late-Layer LoRA Fine-Tuning for Cross-Lingual NLI in Low-Resource African LanguagesEarly-Layer LoRA Fine-Tuning for Zero-Shot Cross-Lingual NLI in Low-Resource African LanguagesEarly-Layer LoRA Fine-Tuning for Cross-Domain Alignment in Lugha-Llama for Low-Resource Bantu Languages