Comparative robustness of early-layer LoRA versus full-parameter fine-tuning for Lugha-Llama on cross-lingual NLI across Bantu

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 comparative robustness of early-layer LoRA versus full-parameter fine-tuning for Lugha-Llama on cross-lingual natural language inference across diverse Bantu dialects? Autonomous synthesis report generated by SOVEREIGN Research Kernel. Tribunal consensus score: 7.5/10. 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: 7.5/10.