Neural Machine Translation (NMT) models for low-resource languages suffer significant performance degradation under domain shift. We quantify this challenge using **Dhao**, an indigenous language of Eastern Indonesia with no digital footprint beyond the New Testament (NT). When applied to the unseen Old Testament (OT), a standard NMT model fine-tuned on the NT drops from an in-domain score of 36.17 chrF++ to 27.11 chrF++. To recover this loss, we introduce a **hybrid framework** where a fine-tuned NMT model generates an initial draft, which is then refined by a Large Language Model (LLM) using Retrieval-Augmented Generation (RAG). The final system achieves 35.21 chrF++ (+8.10 recovery), effectively matching the original in-domain quality. Our analysis reveals that this performance is driven primarily by the **number of retrieved examples** rather than the choice of retrieval algorithm. Qualitative analysis confirms the LLM acts as a robust "safety net," repairing severe failures in zero-shot domains.

We present NusaBERT, a multilingual model built on IndoBERT and tailored for Indonesia’s diverse languages. By expanding vocabulary and pre-training on a regional corpus, NusaBERT achieves state-of-the-art performance on Indonesian NLU benchmarks, enhancing IndoBERT’s multilingual capability. This study also addresses NusaBERT’s limitations and encourages further research on Indonesia’s underrepresented languages.