Teaching Nemotron Greek: Mining a Corpus, Adapting Retrieval, and Grounding Generation for Modern Greek across Specialist Domains

Ayoub Kirouane, Christos Petrocheilos|August 5, 2026arXiv

Key Takeaway

Domain-specific fine-tuning dramatically improves retrieval and generation for underrepresented languages: a modest 1B embedder outperforms multilingual models when trained on just 65K in-domain Greek examples, showing that language adaptation is more important than model size for specialized tasks.

Summary

This paper adapts NVIDIA's Nemotron retrieval system for Modern Greek across legal, energy, financial, and medical domains. The authors mine Greek corpora, train specialized retrieval models, and create HERA—the first large-scale Greek RAG benchmark.

training multimodal applications

Key Terms

rag-pipeline dense-vector-embeddings lora cross-encoder synthetic-supervision