{
  "id": 16912,
  "url": "https://arxiv.org/abs/2608.05138v1",
  "title": "Teaching Nemotron Greek: Mining a Corpus, Adapting Retrieval, and Grounding Generation for Modern Greek across Specialist Domains",
  "summary": "Modern Greek is absent from NVIDIA's Nemotron retrieval models and from major multilingual retrieval benchmarks, despite being important for retrieval-augmented generation (RAG) in legal, energy, financial, and medical applications. We present an end-to-end adaptation of the Nemotron retrieval stack for Modern Greek, including corpus mining, synthetic supervision, retrieval model training, reranker adaptation, reader fine-tuning, and a new benchmark called HERA. Our study shows that a parameter-",
  "authors": "Ayoub Kirouane, Christos Petrocheilos",
  "category": "research",
  "topics": "healthcare,environment",
  "orgs": "nvidia",
  "regions": null,
  "published_at": "2026-08-05T17:56:40.000Z",
  "fetched_at": "2026-08-06T05:10:11.148Z",
  "source_slug": "x-arxiv-cs-ai",
  "source_name": "arXiv cs.AI",
  "source_homepage": "https://arxiv.org/list/cs.AI/recent",
  "ethics_ai_record_url": "https://ethics.ai/record/16912",
  "original_url": "https://arxiv.org/abs/2608.05138v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}