Teaching Nemotron Greek: Mining a Corpus, Adapting Retrieval, and Grounding Generation for Modern Greek across Specialist Domains | Ayoub Kirouane, Christos Petrocheilos | ResearchPod

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

Alex: Welcome to another episode of ResearchPod. Today, we're looking at why modern AI systems often fail when searching through complex Greek legal or financial documents — and what one research team did to fix that.

Sam: So the paper argues these tools are basically "blind" to Greek? That a cutting-edge AI could actually be worse than a simple keyword-search tool from 2009?

Alex: That's exactly what the study suggests. The idea that we have a reliable "state-of-the-art" for every language turns out to be a myth. These models simply haven't seen enough Greek — especially the formal, technical kind used in legal contracts or financial filings — to handle it well.

Sam: Is it purely a lack of training data, or is something more specific going wrong?

Alex: It's primarily about exposure to the right kind of text. Think of it like this: if you want to become a legal translator, reading a thousand children's books in Greek won't help you much. You need to read actual legal documents — the dense, long-winded, formal kind. Without that specific exposure, the model just doesn't develop the right instincts. So the researchers had to build an entire training ecosystem from scratch.

Sam: And how do you build that ecosystem when you don't have thousands of real annotated legal documents to start with?

Alex: That's the central challenge. They used a technique called synthetic query generation. Imagine you're preparing a student for a very specific exam. Instead of waiting for real past papers to appear, you use another AI to write thousands of practice questions directly from the textbook. The key is that each question has to be grounded in a real passage — so the model learns to connect a question to the exact text that answers it.

Sam: But I'd imagine the style of those practice questions matters a lot. If the AI just wrote simple, casual questions, the model wouldn't be prepared for how real users actually phrase things.

Alex: Precisely. They constrained the generation process so the questions matched the formal, multi-clause style of real legal and financial queries. A real user searching a legal database doesn't type "what does this contract say?" — they write something much longer and more specific. The synthetic training data had to reflect that.

Sam: So how did they actually measure whether any of this was working? If they trained on synthetic data, couldn't their tests be biased toward that same synthetic style?

Alex: That's a real risk, and they addressed it by creating a separate, independent benchmark called HERA. It tests two things: first, whether the model can find the right document from a large collection — not just one file, but many. And second, whether it can correctly recognize when a question simply has no answer in the available documents. That second part is often where AI systems quietly fail — they confidently return something plausible-sounding even when the answer isn't there.

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

Ayoub Kirouane, Christos Petrocheilos

Aug 7, 2026·5:52·arxiv·Original Paper

Retrieval-Augmented Generation (RAG)Dense Retrieval AdaptationLexical Baseline (BM25)LoRA-tuningHERA BenchmarkNegative Mining

Listen

6 min

Briefing

Abstract

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-free BM25 baseline outperforms several off-the-shelf multilingual dense retrieval models on specialist Greek corpora. After fine-tuning on 65,773 Greek retrieval pairs, a Nemotron 1B embedder improves nDCG@10 from 0.362 to 0.835 and substantially outperforms its unadapted counterpart. The learned language competence transfers to general-domain Greek, although the advantage over BM25 remains domain-dependent. We further adapt a cross-encoder reranker and demonstrate consistent improvements across specialist domains. Finally, we LoRA-tune a Nemotron 30B-A3B mixture-of-experts reader for grounded generation, increasing judged answer correctness from 29.4% to 66.9% while significantly improving faithfulness and citation quality. We also introduce HERA, the first large-scale Greek benchmark for retrieval-augmented generation, and release our adapted models and benchmark to support future research on Greek-language RAG systems.

Research Approach

This study addresses the absence of Modern Greek in major retrieval-augmented generation (RAG) models and benchmarks. The authors developed an end-to-end adaptation of the NVIDIA Nemotron retrieval stack, specifically targeting legal, energy, financial, and medical domains. The process involved mining a large corpus of Greek text, generating synthetic training pairs, fine-tuning a 1B embedder, and adapting a cross-encoder reranker. To evaluate these systems, the authors introduced HERA (Hellenic Retrieval-Augmented), a new large-scale benchmark designed to measure retrieval and grounded generation performance in Greek.

Key Findings

The researchers discovered that off-the-shelf multilingual dense retrieval models often underperform compared to a parameter-free BM25 lexical baseline when applied to specialist Greek documents. This suggests that for these domains, the primary bottleneck is language exposure rather than model capacity. By fine-tuning a 1B Nemotron embedder on 65,773 Greek retrieval pairs, the authors achieved a substantial improvement in retrieval accuracy (nDCG@10 increasing from 0.362 to 0.835). Furthermore, LoRA-tuning a 30B-A3B mixture-of-experts reader model significantly improved grounded generation, raising judged answer correctness from 29.4% to 66.9% while enhancing citation quality.

Why It Matters

Modern Greek is frequently overlooked in the development of RAG systems, despite the high demand for automated processing of complex, jargon-dense documents in professional sectors. This paper provides a practical roadmap for adapting existing retrieval stacks to low-resource or under-represented languages. By releasing the HERA benchmark and the adapted models, the authors provide the necessary infrastructure for future research into Greek-language RAG, demonstrating that domain-specific adaptation is essential for achieving reliable performance in specialized fields.

Key Terms and Definitions

BM25 — A standard, parameter-free lexical search algorithm that ranks documents based on keyword frequency, serving here as a robust baseline for Greek retrieval.
nDCG@10 — A ranking metric that evaluates the quality of the top 10 retrieved documents by rewarding the presence of relevant items at higher positions.
HERA — A newly introduced large-scale Greek benchmark for evaluating RAG systems, featuring multi-passage context, citation requirements, and unanswerable items.
Cross-encoder — A type of reranker that processes query-document pairs simultaneously to provide a more accurate relevance score than standard dense embedders.
Grounded Generation — The process of generating answers that are strictly supported by provided context, measured here by faithfulness and the accuracy of citations.

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