教Nemotron学习希腊语：语料库挖掘、检索适配与专业领域现代希腊语生成锚定

摘要

现代希腊语在NVIDIA的Nemotron检索模型以及主流多语言检索基准中均未涉及，尽管其在法律、能源、金融和医疗等领域的检索增强生成（RAG）应用中具有重要价值。我们提出了针对现代希腊语的Nemotron检索栈端到端适配方案，涵盖语料挖掘、合成监督、检索模型训练、重排序器适配、阅读器微调，以及一个新基准HERA。我们的研究表明，在专业希腊语语料上，无需参数训练的BM25基线表现优于多种现成的多语言稠密检索模型。在65,773个希腊语检索对上微调后，Nemotron 1B嵌入模型的nDCG@10从0.362提升至0.835，并显著优于未适配的原始模型。所学到的语言能力可迁移至通用领域的希腊语任务，但相对于BM25的优势仍具有领域依赖性。我们进一步适配了交叉编码器重排序器，并在各专业领域展示了持续的性能提升。最后，我们对Nemotron 30B-A3B混合专家阅读器进行LoRA调参以用于生成式问答，将人工评定的答案正确率从29.4%提升至66.9%，同时显著改善了忠实度和引文质量。我们还推出了HERA——首个大规模希腊语检索增强生成基准，并公开发布适配后的模型及基准，以支持希腊语RAG系统的未来研究。

English

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.