用检索增强生成让开源大模型精准翻译中世纪拉丁文
"Don't Teach Minerva": Guiding LLMs Through Complex Syntax for Faithful Latin Translation with RAG
- 先用微调模型生成结构忠实的初稿，再用零样本大模型润色
- 在两个测试集上表现媲美GPT-5，无需特定任务微调
- 适合研究低资源语言翻译与可复现AI系统构建者
翻译语法丰富但资源稀缺的语言如拉丁语面临重大挑战。本文提出一种可复现的基于草稿的精炼流程，使开源大语言模型性能达到与顶级专有系统统计上相当的水平。方法首先使用微调过的NLLB-1.3B模型生成高质量、结构忠实的初稿；随后，零样本大模型（Llama-3.3或Qwen3）对初稿进行润色，该过程可通过引入检索到的外部例句（RAG）进一步优化。我们在两个不同基准上验证了该方法的鲁棒性：一个标准的域内测试集（Rosenthal, 2023）和一个新的、具有挑战性的域外（OOD）测试集——2025年发布的12世纪拉丁书信集。核心发现是，该开源RAG系统在无需任何任务特定微调的情况下，性能与GPT-5基线统计上相当。我们发布了整个流程、Chartres OOD数据集及评估脚本与模型，以促进可复现性和进一步研究。
原文摘要 · Abstract (English)
Translating a morphology-rich, low-resource language like Latin poses significant challenges. This paper introduces a reproducible draft-based refinement pipeline that elevates open-source Large Language Models (LLMs) to a performance level statistically comparable to top-tier proprietary systems. Our method first uses a fine-tuned NLLB-1.3B model to generate a high-quality, structurally faithful draft. A zero-shot LLM (Llama-3.3 or Qwen3) then polishes this draft, a process that can be further enhanced by augmenting the context with retrieved out-context examples (RAG). We demonstrate the robustness of this approach on two distinct benchmarks: a standard in-domain test set (Rosenthal, 2023) and a new, challenging out-of-domain (OOD) set of 12th-century Latin letters (2025). Our central finding is that this open-source RAG system achieves performance statistically comparable to the GPT-5 baseline, without any task-specific LLM fine-tuning. We release the pipeline, the Chartres OOD set, and evaluation scripts and models to facilitate replicability and further research.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。