{"ID":2846644,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.01454","arxiv_id":"2511.01454","title":"\"Don't Teach Minerva\": Guiding LLMs Through Complex Syntax for Faithful Latin Translation with RAG","abstract":"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.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2511.01454","url_pdf":"https://arxiv.org/pdf/2511.01454v1","authors":"[\"Sergio Torres Aguilar\"]","published":"2025-11-03T11:11:27Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.DL\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}