"Don't Teach Minerva": Guiding LLMs Through Complex Syntax for Faithful Latin Translation with RAG

• URL: http://arxiv.org/abs/2511.01454v1
• Date: Mon, 03 Nov 2025 11:11:27 GMT
• Title: "Don't Teach Minerva": Guiding LLMs Through Complex Syntax for Faithful Latin Translation with RAG
• Authors: Sergio Torres Aguilar,
• Abstract summary: This paper introduces a reproducible draft-based refinement pipeline that elevates open-source Large Language Models to a performance level statistically comparable to top-tier proprietary systems.<n>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)
• Score: 0.5076419064097734
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• RAVEL: Reasoning Agents for Validating and Evaluating LLM Text Synthesis [78.32151470154422]
  We introduce RAVEL, an agentic framework that enables the testers to autonomously plan and execute typical synthesis operations.<n>We present C3EBench, a benchmark comprising 1,258 samples derived from professional human writings.<n>By augmenting RAVEL with SOTA LLMs as operators, we find that such agentic text synthesis is dominated by the LLM's reasoning capability.
  arXiv  Detail & Related papers  (2026-02-28T14:47:34Z)
• Recovered in Translation: Efficient Pipeline for Automated Translation of Benchmarks and Datasets [2.0199251985015434]
  We present a fully automated framework designed to enable scalable, high-quality translation of datasets and benchmarks.<n>We apply this approach to translate popular benchmarks and datasets into eight Eastern and Southern European languages.
  arXiv  Detail & Related papers  (2026-02-25T18:58:25Z)
• InvertiTune: High-Quality Data Synthesis for Cost-Effective Single-Shot Text-to-Knowledge Graph Generation [22.34499569359914]
  InvertiTune is a framework that combines a controlled data generation pipeline with supervised fine-tuning.<n>We show that InvertiTune outperforms larger non-fine-tuned LLMs as well as state-of-the-art Text2KG approaches.
  arXiv  Detail & Related papers  (2025-12-02T19:51:28Z)
• InstructLR: A Scalable Approach to Create Instruction Dataset for Under-Resourced Languages [5.046479786355341]
  In this paper, we introduce InstructLR, a novel framework designed to generate high-quality instruction datasets for low-resource languages (LRLs)<n>Our approach integrates LLM-driven text generation with a dual-layer quality filtering mechanism.<n>InstructLR has facilitated the creation of three multi-domain instruction benchmarks: ZarmaInstruct-50k, BambaraInstruct-50k, and FulfuldeInstruct-50k.
  arXiv  Detail & Related papers  (2025-12-01T21:25:33Z)
• LLM-guided Hierarchical Retrieval [54.73080745446999]
  LATTICE is a hierarchical retrieval framework that enables an LLM to reason over and navigate large corpora with logarithmic search complexity.<n>A central challenge in such LLM-guided search is that the model's relevance judgments are noisy, context-dependent, and unaware of the hierarchy.<n>Our framework achieves state-of-the-art zero-shot performance on the reasoning-intensive BRIGHT benchmark.
  arXiv  Detail & Related papers  (2025-10-15T07:05:17Z)
• LLaSO: A Foundational Framework for Reproducible Research in Large Language and Speech Model [9.857195650438966]
  We introduce LLaSO, the first fully open, end-to-end framework for large-scale speech-language modeling.<n>LLaSO provides the community with three essential resources: LLaSO-Align, a 12M-instance speech-text alignment corpus; LLaSO-Instruct, a 13.5M-instance multi-task instruction-tuning dataset; and LLaSO-Eval, a reproducible benchmark for standardized evaluation.<n>By releasing the complete stack of data, benchmarks, and models, LLaSO establishes a foundational open standard to unify research efforts and accelerate community-driven progress in LS
  arXiv  Detail & Related papers  (2025-08-21T10:20:00Z)
• SLRTP2025 Sign Language Production Challenge: Methodology, Results, and Future Work [87.9341538630949]
  The first Sign Language Production Challenge was held as part of the third SLRTP Workshop at CVPR 2025.<n>The competition's aims are to evaluate architectures that translate from spoken language sentences to a sequence of skeleton poses.<n>This paper presents the challenge design and the winning methodologies.
  arXiv  Detail & Related papers  (2025-08-09T11:57:33Z)
• RustRepoTrans: Repository-level Code Translation Benchmark Targeting Rust [50.65321080814249]
  RustRepoTrans is the first repository-level context code translation benchmark targeting incremental translation.<n>We evaluate seven representative LLMs, analyzing their errors to assess limitations in complex translation scenarios.
  arXiv  Detail & Related papers  (2024-11-21T10:00:52Z)
• Unleashing the Power of Large Language Models in Zero-shot Relation Extraction via Self-Prompting [21.04933334040135]
  We introduce the Self-Prompting framework, a novel method designed to fully harness the embedded RE knowledge within Large Language Models.<n>Our framework employs a three-stage diversity approach to prompt LLMs, generating multiple synthetic samples that encapsulate specific relations from scratch.<n> Experimental evaluations on benchmark datasets show our approach outperforms existing LLM-based zero-shot RE methods.
  arXiv  Detail & Related papers  (2024-10-02T01:12:54Z)
• Large Language Model-guided Document Selection [23.673690115025913]
  Large Language Model (LLM) pre-training exhausts an ever growing compute budget. Recent research has demonstrated that careful document selection enables comparable model quality with only a fraction of the FLOPs. We explore a promising direction for scalable general-domain document selection.
  arXiv  Detail & Related papers  (2024-06-07T04:52:46Z)
• YAYI 2: Multilingual Open-Source Large Language Models [53.92832054643197]
  We propose YAYI 2, including both base and chat models, with 30 billion parameters. YAYI 2 is pre-trained from scratch on a multilingual corpus which contains 2.65 trillion tokens filtered by our pre-training data processing pipeline. The base model is aligned with human values through supervised fine-tuning with millions of instructions and reinforcement learning from human feedback.
  arXiv  Detail & Related papers  (2023-12-22T17:34:47Z)
• AlignedCoT: Prompting Large Language Models via Native-Speaking Demonstrations [52.43593893122206]
  Alignedcot is an in-context learning technique for invoking Large Language Models. It achieves consistent and correct step-wise prompts in zero-shot scenarios. We conduct experiments on mathematical reasoning and commonsense reasoning.
  arXiv  Detail & Related papers  (2023-11-22T17:24:21Z)
• A Paradigm Shift in Machine Translation: Boosting Translation Performance of Large Language Models [27.777372498182864]
  We propose a novel fine-tuning approach for Generative Large Language Models (LLMs) Our approach consists of two fine-tuning stages: initial fine-tuning on monolingual data followed by subsequent fine-tuning on a small set of high-quality parallel data. Based on LLaMA-2 as our underlying model, our results show that the model can achieve an average improvement of more than 12 BLEU and 12 COMET over its zero-shot performance.
  arXiv  Detail & Related papers  (2023-09-20T22:53:15Z)
• Text Classification via Large Language Models [63.1874290788797]
  We introduce Clue And Reasoning Prompting (CARP) to address complex linguistic phenomena involved in text classification. Remarkably, CARP yields new SOTA performances on 4 out of 5 widely-used text-classification benchmarks. More importantly, we find that CARP delivers impressive abilities on low-resource and domain-adaptation setups.
  arXiv  Detail & Related papers  (2023-05-15T06:24:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.