# LITERA: An LLM Based Approach to Latin-to-English Translation

arXiv: https://arxiv.org/abs/2504.10660 · HTML: https://mlsanity.com/paper/2504.10660/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 26 references that are in the map.
- First posted on arXiv 14 Apr 2025.

## Builds on (most cited first, 5 of 5)

- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [BLEURT: Learning Robust Metrics for Text Generation](https://mlsanity.com/paper/2004.04696/) (2020)
- [Mixture-of-Agents Enhances Large Language Model Capabilities](https://mlsanity.com/paper/2406.04692/) (2024)
- [Learning Compact Metrics for MT](https://mlsanity.com/paper/2110.06341/) (2021)
- [On the Difficulty of Translating Free-Order Case-Marking Languages](https://mlsanity.com/paper/2107.06055/) (2021)

## Built on by (most cited first, 3 of 3)

- [Can We Triage LLM Translation Errors in Classical Texts Without Human References? Source Novelty, GEMBA Scoring, and Budgeted Review through Pali-to-English Translation](https://mlsanity.com/paper/2609.14963/) (2026)
- ["Don't Teach Minerva": Guiding LLMs Through Complex Syntax for Faithful Latin Translation with RAG](https://mlsanity.com/paper/2511.01454/) (2025)
- [When Simpler Is Better: Evaluating Translation Pipelines for Medieval Latin Manuscripts](https://mlsanity.com/paper/2607.03836/) (2026)

## Abstract (arXiv)

This paper introduces an LLM-based Latin-to-English translation platform designed to address the challenges of translating Latin texts. We named the model LITERA, which stands for Latin Interpretation and Translations into English for Research Assistance. Through a multi-layered translation process utilizing a fine-tuned version of GPT-4o-mini and GPT-4o, LITERA offers an unprecedented level of accuracy, showcased by greatly improved BLEU scores, particularly in classical Latin, along with improved BLEURT scores. The development of LITERA involved close collaboration with Duke University's Classical Studies Department, which was instrumental in creating a small, high-quality parallel Latin-English dataset. This paper details the architecture, fine-tuning methodology, and prompting strategies used in LITERA, emphasizing its ability to produce literal translations.