This paper presents a novel task of extracting low-resourced and noisy Latin fragments from mixed-language historical documents with varied layouts. We benchmark and evaluate the performance of large foundation models against a multimodal dataset of 724 annotated pages. The results demonstrate that reliable Latin detection with contemporary zero-shot models is achievable, yet these models lack a functional comprehension of Latin. This study establishes a comprehensive baseline for processing Latin within mixed-language corpora, supporting quantitative analysis in intellectual history and historical linguistics. Both the dataset and code are available at https://github.com/COMHIS/EACL26-detect-latin.
@article{arxiv.2510.19585,
title = {Detecting Latin in Historical Books with Large Language Models: A Multimodal Benchmark},
author = {Yu Wu and Ke Shu and Jonas Fischer and Lidia Pivovarova and David Rosson and Eetu Mäkelä and Mikko Tolonen},
journal= {arXiv preprint arXiv:2510.19585},
year = {2026}
}
Comments
Accepted by the EACL 2026 main conference. Code and data available at https://github.com/COMHIS/EACL26-detect-latin