@inproceedings{wu-etal-2026-detecting,
    title = "Detecting {L}atin in Historical Books with Large Language Models: A Multimodal Benchmark",
    author = {Wu, Yu  and
      Shu, Ke  and
      Fischer, Jonas  and
      Pivovarova, Lidia  and
      Rosson, David  and
      M{\"a}kel{\"a}, Eetu  and
      Tolonen, Mikko},
    editor = "Demberg, Vera  and
      Inui, Kentaro  and
      Marquez, Llu{\'i}s",
    booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-eacl/2026.eacl-long.245/",
    pages = "5305--5328",
    ISBN = "979-8-89176-380-7",
    abstract = "This paper presents a novel task of extracting low-resourced and noisy Latin fragments from mixed-language historical documents with varied layouts.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."
}