{
 "id": "COMHIS/eacl26-detect-latin",
 "owner": "COMHIS",
 "name": "eacl26-detect-latin",
 "downloads": 1385,
 "likes": 0,
 "last_modified": "2026-10-05T06:30:48.000Z",
 "stated_licence": "cc-by-nc-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-classification",
  "token-classification",
  "object-detection"
 ],
 "citation": "@inproceedings{wu-etal-2026-detecting,\n  title = \"Detecting {L}atin in Historical Books with Large Language Models: A Multimodal Benchmark\",\n  author = {Wu, Yu and\n    Shu, Ke and\n    Fischer, Jonas and\n    Pivovarova, Lidia and\n    Rosson, David and\n    M{\\\"a}kel{\\\"a}, Eetu and\n    Tolonen, Mikko},\n  editor = \"Demberg, Vera and\n    Inui, Kentaro and\n    Marquez, Llu{\\'i}s\",\n  booktitle = \"Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)\",\n  month = mar,\n  year = \"2026\",\n  address = \"Rabat, Morocco\",\n  publisher = \"Association for Computational Linguistics\",\n  url = \"https://aclanthology.org/2026.eacl-long.245/\",\n  doi = \"10.18653/v1/2026.eacl-long.245\",\n  pages = \"5305--5328\",\n  ISBN = \"979-8-89176-380-7\",\n  abstract = \"This paper presents a novel task of extracting low-resourced and noisy Latin fragments from mixed-language historical documents with varied layouts.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.c",
 "signal": "restrictive",
 "reason": "The declared licence (cc-by-nc-4.0) is classified as having use restrictions.",
 "revision": "38f54bf4879efa7774ae70f0d491e35b1f8ea837",
 "stated_evidence": "https://huggingface.co/datasets/COMHIS/eacl26-detect-latin/blob/38f54bf4879efa7774ae70f0d491e35b1f8ea837/README.md",
 "file_evidence": "https://huggingface.co/datasets/COMHIS/eacl26-detect-latin/tree/38f54bf4879efa7774ae70f0d491e35b1f8ea837",
 "card_nc": false
}