mlsanityData to 14 Oct 2026

Detecting Latin in Historical Books with Large Language Models: A Multimodal Benchmark

arXiv 2510.19585 ↗First posted 22 Oct 2025cs.CL cs.AI cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

This paper presents a novel task of extracting low-resourced and noisy Latin fragments from mixed-language historical documents with varied layouts.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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 16 of its 53 references that are in the map. First posted on arXiv 22 Oct 2025.

Builds on

16 of 53 references.

References · 16

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2020Scaling Laws for Neural Language Modelscited by 6,586
  3. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  4. 2023MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGIcited by 2,080
  5. 2025InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Modelscited by 1,834
  6. 2025Gemma 3 Technical Reportcited by 1,824
  7. 2024LayoutLLM: Layout Instruction Tuning with Large Language Models for Document Understandingcited by 95
  8. 2020LinCE: A Centralized Benchmark for Linguistic Code-switching Evaluationcited by 93
  9. 2021Document Collection Visual Question Answeringcited by 45
  10. 2018A Fast, Compact, Accurate Model for Language Identification of Codemixed Textcited by 11
  11. 2025OCR Error Post-Correction with LLMs in Historical Documents: No Free Lunchescited by 11
  12. 2024Sui Generis: Large Language Models for Authorship Attribution and Verification in Latincited by 9
4 more
  1. 2020UDPipe at EvaLatin 2020: Contextualized Embeddings and Treebank Embeddingscited by 6
  2. 2023LatinCy: Synthetic Trained Pipelines for Latin NLPcited by 5
  3. 2021Lexical semantic change for Ancient Greek and Latincited by 4
  4. 2023Reception Reader: Exploring Text Reuse in Early Modern British Publicationscited by 4

Built on by

Not cited yet.