Detecting Latin in Historical Books with Large Language Models: A Multimodal Benchmark
This work addresses the challenge of language detection in historical documents for researchers and archivists, but it is incremental as it benchmarks existing models on a new task.
The paper tackled the problem of extracting Latin fragments from mixed-language historical documents with varied layouts, and found that reliable Latin detection with contemporary models is achievable, as demonstrated on a dataset of 724 annotated pages.
This paper presents a novel task of extracting Latin fragments from mixed-language historical documents with varied layouts.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 models is achievable. Our study provides the first comprehensive analysis of these models' capabilities and limits for this task.