Leveraging LLMs and attention-mechanism for automatic annotation of historical maps

Yunshuang Yuan, Monika Sester

Abstract: Articles | Volume 6 ArticleMetricsRelated articles Articles | Volume 6 https://doi.org/10.5194/agile-giss-6-52-2025 © Author(s) 2025. This work is distributed under the Creative Commons Attribution 4.0 License. https://doi.org/10.5194/agile-giss-6-52-2025 © Author(s) 2025. This work is distributed under the Creative Commons Attribution 4.0 License. Articles | Volume 6 ArticleMetricsRelated articles 09 Jun 2025 | 09 Jun 2025 Leveraging LLMs and attention-mechanism for automatic annotation of historical maps Yunshuang Yuan and Monika Sester Yunshuang Yuan × Institute of Cartography and Geoinformatics, Leibniz University Hannover, Germany Monika Sester × Institute of Cartography and Geoinformatics, Leibniz University Hannover, Germany Keywords: Historical maps, Annotation, Accessibility, Automatic Labelling, Deep Learning, LLM Abstract. Historical maps are essential resources that provide insights into the geographical landscapes of the past. They serve as valuable tools for researchers across disciplines such as history, geography, and urban studies, facilitating the reconstruction of historical environments and the analysis of spatial transformations over time. However, when constrained to analogue or scanned formats, their interpretation is limited to humans and therefore not scalable. Recent advancements in machine learning, particularly in computer vision and large language models (LLMs), have opened new avenues for automating the recognition and classification of features and objects in historical maps. In this paper, we propose a novel distillation method that leverages LLMs and attention mechanisms for the automatic annotation of historical maps. LLMs are employed to generate coarse classification labels for low-resolution historical image patches, while attention mechanisms are utilized to refine these labels to higher resolutions. Experimental results demonstrate that the refined labels achieve a high recall of more than 90%. Additionally, the intersection over union (IoU) scores—84.2% for Wood and 72.0% for Settlement— along with precision scores of 87.1% and 79.5%, respectively, indicate that most labels are well-aligned with ground-truth annotations. Notably, these results were achieved without the use of fine-grained manual labels during training, underscoring the potential of our approach for efficient and scalable historical map analysis. Download & links Article (PDF, 8514 KB) Download & links Article (8514 KB) Metadata XML BibTeX EndNote Share document.addEventListener("DOMContentLoaded", function () { const mobileShareElement = document.querySelector(".mobile-native-share"); if (navigator.share) { // Native sharing is available if (mobileShareElement) { mobileShareElement.style.display = "block"; } } else { // Native sharing is NOT available if (mobileShareElement) { mobileShareElement.style.display = "none"; } } }); How to cite. Yuan, Y. and Sester, M.: Leveraging LLMs and attention-mechanism for automatic annotation of historical maps, AGILE GIScience Ser., 6, 52, https://doi.org/10.5194/agile-giss-6-52-2025, 2025.

External IDs:dblp:conf/agile/YuanS25