自动化Iconclass：LLM和RAG用于大规模宗教木刻版画分类
Automating Iconclass: LLMs and RAG for Large-Scale Classification of Religious Woodcuts
AI总结：
本文提出利用LLM和向量数据库结合RAG技术，实现早期现代宗教图像的高效分类，通过全页上下文生成描述并匹配Iconclass代码，提升分类精度至92%。
摘要：
本文提出了一种新颖的方法，利用大型语言模型（LLMs）和向量数据库结合检索增强生成（RAG）技术，对早期现代宗教图像进行分类。该方法利用 Holy Roman Empire 的书籍插图全页上下文，使 LLM 生成包含视觉和文本元素的详细描述，并通过混合向量搜索匹配相关 Iconclass 代码。该方法在五级和四级分类中分别达到 87% 和 92% 的精度，显著优于传统图像和关键词搜索。通过使用全页描述和 RAG，系统提高了分类准确性，为大规模分析早期现代视觉档案提供强大工具。这种跨学科方法展示了 LLM 和 RAG 在艺术史和数字人文领域研究中的巨大潜力。
英文摘要：
This paper presents a novel methodology for classifying early modern religious images by using Large Language Models (LLMs) and vector databases in combination with Retrieval-Augmented Generation (RAG). The approach leverages the full-page context of book illustrations from the Holy Roman Empire, allowing the LLM to generate detailed descriptions that incorporate both visual and textual elements. These descriptions are then matched to relevant Iconclass codes through a hybrid vector search. This method achieves 87% and 92% precision at five and four levels of classification, significantly outperforming traditional image and keyword-based searches. By employing full-page descriptions and RAG, the system enhances classification accuracy, offering a powerful tool for large-scale analysis of early modern visual archives. This interdisciplinary approach demonstrates the growing potential of LLMs and RAG in advancing research within art history and digital humanities.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
