# Automating Iconclass: LLMs and RAG for Large-Scale Classification of Religious Woodcuts

arXiv: https://arxiv.org/abs/2510.19986 · HTML: https://mlsanity.com/paper/2510.19986/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 8 of its 22 references that are in the map.
- First posted on arXiv 22 Oct 2025.

## Placed in

- Retrieval-augmented generation / [Multimodal RAG](https://mlsanity.com/rag/multimodal-rag/)

## Builds on (most cited first, 8 of 8)

- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [Reproducible scaling laws for contrastive language-image learning](https://mlsanity.com/paper/2212.07143/) (2022)
- [A Data Set and a Convolutional Model for Iconography Classification in Paintings](https://mlsanity.com/paper/2010.11697/) (2020)
- [OmniArt: Multi-task Deep Learning for Artistic Data Analysis](https://mlsanity.com/paper/1708.00684/) (2017)
- [DEArt: Dataset of European Art](https://mlsanity.com/paper/2211.01226/) (2022)
- [SniffyArt: The Dataset of Smelling Persons](https://mlsanity.com/paper/2311.11888/) (2023)
- [Automatic Modeling of Social Concepts Evoked by Art Images as Multimodal Frames](https://mlsanity.com/paper/2110.07420/) (2021)
- [Multimodal Search on Iconclass using Vision-Language Pre-Trained Models](https://mlsanity.com/paper/2306.16529/) (2023)

## Built on by (most cited first, 1 of 1)

- [Large Language Models, Machine-Assisted Cultural Analytics, and the Agentic Turn](https://mlsanity.com/paper/2610.12792/) (2026)

## Abstract (arXiv)

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.