ArtRAG: Retrieval-Augmented Generation with Structured Context for Visual Art Understanding

TL;DR

ArtRAG introduces a training-free framework that enhances multimodal language models with a structured knowledge graph and retrieval mechanism, enabling nuanced, culturally informed art explanations beyond simple object recognition.

Contribution

It presents a novel, training-free method combining structured knowledge graphs with retrieval-augmented generation for improved art understanding.

Findings

Outperforms baselines on SemArt and Artpedia datasets

Generates coherent and culturally enriched art descriptions

Human evaluations favor ArtRAG's interpretative quality

Abstract

Understanding visual art requires reasoning across multiple perspectives -- cultural, historical, and stylistic -- beyond mere object recognition. While recent multimodal large language models (MLLMs) perform well on general image captioning, they often fail to capture the nuanced interpretations that fine art demands. We propose ArtRAG, a novel, training-free framework that combines structured knowledge with retrieval-augmented generation (RAG) for multi-perspective artwork explanation. ArtRAG automatically constructs an Art Context Knowledge Graph (ACKG) from domain-specific textual sources, organizing entities such as artists, movements, themes, and historical events into a rich, interpretable graph. At inference time, a multi-granular structured retriever selects semantically and topologically relevant subgraphs to guide generation. This enables MLLMs to produce contextually grounded, culturally informed art descriptions. Experiments on the SemArt and Artpedia datasets show that ArtRAG outperforms several heavily trained baselines. Human evaluations further confirm that ArtRAG generates coherent, insightful, and culturally enriched interpretations.