Paper
Does AI See like Art Historians? Interpreting How Vision Language Models Recognize Artistic Style
Authors
Marvin Limpijankit, Milad Alshomary, Yassin Oulad Daoud, Amith Ananthram, Tim Trombley, Elias Stengel-Eskin, Mohit Bansal, Noam M. Elcott, Kathleen McKeown
Abstract
VLMs have become increasingly proficient at a range of computer vision tasks, such as visual question answering and object detection. This includes increasingly strong capabilities in the domain of art, from analyzing artwork to generation of art. In an interdisciplinary collaboration between computer scientists and art historians, we characterize the mechanisms underlying VLMs' ability to predict artistic style and assess the extent to which they align with the criteria art historians use to reason about artistic style. We employ a latent-space decomposition approach to identify concepts that drive art style prediction and conduct quantitative evaluations, causal analysis and assessment by art historians. Our findings indicate that 73% of the extracted concepts are judged by art historians to exhibit a coherent and semantically meaningful visual feature and 90% of concepts used to predict style of a given artwork were judged relevant. In cases where an irrelevant concept was used to successfully predict style, art historians identified possible reasons for its success; for example, the model might "understand" a concept in more formal terms, such as dark/light contrasts.
Metadata
Related papers
Gen-Searcher: Reinforcing Agentic Search for Image Generation
Kaituo Feng, Manyuan Zhang, Shuang Chen, Yunlong Lin, Kaixuan Fan, Yilei Jian... • 2026-03-30
On-the-fly Repulsion in the Contextual Space for Rich Diversity in Diffusion Transformers
Omer Dahary, Benaya Koren, Daniel Garibi, Daniel Cohen-Or • 2026-03-30
Graphilosophy: Graph-Based Digital Humanities Computing with The Four Books
Minh-Thu Do, Quynh-Chau Le-Tran, Duc-Duy Nguyen-Mai, Thien-Trang Nguyen, Khan... • 2026-03-30
ParaSpeechCLAP: A Dual-Encoder Speech-Text Model for Rich Stylistic Language-Audio Pretraining
Anuj Diwan, Eunsol Choi, David Harwath • 2026-03-30
RAD-AI: Rethinking Architecture Documentation for AI-Augmented Ecosystems
Oliver Aleksander Larsen, Mahyar T. Moghaddam • 2026-03-30
Raw Data (Debug)
{
"raw_xml": "<entry>\n <id>http://arxiv.org/abs/2603.11024v1</id>\n <title>Does AI See like Art Historians? Interpreting How Vision Language Models Recognize Artistic Style</title>\n <updated>2026-03-11T17:49:45Z</updated>\n <link href='https://arxiv.org/abs/2603.11024v1' rel='alternate' type='text/html'/>\n <link href='https://arxiv.org/pdf/2603.11024v1' rel='related' title='pdf' type='application/pdf'/>\n <summary>VLMs have become increasingly proficient at a range of computer vision tasks, such as visual question answering and object detection. This includes increasingly strong capabilities in the domain of art, from analyzing artwork to generation of art. In an interdisciplinary collaboration between computer scientists and art historians, we characterize the mechanisms underlying VLMs' ability to predict artistic style and assess the extent to which they align with the criteria art historians use to reason about artistic style. We employ a latent-space decomposition approach to identify concepts that drive art style prediction and conduct quantitative evaluations, causal analysis and assessment by art historians. Our findings indicate that 73% of the extracted concepts are judged by art historians to exhibit a coherent and semantically meaningful visual feature and 90% of concepts used to predict style of a given artwork were judged relevant. In cases where an irrelevant concept was used to successfully predict style, art historians identified possible reasons for its success; for example, the model might \"understand\" a concept in more formal terms, such as dark/light contrasts.</summary>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.CV'/>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n <published>2026-03-11T17:49:45Z</published>\n <arxiv:comment>12 pages, 12 figures</arxiv:comment>\n <arxiv:primary_category term='cs.CV'/>\n <author>\n <name>Marvin Limpijankit</name>\n </author>\n <author>\n <name>Milad Alshomary</name>\n </author>\n <author>\n <name>Yassin Oulad Daoud</name>\n </author>\n <author>\n <name>Amith Ananthram</name>\n </author>\n <author>\n <name>Tim Trombley</name>\n </author>\n <author>\n <name>Elias Stengel-Eskin</name>\n </author>\n <author>\n <name>Mohit Bansal</name>\n </author>\n <author>\n <name>Noam M. Elcott</name>\n </author>\n <author>\n <name>Kathleen McKeown</name>\n </author>\n </entry>"
}