# On the Explainability of Vision-Language Models in Art History

arXiv: https://arxiv.org/abs/2602.20853 · HTML: https://mlsanity.com/paper/2602.20853/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 22 of its 35 references that are in the map.
- First posted on arXiv 24 Feb 2026.

## Placed in

- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)

## Builds on (most cited first, 22 of 22)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs](https://mlsanity.com/paper/2111.02114/) (2021)
- [Explanation in Artificial Intelligence: Insights from the Social Sciences](https://mlsanity.com/paper/1706.07269/) (2017)
- [Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks](https://mlsanity.com/paper/1710.11063/) (2017)
- [Attention is not Explanation](https://mlsanity.com/paper/1902.10186/) (2019)
- [Quantifying Attention Flow in Transformers](https://mlsanity.com/paper/2005.00928/) (2020)
- [Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks](https://mlsanity.com/paper/1910.01279/) (2019)
- [LiT: Zero-Shot Transfer with Locked-image text Tuning](https://mlsanity.com/paper/2111.07991/) (2021)
- [CLIP-Dissect: Automatic Description of Neuron Representations in Deep Vision Networks](https://mlsanity.com/paper/2204.10965/) (2022)
- [Explainable AI (XAI): A Systematic Meta-Survey of Current Challenges and Future Opportunities](https://mlsanity.com/paper/2111.06420/) (2021)
- [Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)](https://mlsanity.com/paper/2402.10376/) (2024)
- [Evaluating Weakly Supervised Object Localization Methods Right](https://mlsanity.com/paper/2001.07437/) (2020)
- [A Closer Look at the Explainability of Contrastive Language-Image Pre-training](https://mlsanity.com/paper/2304.05653/) (2023)
- [LeGrad: An Explainability Method for Vision Transformers via Feature Formation Sensitivity](https://mlsanity.com/paper/2404.03214/) (2024)
- [Weakly Supervised Object Detection in Artworks](https://mlsanity.com/paper/1810.02569/) (2018)
- [A Data Set and a Convolutional Model for Iconography Classification in Paintings](https://mlsanity.com/paper/2010.11697/) (2020)
- [CLIP-QDA: An Explainable Concept Bottleneck Model](https://mlsanity.com/paper/2312.00110/) (2023)
- [DEArt: Dataset of European Art](https://mlsanity.com/paper/2211.01226/) (2022)
- [iART: A Search Engine for Art-Historical Images to Support Research in the Humanities](https://mlsanity.com/paper/2108.01542/) (2021)
- [Poses of People in Art: A Data Set for Human Pose Estimation in Digital Art History](https://mlsanity.com/paper/2301.05124/) (2023)

## Built on by (most cited first, 2 of 2)

- [Understanding How MLLMs Describe Artworks Using Token Activation Maps](https://mlsanity.com/paper/2606.27947/) (2026)
- [ArtMine: Discovering and Formalizing Artistic Processes](https://mlsanity.com/paper/2607.08331/) (2026)

## Abstract (arXiv)

Vision-Language Models (VLMs) transfer visual and textual data into a shared embedding space. In so doing, they enable a wide range of multimodal tasks, while also raising critical questions about the nature of machine 'understanding.' In this paper, we examine how Explainable Artificial Intelligence (XAI) methods can render the visual reasoning of a VLM - namely, CLIP - legible in art-historical contexts. To this end, we evaluate seven methods, combining zero-shot localization experiments with human interpretability studies. Our results indicate that, while these methods capture some aspects of human interpretation, their effectiveness hinges on the conceptual stability and representational availability of the examined categories.