# Attention, Please! PixelSHAP Reveals What Vision-Language Models Actually Focus On

arXiv: https://arxiv.org/abs/2503.06670 · HTML: https://mlsanity.com/paper/2503.06670/

## Key facts

- Cited by 9 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 15 of its 22 references that are in the map.
- First posted on arXiv 9 Mar 2025.

## Placed in

- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)
- Mechanistic interpretability / [Interpreting vision and multimodal models](https://mlsanity.com/mechinterp/interpreting-vision-and-multimodal-models/)

## Builds on (most cited first, 15 of 15)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [RISE: Randomized Input Sampling for Explanation of Black-box Models](https://mlsanity.com/paper/1806.07421/) (2018)
- [Transformer Interpretability Beyond Attention Visualization](https://mlsanity.com/paper/2012.09838/) (2020)
- [Interpretable Explanations of Black Boxes by Meaningful Perturbation](https://mlsanity.com/paper/1704.03296/) (2017)
- [Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks](https://mlsanity.com/paper/1910.01279/) (2019)
- [Understanding Deep Networks via Extremal Perturbations and Smooth Masks](https://mlsanity.com/paper/1910.08485/) (2019)
- [FastSHAP: Real-Time Shapley Value Estimation](https://mlsanity.com/paper/2107.07436/) (2021)
- [XRAI: Better Attributions Through Regions](https://mlsanity.com/paper/1906.02825/) (2019)
- [TokenSHAP: Interpreting Large Language Models with Monte Carlo Shapley Value Estimation](https://mlsanity.com/paper/2407.10114/) (2024)

## Built on by (most cited first, 9 of 9)

- [MultiSHAP: A Shapley-Based Framework for Explaining Cross-Modal Interactions in Multimodal AI Models](https://mlsanity.com/paper/2508.00576/) (2025)
- [GLIMPSE: Holistic Cross-Modal Explainability for Large Vision-Language Models](https://mlsanity.com/paper/2506.18985/) (2025)
- [Towards Reliable and Interpretable Document Question Answering via VLMs](https://mlsanity.com/paper/2509.10129/) (2025)
- [llmSHAP: A Principled Approach to LLM Explainability](https://mlsanity.com/paper/2511.01311/) (2025)
- [Quantifying Modality Contributions via Disentangling Multimodal Representations](https://mlsanity.com/paper/2511.19470/) (2025)
- [A Video Is Not Worth a Thousand Words](https://mlsanity.com/paper/2510.23253/) (2025)
- [AgentSHAP: Interpreting LLM Agent Tool Importance with Monte Carlo Shapley Value Estimation](https://mlsanity.com/paper/2512.12597/) (2025)
- [TabSHAP](https://mlsanity.com/paper/2604.21120/) (2026)
- [GridVQA-X: A Framework for Evaluating Multimodal Explainability Methods](https://mlsanity.com/paper/2606.14740/) (2026)

## Abstract (arXiv)

Interpretability in Vision-Language Models (VLMs) is crucial for trust, debugging, and decision-making in high-stakes applications. We introduce PixelSHAP, a model-agnostic framework extending Shapley-based analysis to structured visual entities. Unlike previous methods focusing on text prompts, PixelSHAP applies to vision-based reasoning by systematically perturbing image objects and quantifying their influence on a VLM's response. PixelSHAP requires no model internals, operating solely on input-output pairs, making it compatible with open-source and commercial models. It supports diverse embedding-based similarity metrics and scales efficiently using optimization techniques inspired by Shapley-based methods. We validate PixelSHAP in autonomous driving, highlighting its ability to enhance interpretability. Key challenges include segmentation sensitivity and object occlusion. Our open-source implementation facilitates further research.