# Attention-Guided Saliency Maps for Interpreting Visualization Literacy in VLMs

arXiv: https://arxiv.org/abs/2607.16105 · HTML: https://mlsanity.com/paper/2607.16105/

## Key facts

- No citing papers in the map yet (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 26 references that are in the map.
- First posted on arXiv 17 Jul 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)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [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)
- [ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning](https://mlsanity.com/paper/2203.10244/) (2022)
- [RISE: Randomized Input Sampling for Explanation of Black-box Models](https://mlsanity.com/paper/1806.07421/) (2018)
- [Quantifying Attention Flow in Transformers](https://mlsanity.com/paper/2005.00928/) (2020)
- [Transformer Interpretability Beyond Attention Visualization](https://mlsanity.com/paper/2012.09838/) (2020)
- [PlotQA: Reasoning over Scientific Plots](https://mlsanity.com/paper/1909.00997/) (2019)
- [ChartLlama: A Multimodal LLM for Chart Understanding and Generation](https://mlsanity.com/paper/2311.16483/) (2023)
- [VisText: A Benchmark for Semantically Rich Chart Captioning](https://mlsanity.com/paper/2307.05356/) (2023)
- [ChartGemma: Visual Instruction-tuning for Chart Reasoning in the Wild](https://mlsanity.com/paper/2407.04172/) (2024)
- [Beyond Question-Based Biases: Assessing Multimodal Shortcut Learning in Visual Question Answering](https://mlsanity.com/paper/2104.03149/) (2021)
- [How Good (Or Bad) Are LLMs at Detecting Misleading Visualizations?](https://mlsanity.com/paper/2407.17291/) (2024)
- [Attention Guided CAM: Visual Explanations of Vision Transformer Guided by Self-Attention](https://mlsanity.com/paper/2402.04563/) (2024)
- [Mini-VLAT: A Short and Effective Measure of Visualization Literacy](https://mlsanity.com/paper/2304.07905/) (2023)
- [Saliency Cards: A Framework to Characterize and Compare Saliency Methods](https://mlsanity.com/paper/2206.02958/) (2022)
- [Probing the Visualization Literacy of Vision Language Models: the Good, the Bad, and the Ugly](https://mlsanity.com/paper/2504.05445/) (2025)
- [Chart Question Answering from Real-World Analytical Narratives](https://mlsanity.com/paper/2507.01627/) (2025)
- [ChartGaze: Enhancing Chart Understanding in LVLMs with Eye-Tracking Guided Attention Refinement](https://mlsanity.com/paper/2509.13282/) (2025)
- [Capturing Visualization Design Rationale](https://mlsanity.com/paper/2506.16571/) (2025)

## Abstract (arXiv)

Understanding how vision-language models (VLMs) interpret data visualizations remains an open problem, and is increasingly important as these models are used for analytical tasks where reliable reasoning is essential. We introduce a lightweight, diagnostic saliency map method tailored for text generation over images using transformer models, the current state-of-the-art models in visualization interpretation. Our approach aggregates the language model's attention over the visual tokens across all heads and layers, then maps this attention back onto the vision encoder's patch grid to localise it over the image, producing a direct correspondence between each generated answer token and the image regions it attended to. This yields fast, gradient-free saliency maps that expose how VLMs allocate focus across visual elements during answer generation, enabling inspection of whether model attention aligns with semantically relevant components. We evaluate our approach using a deletion metric which validates the causal faithfulness of our saliency maps to the model's behavior.