# Automated Visualization Makeovers with LLMs

arXiv: https://arxiv.org/abs/2508.05637 · HTML: https://mlsanity.com/paper/2508.05637/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 18 references that are in the map.
- First posted on arXiv 21 Jul 2025.

## Builds on (most cited first, 10 of 10)

- [LIDA: A Tool for Automatic Generation of Grammar-Agnostic Visualizations and Infographics using Large Language Models](https://mlsanity.com/paper/2303.02927/) (2023)
- [Towards Natural Language Interfaces for Data Visualization: A Survey](https://mlsanity.com/paper/2109.03506/) (2021)
- [VisEval: A Benchmark for Data Visualization in the Era of Large Language Models](https://mlsanity.com/paper/2407.00981/) (2024)
- [How Good (Or Bad) Are LLMs at Detecting Misleading Visualizations?](https://mlsanity.com/paper/2407.17291/) (2024)
- [VizLinter: A Linter and Fixer Framework for Data Visualization](https://mlsanity.com/paper/2108.10299/) (2021)
- [How Good is ChatGPT in Giving Advice on Your Visualization Design?](https://mlsanity.com/paper/2310.09617/) (2023)
- [Misinformed by Visualization: What Do We Learn From Misinformative Visualizations?](https://mlsanity.com/paper/2204.09548/) (2022)
- [Challenges and Opportunities in Data Visualization Education: A Call to Action](https://mlsanity.com/paper/2308.07703/) (2023)
- [Using Large Language Models to Generate Engaging Captions for Data Visualizations](https://mlsanity.com/paper/2212.14047/) (2022)
- [Why Change My Design: Explaining Poorly Constructed Visualization Designs with Explorable Explanations](https://mlsanity.com/paper/2309.01445/) (2023)

## Abstract (arXiv)

Making a good graphic that accurately and efficiently conveys the desired message to the audience is both an art and a science, typically not taught in the data science curriculum. Visualisation makeovers are exercises where the community exchange feedback to improve charts and data visualizations. Can multi-modal large language models (LLMs) emulate this task? Given a plot in the form of an image file, or the code used to generate it, an LLM, primed with a list of visualization best practices, is employed to semi-automatically generate constructive criticism to produce a better plot. Our system is centred around prompt engineering of a pre-trained model, relying on a combination of userspecified guidelines and any latent knowledge of data visualization practices that might lie within an LLMs training corpus. Unlike other works, the focus is not on generating valid visualization scripts from raw data or prompts, but on educating the user how to improve their existing data visualizations according to an interpretation of best practices. A quantitative evaluation is performed to measure the sensitivity of the LLM agent to various plotting issues across different chart types. We make the tool available as a simple self-hosted applet with an accessible Web interface.