Automated Visualization Makeovers with LLMs

TL;DR

This paper explores using multi-modal large language models to provide constructive feedback on data visualizations, aiming to improve existing charts by leveraging best practices through prompt engineering.

Contribution

It introduces a system that uses prompt engineering of pre-trained LLMs to critique and suggest improvements for visualizations based on best practices, differing from traditional visualization generation methods.

Findings

The LLM system can identify various plotting issues across chart types.

Quantitative evaluation shows sensitivity to visualization problems.

The tool is accessible via a self-hosted web app.

Abstract

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.