ChatVis: Automating Scientific Visualization with a Large Language Model

TL;DR

ChatVis is an iterative LLM-based tool that automatically generates and refines Python scripts for data visualization, successfully handling errors and outperforming unassisted models in five canonical scenarios.

Contribution

This work introduces an iterative, error-correcting approach to automate scientific visualization script generation using a large language model.

Findings

ChatVis successfully generated correct scripts in all tested scenarios.

It outperformed other LLMs without assistance in accuracy.

The method effectively detects and corrects errors during script execution.

Abstract

We develop an iterative assistant we call ChatVis that can synthetically generate Python scripts for data analysis and visualization using a large language model (LLM). The assistant allows a user to specify the operations in natural language, attempting to generate a Python script for the desired operations, prompting the LLM to revise the script as needed until it executes correctly. The iterations include an error detection and correction mechanism that extracts error messages from the execution of the script and subsequently prompts LLM to correct the error. Our method demonstrates correct execution on five canonical visualization scenarios, comparing results with ground truth. We also compared our results with scripts generated by several other LLMs without any assistance. In every instance, ChatVis successfully generated the correct script, whereas the unassisted LLMs failed to do so. The code is available on GitHub: https://github.com/tanwimallick/ChatVis/.