ChatVis: Automating Scientific Visualization with a Large Language Model

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mallick, Tanwi, Yildiz, Orcun, Lenz, David, Peterka, Tom
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914974128930816
author Mallick, Tanwi
Yildiz, Orcun
Lenz, David
Peterka, Tom
author_facet Mallick, Tanwi
Yildiz, Orcun
Lenz, David
Peterka, Tom
contents 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/.
format Preprint
id arxiv_https___arxiv_org_abs_2410_11863
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ChatVis: Automating Scientific Visualization with a Large Language Model
Mallick, Tanwi
Yildiz, Orcun
Lenz, David
Peterka, Tom
Human-Computer Interaction
Artificial Intelligence
Computation and Language
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/.
title ChatVis: Automating Scientific Visualization with a Large Language Model
topic Human-Computer Interaction
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2410.11863