Saved in:
Bibliographic Details
Main Authors: Lee, Christopher J., Tran, Giorgio, Tabalba, Roderick, Leigh, Jason, Longman, Ryan
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2408.12726
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929471287721984
author Lee, Christopher J.
Tran, Giorgio
Tabalba, Roderick
Leigh, Jason
Longman, Ryan
author_facet Lee, Christopher J.
Tran, Giorgio
Tabalba, Roderick
Leigh, Jason
Longman, Ryan
contents This paper explores the intersection of data visualization and Large Language Models (LLMs). Driven by the need to make a broader range of data visualization types accessible for novice users, we present a guided LLM-based pipeline designed to transform data, guided by high-level user questions (referred to as macro-queries), into a diverse set of useful visualizations. This approach leverages various prompting techniques, fine-tuning inspired by Abela's Chart Taxonomy, and integrated SQL tool usage.
format Preprint
id arxiv_https___arxiv_org_abs_2408_12726
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Macro-Queries: An Exploration into Guided Chart Generation from High Level Prompts
Lee, Christopher J.
Tran, Giorgio
Tabalba, Roderick
Leigh, Jason
Longman, Ryan
Computation and Language
This paper explores the intersection of data visualization and Large Language Models (LLMs). Driven by the need to make a broader range of data visualization types accessible for novice users, we present a guided LLM-based pipeline designed to transform data, guided by high-level user questions (referred to as macro-queries), into a diverse set of useful visualizations. This approach leverages various prompting techniques, fine-tuning inspired by Abela's Chart Taxonomy, and integrated SQL tool usage.
title Macro-Queries: An Exploration into Guided Chart Generation from High Level Prompts
topic Computation and Language
url https://arxiv.org/abs/2408.12726