LLM assistance changes how data visualization designs evolve over years
Design Reflections on Transition to LLM-Aided Novel Visualizations
Human-Computer Interaction
Summary
Creating data visualizations can be complicated and time-consuming. The authors studied how designing these visualizations changed over more than a decade, especially after Large Language Models (LLMs) became available. They found that LLMs helped designers by reducing the time spent coding, opening up new creative possibilities, and changing how designers approach their work. The study shows how these AI tools influence the process and experience of design over time.
What this means in practice
- •For data visualization designers: Develop visualization designs faster by integrating LLMs to reduce coding time and generate creative design options.
- •For ux design teams: Use LLMs to explore new user interface concepts inspired by AI-driven design space exploration for improved user engagement.
Tested on one dataset.
Authors
Richard Brath
Abstract
This study examines data visualization design evolution over 12.5 years, reflecting on the impact of Large Language Models over the last 3.75 years. Using a longitudinal corpus of 55 visualizations from a single-subject design record, the study identifies how LLMs have aided design-space exploration: reducing coding effort, enabling new design opportunities, shock, excitement, accomplishments, and shifts to the design process.