Data Formulator 2: Iterative Creation of Data Visualizations, with AI Transforming Data Along the Way
Chenglong Wang, Bongshin Lee, Steven Drucker, Dan Marshall, Jianfeng, Gao

TL;DR
Data Formulator 2 is an AI-powered visualization system that facilitates iterative data analysis by combining graphical interfaces and natural language, enabling efficient data transformations and visualization reuse.
Contribution
It introduces a novel system that supports iterative visualization creation through integrated GUI and natural language, addressing limitations of previous AI visualization tools.
Findings
Participants successfully developed their own iteration styles.
DF2 enabled efficient exploration of complex data visualizations.
User study demonstrated improved flexibility in data analysis.
Abstract
Data analysts often need to iterate between data transformations and chart designs to create rich visualizations for exploratory data analysis. Although many AI-powered systems have been introduced to reduce the effort of visualization authoring, existing systems are not well suited for iterative authoring. They typically require analysts to provide, in a single turn, a text-only prompt that fully describe a complex visualization. We introduce Data Formulator 2 (DF2 for short), an AI-powered visualization system designed to overcome this limitation. DF2 blends graphical user interfaces and natural language inputs to enable users to convey their intent more effectively, while delegating data transformation to AI. Furthermore, to support efficient iteration, DF2 lets users navigate their iteration history and reuse previous designs, eliminating the need to start from scratch each time. A…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsData Visualization and Analytics · Computational Physics and Python Applications
