VisCanvas: A Node-Based Interface for Exploratory Visualization Authoring with LLMs
Authors
Yuki Ueno (Arizona State University), Bretho Danzy (Arizona State University), Zhuojun Jiang (Arizona State University), Chris Bryan (Arizona State University)
Presentation
- Session
- Modern talking-visually
- Time
- Tuesday, Nov 10, 14:00 – 14:12 (US/Eastern) · session 13:00 – 14:30
- Location
- Hall America center
Links
Sign in to access the preprint PDF.
Sign in- Download Supplemental Material
Keywords
Visualization Authoring, Large Language Models, Exploratory Analysis, Provenance
Abstract
Visual data analysis involves both open-ended exploration and targeted question answering. Visualization authoring tools support this process by enabling users to create visualizations for these tasks. With the rise of large language models (LLMs), substantial effort has been devoted to developing visualization authoring tools that use natural language instructions. However, existing systems are typically based on a linear chat interface, which is not well suited to exploratory visual analysis workflows. In this paper, we introduce VisCanvas, a node-based interface for exploratory visualization authoring with LLMs. VisCanvas allows users to create, revise, branch, and merge visualizations in a non-linear way, enabling more efficient exploration of multiple analytical directions. We conducted a user study with 20 participants to evaluate the effectiveness of VisCanvas compared to a baseline chat-based interface. The results show that VisCanvas facilitates more diverse data interaction while maintaining performance levels (i.e., cognitive load and usability) that are indistinguishable from current prevailing methods. We then distill design principles for future AI-assisted visualization authoring environments. All supplemental materials required to reproduce the study are available at https://osf.io/gsxhn.
For Practitioners
This paper is relevant to developers of AI-assisted visualization and data analysis tools, as well as data analysts and data scientists who use LLMs for exploratory analysis. Practitioners can apply our findings by representing intermediate visualizations as reusable, spatially organized artifacts rather than maintaining a purely linear chat history. Features such as branching, merging, on-demand suggestions, and semantic zoom can support parallel exploration, comparison, and revisitation without substantially increasing perceived workload. These findings provide practical guidance for designing human–AI authoring environments that support both open-ended exploration and focused analysis.