VisCanvas: A Node-based Interface for Exploratory Visualization Authoring with LLMs

2026-07-23

AI Summary

This work addresses the limitations of current chat-based visualization tools in supporting nonlinear exploratory data analysis. To overcome this, the authors propose and implement VisCanvas—the first interactive system that integrates large language models (LLMs) with a node-based graphical interface, enabling users to create, modify, branch, and merge visualizations through natural language to pursue multiple analytical paths. This study pioneers the incorporation of node-based interfaces into LLM-driven visualization authoring and articulates a set of design principles for AI-augmented visualization. User studies demonstrate that VisCanvas significantly enhances the diversity of data interactions and exploration efficiency while maintaining cognitive load and usability comparable to conventional chat-based interfaces.

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, 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/overview?view_only=98e94f52985c4cc2ad32209db8772058.

Problem

• exploratory visualization
• visualization authoring
• large language models
• node-based interface
• visual data analysis

Innovation

• node-based interface
• exploratory visualization
• large language models
• visualization authoring
• non-linear workflow