Visualization Autocomplete: Visualization Authoring via Stepwise Design Recommendations
Human-Computer Interaction
Summary
The authors created VisAutocomplete, a tool that helps people design charts step-by-step by suggesting the best next action, similar to how text autocompletion works. Instead of users figuring out the whole design at once, the system offers choices at each stage, and users can accept or change them. They built this system to work quickly by simplifying a large language model’s decision process into a fast function. When compared to other tools like Excel and automated chart recommenders, VisAutocomplete made it easier to create complex charts while being just as user-friendly as chatting with a language model.
Authors
Hyeon Jeon, Sungbok Shin, Niklas Elmqvist
Abstract
When domain experts create charts, the bottleneck is rarely the data, but knowing the optimal next step in chart design. The visualization design space is vast, and while domain experts can recognize a good design when they see it, it is often challenging to determine the exact path to get there. To address this, we present VISAUTOCOMPLETE, a system inspired by text autocompletion that reconceptualizes visualization design as a sequential process, recommending concrete next steps at each stage of the authoring process based on common practices. Users can intervene at any step, or delegate multiple steps to the system and select one from the design recommendations. To support responsive interaction, we distill the translation logic of a large language model (LLM) into a single function that receives the current chart state and recommended transition as input and returns the updated chart specification as output. We evaluate the system against a LLM vibecoding, Microsoft Excel, and TaskVis, an automated chart recommendation engine, on chart quality and approachability. Our results show that VisAutocomplete outperforms all baselines in the articulacy of complex chart authoring, while remaining on par with LLM in approachability.