Visualization Autocomplete: Visualization Authoring via Stepwise Design Recommendations

2026-07-17

AI Summary

This work addresses the challenge that domain experts, despite their ability to recognize high-quality visualizations, often struggle to determine effective design pathways due to a lack of efficient guidance. To bridge this gap, we propose the first approach that formulates visualization design as a sequential recommendation task, drawing inspiration from text auto-completion: at each design step, the system recommends the next action aligned with established visualization best practices, while allowing users to flexibly intervene or delegate batch generation. Our method integrates lightweight transformation functions distilled from large language models (LLMs), an interactive recommendation mechanism, and incremental chart state updates. This combination achieves usability comparable to LLM-based approaches while significantly outperforming baseline systems—including LLM vibecoding, Excel, and TaskVis—in expressive power for complex chart creation.

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.

Problem

• visualization design
• chart authoring
• design recommendation
• stepwise guidance
• visualization autocomplete

Innovation

• visualization autocomplete
• stepwise design recommendation
• chart authoring
• large language model distillation
• interactive visualization