DeepVIS: Bridging Natural Language and Data Visualization Through Step-wise Reasoning

TL;DR

DeepVIS introduces a step-wise reasoning approach to natural language to visualization, enhancing transparency, user interaction, and accuracy in automatic visualization generation.

Contribution

We integrate Chain-of-Thought reasoning into NL2VIS, develop a detailed reasoning dataset, and create an interactive interface for improved visualization generation and user understanding.

Findings

Enhanced visualization quality through CoT reasoning

Improved user understanding via reasoning inspection

Quantitative and user study validation of effectiveness

Abstract

Although data visualization is powerful for revealing patterns and communicating insights, creating effective visualizations requires familiarity with authoring tools and often disrupts the analysis flow. While large language models show promise for automatically converting analysis intent into visualizations, existing methods function as black boxes without transparent reasoning processes, which prevents users from understanding design rationales and refining suboptimal outputs. To bridge this gap, we propose integrating Chain-of-Thought (CoT) reasoning into the Natural Language to Visualization (NL2VIS) pipeline. First, we design a comprehensive CoT reasoning process for NL2VIS and develop an automatic pipeline to equip existing datasets with structured reasoning steps. Second, we introduce nvBench-CoT, a specialized dataset capturing detailed step-by-step reasoning from ambiguous natural language descriptions to finalized visualizations, which enables state-of-the-art performance when used for model fine-tuning. Third, we develop DeepVIS, an interactive visual interface that tightly integrates with the CoT reasoning process, allowing users to inspect reasoning steps, identify errors, and make targeted adjustments to improve visualization outcomes. Quantitative benchmark evaluations, two use cases, and a user study collectively demonstrate that our CoT framework effectively enhances NL2VIS quality while providing insightful reasoning steps to users.