nvBench 2.0: Resolving Ambiguity in Text-to-Visualization through Stepwise Reasoning

Understand

Text-to-Visualization (Text2VIS) enables users to create visualizations from natural language queries, making data insights more accessible.

• However, Text2VIS faces challenges in interpreting ambiguous queries, as users often express their visualization needs in imprecise language.
• To address this challenge, we introduce nBench 2.0, a new benchmark designed to evaluate Text2VIS systems in scenarios involving ambiguous queries.
• nvBench 2.0 includes 7,878 natural language queries and 24,076 corresponding visualizations, derived from 780 tables across 153 domains.