Text2Vis is a diverse 1,985-sample benchmark for text-to-visualization with complex queries, and a cross-modal actor-critic agent improves GPT-4o's pass rate from 26% to 42%.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Text2Vis: A Challenging and Diverse Benchmark for Generating Multimodal Visualizations from Text
Text2Vis is a diverse 1,985-sample benchmark for text-to-visualization with complex queries, and a cross-modal actor-critic agent improves GPT-4o's pass rate from 26% to 42%.