
Existing text-to-visualization models exhibit inadequate robustness against input variations, and a novel Retrieval-Augmented Generation (RAG) framework called GRED is proposed to address this challenge.


coremsg

enhancing-robustness-of-text-to-visualization-translation-against-lexical-and-phrasal-variations


Enhancing Robustness of Text-to-Visualization Translation Against Lexical and Phrasal Variations


title_rewrite


While both text and voice instructions often cover the basic chart elements and element organization, voice descriptions exhibit a greater variety of command formats, element characteristics, and complex linguistic features compared to text instructions.


exploring-cross-modality-differences-in-natural-language-instructions-for-ai-assisted-chart-authoring


Exploring Cross-Modality Differences in Natural Language Instructions for AI-Assisted Chart Authoring
