Exploring Multimodal Prompt for Visualization Authoring with Large Language Models
Quick summary
arXiv:2504.13700v2 Announce Type: replace-cross Abstract: Recent advances in large language models (LLMs) have shown great potential in automating the process of visualization authoring through simple natural language utterances. However, instructing LLMs using natural language is limited in precision and expressiveness for conveying visualization intent, leading to misinterpretation and time-consuming iterations. To address these limitations, we conduct an empirical study to understand how LLMs interpret ambiguous or incomplete text prompts in the context of visualization authoring, and the c
Key takeaways
- arXiv:2504.13700v2 Announce Type: replace-cross Abstract: Recent advances in large language models (LLMs) have shown great potential in automating the process of visualization authoring through simple natural language utterances.
- However, instructing LLMs using natural language is limited in precision and expressiveness for conveying visualization intent, leading to misinterpretation and time-consuming iterations.
- To address these limitations, we conduct an empirical study to understand how LLMs interpret ambiguous or incomplete text prompts in the context of visualization authoring, and the c
Why it matters
“Exploring Multimodal Prompt for Visualization Authoring with Large Language Models” should be evaluated beyond branding and benchmark scores. Its practical importance will emerge in task accuracy, latency, unit cost, safety and integration with real workflows.
Member comments