Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
February 17, 2024Open Access

MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualization

View Full Paper
Ask AI
Bookmark
Share

Authors

ZYZheng YangZZZihan ZhouSWShuo Wang

Discussion

Loading...

Member takes

Overview

Benchmark evaluation demonstrates improved scientific data visualization across diverse large language models, highlighting the utility of visual feedback mechanisms.

Key Points

  • Automated scientific data visualization performance improves across diverse large language models when guided by the model-agnostic MatPlotAgent agentic framework.
  • Across 100 human-verified test cases in the MatPlotBench benchmark, visual feedback and iterative debugging enabled substantial gains in code generation accuracy.
  • Assessment using the MatPlotBench framework and GPT-4V evaluation correlates strongly with human annotations, highlighting viable automated multi-modal LLM scoring.

Cite This Study

Yang et al. (2024) studied this question.

synapsesocial.com/papers/68e78cf2b6db6435876feb08https://doi.org/10.48550/arxiv.2402.11453
View Full Paper
Ask AI
Bookmark
Share