Does visualization help AI understand data?
This addresses the problem of enhancing AI data understanding for researchers and practitioners, though it is incremental as it builds on existing vision-language models.
The study investigated whether AI systems benefit from data visualizations by testing two commercial vision-language models on analysis tasks, finding that providing scatterplots with raw data improved description precision and accuracy, especially for complex datasets.
Charts and graphs help people analyze data, but can they also be useful to AI systems? To investigate this question, we perform a series of experiments with two commercial vision-language models: GPT 4.1 and Claude 3.5. Across three representative analysis tasks, the two systems describe synthetic datasets more precisely and accurately when raw data is accompanied by a scatterplot, especially as datasets grow in complexity. Comparison with two baselines -- providing a blank chart and a chart with mismatched data -- shows that the improved performance is due to the content of the charts. Our results are initial evidence that AI systems, like humans, can benefit from visualization.