可视化能提升AI对数据的理解，尤其在复杂数据场景下。
Does visualization help AI understand data?
- 用散点图辅助原始数据，提升AI分析精度
- 复杂数据下性能提升明显，比空白/错配图表更好
- 适合关注AI与可视化交互的研究者
图表和图形帮助人类分析数据，但对AI系统是否有用？我们通过两个商用视觉-语言模型（GPT-4.1 和 Claude 3.5）在三个典型分析任务上的实验发现，当原始数据搭配散点图时，AI对合成数据的描述更精确、准确，尤其在数据复杂度升高时表现更优。与提供空白图表或数据不匹配图表的基线对比表明，性能提升源于图表内容本身。结果初步证明，像人类一样，AI系统也能从可视化中获益。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。