GPT-5.5基于图像的视觉化读取的史蒂文斯幂律检验
A Stevens's Power Law Check-up of GPT-5.5's Implicit Reading of Visual Encoding
浏览论文内容
中文总结 AI 辅助
本研究将史蒂文斯幂律应用于衡量AI模型读取视觉化的内在能力,通过无图例的参考估计方法评估十二种视觉变量,使算法模型的视觉编码读取可测量、可比较且可解释。
中文摘要 AI 辅助
我们将史蒂文斯幂律应用于衡量AI模型读取视觉化的内在能力,这可以揭示算法模型内置的感知机制。在我们的初步研究中,模型看不到图例。模型首先查看一个参考视觉表示并估计其量级,然后相对于该参考估计同一表示的每个后续图像的量级。我们对十二种视觉变量的评估使得算法模型如何读取视觉编码变得可测量、可与人类感知比较,并且对人类更可解释。
英文摘要
We adapt Stevens's power law to measure the implicit ability of AI models to read visualizations, which can reveal the built-in perceptual mechanisms of algorithmic models. In our pilot study, AIs see no legend. In the color conditions, no colormap name is provided either. GPT-5.5 first views a reference visual representation and estimates its magnitude, then estimates the magnitude of each subsequent image of the same representation relative to that reference. Our evaluation of twelve visual variables makes how algorithmic models read visual encodings measurable, comparable with human perception, and more transparent to humans.
发表机构
- The Ohio State University(俄亥俄州立大学)
机构由 AI 辅助整理,请以论文原文为准。