Recently, it has been recognized that large language models demonstrate high
performance on various intellectual tasks. However, few studies have
investigated alignment with humans in behaviors that involve sensibility, such
as aesthetic evaluation. This study investigates the performance of GPT-4 with
Vision, a state-of-the-art language model that can handle image input, on the
task of aesthetic evaluation of images. We employ two tasks, prediction of the
average evaluation values of a group and an individual's evaluation values. We
investigate the performance of GPT-4 with Vision by exploring prompts and
analyzing prediction behaviors. Experimental results reveal GPT-4 with Vision's
superior performance in predicting aesthetic evaluations and the nature of
different responses to beauty and ugliness. Finally, we discuss developing an
AI system for aesthetic evaluation based on scientific knowledge of the human
perception of beauty, employing agent technologies that integrate traditional
deep learning models with large language models.

最近，研究发现大型语言模型在各种智力任务中表现出色，然而，很少有研究探讨其与人类行为对齐，特别是涉及审美评价的行为。本研究调查了可以处理图像输入的先进语言模型 GPT-4 with Vision 在图像的审美评价任务上的表现。我们采用了两个任务，一个是预测一个群体的平均评价值，另一个是预测个体的评价值。通过探索提示和分析预测行为，我们调查了 GPT-4 with Vision 的表现。实验结果显示，GPT-4 with Vision 在预测审美评价方面表现出优秀的性能，并展现出对美和丑之间不同响应的特性。最后，我们讨论了基于人类对美感知的科学知识以及融合传统深度学习模型和大型语言模型的代理技术来开发用于审美评价的 AI 系统。