用机器学习复刻人类策展，小模型也能达到大模型效果
Curating art exhibitions using machine learning
- 构建四个基于机器学习的策展模型，模仿人类专家决策
- 三款模型能以显著高于随机水平的准确率复现展览布局
- 小模型通过精心设计可媲美大型语言模型，无需海量参数
本文提出四个相互关联的机器学习模型，旨在从人类专家策展的展览中学习规律，以实现类似策展工作。在四个模型中，三个展现出对各类策展风格的合理模仿能力，具备不同程度的准确性和策展一致性。关键发现有两点：其一，现有展览中蕴含足够信息，可训练出远超随机选择精度的策展模型；其二，通过特征工程与合理架构设计，小型模型性能几乎可媲美采用暴力策略的大语言模型（如GPT）。
原文摘要 · Abstract (English)
Here we present a series of artificial models - a total of four related models - based on machine learning techniques that attempt to learn from existing exhibitions which have been curated by human experts, in order to be able to do similar curatorship work. Out of our four artificial intelligence models, three achieve a reasonable ability at imitating these various curators responsible for all those exhibitions, with various degrees of precision and curatorial coherence. In particular, we can conclude two key insights: first, that there is sufficient information in these exhibitions to construct an artificial intelligence model that replicates past exhibitions with an accuracy well above random choices; and second, that using feature engineering and carefully designing the architecture of modest size models can make them almost as good as those using the so-called large language models such as GPT in a brute force approach.
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。