Seismic advances in generative AI algorithms for imagery, text, and other data types has led to the temptation to use synthetic data to train next-generation models. Repeating this process creates an autophagous (self-consuming) loop whose properties are poorly understood. We conduct a thorough analytical and empirical analysis using state-of-the-art generative image models of three families of autophagous loops that differ in how fixed or fresh real training data is available through the generations of training and in whether the samples from previous generation models have been biased to trade off data quality versus diversity. Our primary conclusion across all scenarios is that without enough fresh real data in each generation of an autophagous loop, future generative models are doomed to have their quality (precision) or diversity (recall) progressively decrease. We term this condition Model Autophagy Disorder (MAD), making analogy to mad cow disease.

翻译：针对图像、文本及其他数据类型的生成式人工智能算法取得了突破性进展，这促使人们倾向于使用合成数据来训练下一代模型。重复这一过程会形成一个自吞噬（自食性）循环，其特性尚未得到充分理解。我们采用最先进的生成式图像模型，对三类自吞噬循环进行了深入的分析与实证研究。这些循环的区别在于：在逐代训练过程中，固定或全新的真实训练数据是否可用，以及前一代模型生成的样本是否在数据质量与多样性之间进行了权衡。我们的主要结论是：在所有场景中，若自吞噬循环的每一代缺乏足够的新鲜真实数据，未来的生成式模型将不可避免地出现质量（精确度）或多样性（召回率）的逐步下降。我们将此状况称为“模型自噬障碍”（Model Autophagy Disorder，MAD），类比于疯牛病。