BriefGPT.xyz
Oct, 2023
基础模型的嵌入表示或许能够检测分布偏移
Foundation Model's Embedded Representations May Detect Distribution Shift
HTML
PDF
Adam Tsou, Max Vargas, Andrew Engel, Tony Chiang
TL;DR
通过在预训练的GPT-2模型上进行情感分类的迁移学习案例研究，我们发现训练集和测试集之间的分布变化使我们无法准确了解神经网络模型的泛化能力。
Abstract
distribution shifts
between
train and test datasets
obscure our ability to understand the
generalization capacity
of
→