1
A Pre-Training Analogue of Grokking in Language Models: Tracing Delayed Grammatical Generalization
语言模型预训练时竟出现类似“顿悟”的语法泛化延迟现象，揭示学习路径的意外转折。
arXiv:2606.00230v1 Announce Type: new Abstract: Grokking, the phenomenon in which neural networks generalize long after fitting their training data, h…