1
Language models struggle with compartmentalization
大模型面对同一概念的不同语言或编码形式时，会表现出“分隔化”现象，揭示其泛化能力的缺陷。
arXiv:2605.19284v1 Announce Type: cross Abstract: In the training data used by large language models (LLMs), the same latent concept is often presente…