On the Persistent Effects of Lexicality in Large Language Mod 事件

On the Persistent Effects of Lexicality in Large Language Mod arXiv:2606.02750v1 Announce Type: new Abstract: Representations extracted from large language models (LLMs) play an important role in many downstream applications. However, the structure of these representations is often influenced by lexical overlap rather than semantic content. Our understanding of the relationship between this lexical influence and semantic content, and its implications for downstream tasks, remains limited. In th