Author name: Xu Pan, Jingxuan Fan, Zidi Xiong, Ely Hahami, Jorin Overwiening, Ziqian Xie

arXiv:2508.15815v3 Announce Type: replace
Abstract: Modern large language models (LLMs) are typically trained and deployed using structured role tags (e.g. system, user, assistant, tool) that explicitly mark the source of each piece of context. While …