Story
arxiv_cs_cl · Nov 13, 2026 · paper
arxiv.orgNov 13, 2026
original source linked
In brief
The fingerprint by which a classifier recognizes the LLM behind a text is usually treated as a fixed property of the model. We show that it is contagious: a model that continues a conversation begun by another model inherits that model's fingerprint. This undermines audits of API