LLM Digest
Subscribe

Story

arxiv_cs_cl · Nov 13, 2026 · paper

Source brief

Contagious Fingerprints: When LLMs Inherit Another Model's Identity

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

Continue reading

Read the original at arxiv.org →Open in live feedRead that day’s brief

Earlier in this thread 4 items