Linear Ensembles Can Erase LLM Watermarks

Watermarking schemes that embed distributional perturbations into LLM outputs are effectively broken by linear ensembles of a few independently trained models. The intuition behind most provenance tools is that a tiny bias introduced at generation time survives any downstream processing, making it detectable by a statistical test. In practice, that assumption collapses as soon as an application draws from more than one provider. The result is a hidden amplifier for hallucination‑free text that s...