Invisible Ink, Visible Lies: How Production Watermarking Causes LLMs to Hallucinate

Excerpt

arXiv:2610.04860v1 Announce Type: cross Abstract: Text watermarking helps identify AI-generated content, but its effect on factual reliability remains underexplored. In this paper, we study watermarking hallucination: factual errors induced or amplified by watermarking even when the required evidence is present in the context and the unwatermarked model can answer correctly. Using a controlled retrieval-augmented generation setting, we compare unwatermarked and watermarked generations under the