More Haste, Less Speed: Weaker Single-Layer Watermark Improves Distortion-Free Watermark Ensembles

The paper investigates watermarking for large language model outputs, noting that stronger single-layer watermarks reduce token entropy and weaken subsequent layers. It demonstrates that detectability is limited by entropy and that watermark ensembles monotonically lower entropy and the green‑list ratio. The authors propose using weaker single‑layer watermarks to maintain entropy, showing through theory and experiments that this approach improves both detectability and robustness compared to strong baselines.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

• llms