Averaging output distributions across 3-5 LLMs recovers the unwatermarked distribution, suppressing detection z-scores below threshold while improving quality.
No free lunch in LLM watermarking: Trade-offs in watermarking design choices.arXiv preprint arXiv:2402.16187
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
representative citing papers
LLM watermarking adoption is limited by misaligned stakeholder incentives; incentive-aligned approaches such as in-context watermarking can enable practical use in targeted domains like education and peer review.
citing papers explorer
-
Linear Ensembles Wash Away Watermarks: On the Fragility of Distributional Perturbations in LLMs
Averaging output distributions across 3-5 LLMs recovers the unwatermarked distribution, suppressing detection z-scores below threshold while improving quality.
-
Position: LLM Watermarking Should Align Stakeholders' Incentives for Practical Adoption
LLM watermarking adoption is limited by misaligned stakeholder incentives; incentive-aligned approaches such as in-context watermarking can enable practical use in targeted domains like education and peer review.