Refined Detection for Gumbel Watermarking
Not on the map. Why?
Abstract (arXiv)
We propose a simple detection mechanism for the Gumbel watermarking scheme proposed by Aaronson (2022). The new mechanism is proven to be near-optimal in a problem-dependent sense among all model-agnostic watermarking schemes under the assumption that the next-token distribution is sampled i.i.d.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 14 of its 23 references that are in the map. First posted on arXiv 31 Mar 2026.
Builds on
14 of 23 references.
References · 14
- 2023A Watermark for Large Language Modelscited by 667
- 2023Robust Distortion-free Watermarks for Language Modelscited by 279
- 2023Undetectable Watermarks for Language Modelscited by 208
- 2023A Survey of Text Watermarking in the Era of Large Language Modelscited by 102
- 2023Three Bricks to Consolidate Watermarks for Large Language Modelscited by 80
- 2023Mark My Words: Analyzing and Evaluating Language Model Watermarkscited by 62
- 2023An Unforgeable Publicly Verifiable Watermark for Large Language Modelscited by 54
- 2024A Statistical Framework of Watermarks for Large Language Models: Pivot, Detection Efficiency and Optimal Rulescited by 53
- 2024Robust Detection of Watermarks for Large Language Models Under Human Editscited by 29
- 2023Towards Optimal Statistical Watermarkingcited by 25
- 2025An Overview of Large Language Models for Statisticianscited by 24
- 2025Optimized Couplings for Watermarking Large Language Modelscited by 9
2 more
Built on by
Citing papers per year: 2026: 2.
2 papers.