Batorski et al.
Distortion-free multi-bit watermark adds certified decoding to language model outputs
CertMark embeds messages via Gumbel-max sampling seeds, preserving text quality while providing mathematical bounds on false recovery.
Academic
Paweł Batorski · Przemysław Spurek · Paul Swoboda
Heinrich Heine University Düsseldorf · Jagiellonian University · IDEAS Research Institute
Research Digest··2 min read
The authors introduce CertMark, a watermarking method for LLMs that embeds multi-bit messages without altering token probabilities.
Why this paper
From Heinrich Heine University Düsseldorf and 2 others · Released code
In one line
CertMark is a distortion-free multi-bit watermark that provides certified decoding with mathematical bounds on incorrect message probability.
What it released
Code
What we could check
- ✓Code link in the paper (github.com)
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ✓Limitations stated by the authors (2 noted)
- ·No benchmark numbers found
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§