The authors introduce TTMark, which reweights the joint probability of consecutive tokens during LLM decoding to embed a watermark.
Pairwise token watermarking improves AI text detection without altering output
TTMark extends distortion-free watermarking from single tokens to token pairs, boosting detectability especially in low-entropy settings.
Top University
Ruibo Chen · Zhengmian Hu · Donghang Lu · Xuehao Cui · Georgios Milis · Yihan Wu · +2 more
University of Maryland, College Park · TikTok
Research Digest··2 min read
Thread:Language Model Watermarking
The authors propose Tandem Token WaterMark (TTMark), a distortion-free watermarking framework that operates on adjacent token pairs rather than individual tokens.
Why this paper
From University of Maryland, College Park and TikTok
In one line
Pairwise distortion-free watermarking of adjacent token pairs improves detection in low-entropy regimes while preserving output distributions.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ✓Reports numbers on named benchmarks
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§