Tournament sampling begins with multiple independently drawn candidates. They are paired and compared across rounds until one remains, allowing a selection rule to shape the final choice without assigning a single direct score adjustment to every candidate.
In keyed text watermarking, the comparison rule prefers candidates according to secret green-list decisions. Because the initial candidates come from the original model distribution, the method can preserve marginal probabilities more faithfully than a fixed logit bias while still accumulating a detectable keyed pattern.
Acronyms and aliases
keyed tournament sampling variant
Related terms
Frequently asked questions
Why use tournament sampling in text watermarking?
It can introduce a keyed preference while drawing candidates honestly from the model's original next-token distribution.
Does tournament sampling always preserve the original distribution?
Preservation depends on the tournament design and keyed selection rule, so the method needs mathematical analysis and empirical validation.
