[tomsander1998]

text watermarking works pretty well! https://arxiv.org/abs/2301.10226

When you generate a text with an LLM, you always have some choice. So you can sample in a way that is very likely under your watermark scheme, and unlikely otherwise

[FergusArgyll]

but that's what I'm saying, When you ask for exclamation marks after each word that must change the likelihoods of next token by quite a bit. You then remove the marks which hides the fact that you just changed every word without loss of meaning