[anankaie]

I suspect that it will be possible to, assuming the number of popular open LLMfor this remains low, target the popular ones to have your watermark be resilient. With that said, watermarking to indicate that something was generated by AI reminds me of what someone told me about locks: They are there to keep honest people honest.

It will certainly not defeat an adversary directly targeting the technique. It is likely that a LoRA based approach would defeat this, especially if the detector for the watermark is broadly available and cheap to run.

[valine]

This watermark relies on subtle grammatical variations. Passing it through any model is going to wipe out the distribution.

The number of open LLMs is exploding, and the most popular ones are fine tuned by small groups / individuals. None of the folks volunteering their time and compute to fine tuning open models are going to waste resources adding your watermark.