I don't quite understand the aim of this paper. They focus on undetectable watermarks for LM text. But isn't rather the difficulty that it is hard to distinguish between AI generated and normal text in the first place, even with detectable watermarks? Unlike photos, audio, or video, text has an incredibly low bitrate, so there isn't much room for steganography. It's like they are trying to solve a hard problem without having solved the easier problem first.