Undetectable Watermarks for Language Models

Posted by cryptohell on Thursday June 15, 2023 @09:40PM
from the arxiv.org dept.

( 1 comment | on HN )

Re:Undetectable Watermarks for Language Models by cryptohell on Thursday June 15, 2023 @09:40PM (#36349828)

How many people do you think actually bother rephrasing LLM outputs? Do you personally ever copy paste a full chunk of a response?

[ Parent | on HN ]