Learning to Watermark LLM-generated Text via Reinforcement Learning
Keywords: LLM Watermark
Abstract: We study how to watermark LLM outputs, i.e. embedding algorithmically detectable signals into LLM-generated text to track misuse. Unlike the current mainstream methods that work with a fixed LLM, we expand the watermark design space by including the LLM tuning stage in the watermark pipeline. While prior works focus on token-level watermark that embeds signals into the output, we design a model-level watermark that embeds signals into the LLM weights, and such signals can be detected by a paired detector. We propose a co-training framework based on reinforcement learning that iteratively (1) trains a detector to detect the generated watermarked text and (2) tunes the LLM to generate text easily detectable by the detector while keeping its normal utility. We empirically show that our watermarks are more accurate, robust, and adaptable (to new attacks) with no generation overhead. It also allows watermarked model open-sourcing. In addition, if used together with alignment, the extra overhead introduced is low -- only training an extra reward model (i.e. our detector). We hope our work can bring more effort into studying a broader watermark design that is not limited to working with a fixed LLM.
Primary Area: alignment, fairness, safety, privacy, and societal considerations
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 7704
Loading