Covert Multi-bit LLM Watermarking: An Information Theory and Coding Approach
摘要
We study the problem of multi-bit watermarking for large language models (LLMs). We introduce a block-autoregressive model inspired by multi-token prediction, in which the encoder has limited non-causal access to token distributions within each block. This formulation enables an information-theoretic characterization of multi-bit watermarking capacity, by which the knowledge of LLM cover statistics is leveraged to enable a multi-bit covert embedding. We study the information-theoretic limits of the model by combining Gelfand-Pinsker and channel synthesis coding techniques and obtain an exact characterization of the capacity. The embedding strategy is further optimized across blocks using a constrained Markov decision process (CMDP) and we develop an explicit algorithm based on polar codes following the information-theoretic principles. Our algorithm achieves a bit-error rate below 10 percent with a rate of 0.375 bits/token over short token lengths with negligible perplexity and distortion degradation.
引用
@article{arxiv.2605.16709,
title = {Covert Multi-bit LLM Watermarking: An Information Theory and Coding Approach},
author = {Sidong Guo and Tyler Kann and Teodora Baluta and Matthieu R. Bloch},
journal= {arXiv preprint arXiv:2605.16709},
year = {2026}
}