Optimal Multi-bit Generative Watermarking Schemes Under Worst-Case False-Alarm Constraints

arXiv:2604.08759v1 Announce Type: cross Abstract: This paper considers the problem of multi-bit generative watermarking for large language models under a worst-case false-alarm constraint. Prior work established a lower bound on the achievable miss-detection probability in the finite-token regime and proposed a scheme claimed to achieve this bound. We show, however, that the proposed scheme is in fact suboptimal. We then develop two new encoding-decoding constructions that attain the previously established lower bound, thereby completely characterizing the optimal multi-bit watermarking performance. Our approach formulates the watermark design problem as a linear program and derives the structural conditions under which optimality can be achieved. In addition, we identify the failure mechanism of the previous construction and compare the tradeoffs between the two proposed schemes.

Related

• Differentially Private Language Generation and Identification in the Limit
• Is More Data Worth the Cost? Dataset Scaling Laws in a Tiny Attention-Only Decoder
• Incentive-Aware Multi-Fidelity Optimization for Generative Advertising in Large Language Models
• Rethinking Data Mixing from the Perspective of Large Language Models

Source: arXiv cs.CL | 2026-04-13