SOURCE-LINKED INTELLIGENCE

WeaveMark: Robust and Scalable Multi-bit LLM Watermarking via Coded Payload Spreading

arXiv · AI, language, vision and robotics · article · Sep 2, 2026 · UTC

Multi-bit watermarking for large language models (LLMs) enables content source tracing by embedding user-identifiable messages into generated text. Existing methods face a fundamental trade-off among extraction accuracy, text quality, and payload capacity. We propose WeaveMark, a robust and scalable multi-bit LLM watermarking scheme based on coded payload spreading. WeaveMark shifts this trade-off frontier by improving payload capacity through multi-bit-per-token spreading, improving extraction accuracy through soft-decision error-correcting code, and preserving text quality through unbiased m

Read original source ↗ Open in workspace

recordType

paper

region

Global