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

Abstract

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

Categories

@misc{park2026weavemark,
  title = {{WeaveMark: Robust and Scalable Multi-bit LLM Watermarking via Coded Payload Spreading}},
  author = {Gang-Hyun Park and Ju-Hyeong Lee and Hee-Youl Kwak and Dae-Young Yun},
  year = {2026},
  month = sep,
  eprint = {2609.02177},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.02177}
}