cs.CRNov 12, 2026

Look It Up: Multi-bit LLM Watermarking via Codebook Search

Authors: Jarosław Janas, Paweł Morawiecki, Josef Pieprzyk

Organizations: Institute of Computer Science, Polish Academy of Sciences, 01-248 Warsaw, Poland · CSIRO, Marsfield, NSW 2122, Australia

Abstract

Attributing short LLM-generated texts to a specific source remains challenging for existing multi-bit watermarking methods, which often require long generations or costly decoding to recover payloads reliably. We propose a codebook-based watermarking scheme that maps an nn-bit payload to a longer uu-bit codeword and embeds it during generation through token-level logit biasing. During extraction, the received bit sequence is matched to the nearest codeword in a precomputed secret codebook using Hamming or Levenshtein distance. Experiments show that our method achieves near-perfect recovery for 16-24 bit payloads on 200-token generations and strong performance on 127-token generations for base models. Results are weaker on some instruction-tuned models with very short texts, where low-entropy output distributions reduce embedding reliability. We also study a BCH-based variant that avoids codebook storage but generally reduces robustness. The Levenshtein variant improves resilience to deletions and light paraphrasing, while insertions and stronger rewrites remain challenging. We analyze collision probability, codeword separation, extraction time, tokenization consistency, and text quality, highlighting both the practicality and limitations of codebook-based watermarking for short-form attribution.

Figures & tables

Appendix figures & tables8 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. XMark: Reliable Multi-Bit Watermarking for LLM-Generated Texts

    Apr 6, 2026Jiahao Xu, Rui Hu, Olivera Kotevska +1Multi-Bit WatermarkingText Watermarking

  2. Majority Bit-Aware Watermarking For Large Language Models

    Aug 5, 2025Jiahao Xu, Rui Hu, Zikai Zhang +1Multi-Bit WatermarkingText Watermarking