Codebook-Based Multi-Bit Watermarking for Short LLM Outputs
Researchers propose a multi-bit LLM watermarking scheme that maps an n-bit payload to a longer u-bit codeword and embeds it during generation via token-level logit biasing. Extraction matches the received bit sequence to the nearest codeword in a precomputed secret codebook using Hamming or Levenshtein distance. Experiments report near-perfect recovery for 16-24 bit payloads on 200-token generations and strong performance on 127-token generations for base models, with weaker results on some instruction-tuned models and very short texts. A BCH-based variant avoids codebook storage but generally reduces robustness, while the Levenshtein variant improves resilience to deletions and light paraphrasing.
It offers a practical approach to attributing short LLM-generated texts, a setting where existing multi-bit watermarking methods often struggle.
Comments & Questions (0)
No comments yet
Be the first to comment!