selective-disclosure-watermarking-for-large-language-models-6b08369a·1 events·first seen Aliases: Selective Disclosure Watermarking for Large Language Models
Researchers introduce Hierarchical Vocabulary Routing (HeRo), a watermarking framework for LLMs that enables selective disclosure of embedded metadata. Unlike existing multi-bit watermarking schemes that require revealing the entire embedded message for any verification, HeRo recursively partitions the vocabulary and distributes watermark information across hierarchical layers, allowing different verifiers to decode only the portions corresponding to their access level. The authors claim the method preserves text quality by maintaining unbiased sampling, and demonstrate high detection accuracy with low latency. Code is publicly available.