Selective Disclosure Watermarking for Large Language Models
Watermarking methods embed imperceptible and verifiable signals into text generated by large language models (LLMs). Existing approaches include zero-bit schemes for distinguishing synthetic text from human writing and multi-bit schemes for embedding metadata. However, current multi-bit watermarking methods do not allow selective disclosure: verifying any part of the watermark requires revealing the entire embedded message. This lack of control leads to unnecessary information exposure and raises privacy concerns. We propose Hierarchical Vocabulary Routing (HeRo), a watermarking framework that
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
- Linked via arxiv authorXuyang Chen →
Selective Disclosure Watermarking for Large Language Models
- Linked via arxiv authorXiang Li →
Selective Disclosure Watermarking for Large Language Models
- Linked via arxiv authorYangxinyu Xie →
Selective Disclosure Watermarking for Large Language Models
- Linked via arxiv authorQi Long →
Selective Disclosure Watermarking for Large Language Models