A message-dependent token-reweighting method embeds multi-bit provenance data into LLM output while preserving the expected output distribution.
Undetectable watermarks for language models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
StealthInk: A Multi-bit and Stealthy Watermark for Large Language Models
A message-dependent token-reweighting method embeds multi-bit provenance data into LLM output while preserving the expected output distribution.