Unverified50% confidenceFactExact time
The classic approach to watermarking is to randomly divide the vocabulary into a green list and a red list before sampling, with the division typically determined by a hash function applied to the preceding token.
1
Sources
50%
Confidence
Long-term
Relevance
9/11/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe green token watermarking method divides the vocabulary into green and red groups based on the hash value of the previous token before sampling, applies probability weighting to green tokens, and causes the frequency of green tokens in watermarked text to be significantly higher than the natural language baseline74% similarUnverifiedInvisible watermarking technology embeds statistical signals during the generation phase of large language models by fine-tuning the token sampling strategy (dividing the vocabulary into green and red tokens and biasing toward green tokens).71% similarUnverifiedSimple editing operations such as replacing synonyms, adjusting word order, and inserting or deleting words can also weaken watermarks, and modifying a sufficient proportion of tokens can bring the green-list statistics back to a random level.64% similarUnverifiedMore robust watermarking research directions include watermarks based on semantics rather than surface tokens, or the adoption of more sophisticated hash-window strategies.63% similarVerifiedText watermarking technology was proposed by Kirchenbauer et al. at the University of Maryland in 2023, embedding hidden signals by dividing the vocabulary into green and red groups and biasing toward selecting green tokens.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/898142API
curl https://kongchang.com/api/v1/knowledge/claims/898142MCP
get_claim(id=898142)