Unverified50% confidenceFactExact time
Kirchenbauer等人的水印算法在生成每个token时，根据前文的哈希值将词汇表划分为绿名单和红名单，并轻微提升绿名单token被选中的概率
1
Sources
50%
Confidence
Long-term
Relevance
8/23/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedKirchenbauer方案在模型原始logits上为绿名单token加上一个通常取1-2之间的固定偏置δ，再进行softmax归一化后采样68% similarUnverifiedThe recall rate is calculated as the number of correctly recognized terms divided by the total number of terms actually present.53% similarUnverifiedMainstream LLM text watermarking schemes embed statistical signals by manipulating the token sampling probability distribution during model generation, rather than inserting special characters.53% similarUnverifiedWhen generating each token, large language models perform probabilistic sampling over all possible next words in the vocabulary, rather than deterministically selecting a unique answer.51% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/789698API
curl https://kongchang.com/api/v1/knowledge/claims/789698MCP
get_claim(id=789698)