Unverified50% confidenceFactExact time
Greedy decoding itself is deterministic, but the logits computation it relies on is not deterministic, because changes in batch shape alter the summation order of floating-point operations.
1
Sources
50%
Confidence
Long-term
Relevance
10/18/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedConstrained Decoding computes the set of valid tokens at each token step of autoregressive generation based on a finite state machine or context-free grammar and renormalizes the probabilities, mathematically guaranteeing that the output conforms to the target schema.69% similarUnverifiedLogit-lens projects the hidden states of each layer into the vocabulary logit space to observe what the model would output if forced to decode at that layer.66% similarVerifiedConstrained decoding dynamically blocks candidate words that do not conform to the target grammar or schema when the model generates each token, ensuring the output structure is legal at the decoding level.64% similarUnverifiedDuring the decoding process of masked diffusion language models, once a token is committed to a masked position it is generally irreversible and cannot be corrected.63% similarUnverifiedGBNF 通过在每个 Token 生成步骤对 logits 进行掩码过滤，强制模型只能生成符合预定义语法规则的 Token 序列63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1060909API
curl https://kongchang.com/api/v1/knowledge/claims/1060909MCP
get_claim(id=1060909)