Unverified50% confidenceSolutionExact time
Semi-autoregressive generative models generate a block of tokens in parallel at each step, with blocks still generated in autoregressive order, seeking a balance between parallelism and sequential dependency.
1
Sources
50%
Confidence
Long-term
Relevance
9/9/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedAutoregressive generation refers to the model predicting the next token each time based on all previously generated tokens, progressively unfolding until a complete code block is generated68% similarUnverifiedLarge language models use an autoregressive generation mechanism, sampling the next token at each step based solely on a probability distribution, with each token's generation conditioned on all preceding tokens to form a chain of probabilistic dependencies.66% similarUnverifiedAutoregressive generative models sample the next token at each step based on the probability distribution of the preceding context; when a repetitive pattern gains a slightly higher probability, it forms a positive feedback loop that leads to repetition degeneration.66% similarUnverifiedAutoregressive models work by taking the output of the previous step as the input for the next step, generating sequences incrementally.66% similarUnverified自回归模型采用从左到右的顺序生成，推理阶段必须串行执行，无法并行65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/884179API
curl https://kongchang.com/api/v1/knowledge/claims/884179MCP
get_claim(id=884179)