Verified75% confidenceFactTime unknown
Large language models are based on the Transformer architecture; each inference is an independent forward propagation process that retains no session state.
5
Sources
75%
Confidence
Long-term
Relevance
5/31/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedCurrent mainstream large language models adopt the autoregressive generation mechanism of the Transformer architecture, generating token by token from left to right, and cannot go back to modify already-output reasoning steps after generation.81% similarVerifiedLarge models are based on the Transformer architecture; their inference process is stateless, each request is an independent forward propagation computation, and the model itself retains no information between requests.80% similarUnverifiedTransformer-based LLMs perform an independent forward-pass computation for each inference, with model weights fixed during the inference phase; what is referred to as context memory is essentially the re-injection of historical conversation text into the prompt.78% similarVerifiedEach inference call to a large model is an independent forward pass; the model weights are completely fixed during inference and there is no mechanism to preserve state across conversation sessions.78% similarVerifiedLarge language models are essentially stateless functions whose weights are fixed at inference time and do not learn over time.75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/14783API
curl https://kongchang.com/api/v1/knowledge/claims/14783MCP
get_claim(id=14783)