Unverified50% confidenceFactExact time
Generative models (such as LLMs like GPT and Claude) generate text word by word through probabilistic sampling, and their outputs are open-ended and diverse, but the same input may yield different results.
1
Sources
50%
Confidence
Long-term
Relevance
10/26/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedThe output of LLMs is inherently non-deterministic; even with the same Prompt as input, the model may return results with different formats, content, or even logic at different times.72% similarVerifiedLLMs generate output token by token in an autoregressive manner, with each word's selection based on probability sampling from the current context.70% similarVerifiedDecision models do not generate text; instead, given an input state and a set of named questions, they return typed answers with probabilities in a single forward pass.70% similarUnverifiedModels tend to give high scores to their own outputs (or outputs of similar style); Panickssery et al. found that LLM evaluators can recognize their own generated content and favor it.70% similarUnverifiedDiscriminative models learn which class a given input-output belongs to or its probability, with typical representatives including BERT and its fine-tuned variants.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1100752API
curl https://kongchang.com/api/v1/knowledge/claims/1100752MCP
get_claim(id=1100752)