Top-p sampling
Generation restricted to the smallest token set whose cumulative probability reaches a threshold.
What Top-p sampling does not show
It controls diversity, not factuality or source selection.
Terms this definition uses
Related terms in Models and generation
How a model produces text, what its training and decoding controls change, and what none of them can prove about a source.
Autoregressive model · Transformer · Attention · Self-attention · Parameter · Inference · Pretraining · Fine-tuning · Supervised fine-tuning · Instruction tuning · RLHF · Preference optimization · Knowledge distillation · Quantization · Mixture of experts · Multimodal model · Vision-language model · Small language model · Tokenizer · Temperature · Deterministic decoding · System prompt · Developer message · Tool call · Function calling · Structured output · Constrained decoding · Chain of thought · Reasoning trace · Context caching · Context compaction · Model routing · Model drift · Model version
Questions about Top-p sampling
What is Top-p sampling?
Generation restricted to the smallest token set whose cumulative probability reaches a threshold.
What does Top-p sampling not show or guarantee?
It controls diversity, not factuality or source selection.
Which area of the glossary does Top-p sampling belong to?
Models and generation: How a model produces text, what its training and decoding controls change, and what none of them can prove about a source.
← Temperature · Deterministic decoding →
See it in the full glossary · 731 terms across 19 areas.