Verified80% confidenceFactExact time
Top-P (nucleus sampling) samples from the smallest set of tokens whose cumulative probability exceeds the threshold P, while Top-K selects only from the K candidates with the highest probabilities.
7
Sources
80%
Confidence
Long-term
Relevance
7/7/2026
First Seen
Sources
Why Large Language Models Are Starting to 'Invent Words': The Nature of LLM Language Boundaries
hackernewshackernews7/6/2026
Related Claims
UnverifiedTop-p (nucleus sampling) dynamically truncates to the smallest set of tokens whose cumulative probability exceeds the threshold p.80% similarUnverifiedTop-K SAE retains only the K features with the highest activation values during encoding and forces all others to zero, thereby compelling the model to learn sparse representations.68% similarUnverifiedTop-K retrieval refers to returning the top K chunks with the highest similarity during the retrieval stage, and K is usually taken from 3 to 10.68% similarUnverifiedThe value of K in Top-K should be determined through offline evaluation by measuring Recall@K at different K values on an annotated test set and finding the inflection point where the recall curve begins to flatten.67% similarUnverifiedTop-1精度衡量量化模型预测的最高概率token与原始模型预测的最高概率token相匹配的比例67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/170076API
curl https://kongchang.com/api/v1/knowledge/claims/170076MCP
get_claim(id=170076)