Unverified50% confidenceFactExact time
A score question outputs a numerical value used to measure the strength of some attribute, suitable for scenarios requiring continuous values, such as sentiment analysis, risk scoring, and priority ranking.
1
Sources
50%
Confidence
Long-term
Relevance
10/26/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedA weighted scoring model lists several evaluation dimensions, assigns a weight to each dimension, scores candidate options item by item, and then sums them with weights, with the highest score winning.75% similarUnverifiedIn evaluation set design, a holdout set refers to the portion of data deliberately kept out of the optimization process and used only for final validation, to detect overfitting, provided that the scorer definition reflects the good outputs you truly care about.73% similarUnverifiedThe evaluation program feeds the question, reference answer, and actual response together into the judge model, along with scoring instructions (e.g., relevance, accuracy, and completeness each scored 0–5), and the judge model outputs structured scores and reasoning.72% similarUnverifiedThe recommendation rate metric requires repeatedly running priority buyer questions across multiple AI vendors, counting the proportion of times the brand is mentioned or recommended, and reporting it broken down by funnel stage.72% similarUnverifiedEach sample in the test set needs a clear expected output or scoring criterion, which can be exact match, key information inclusion, or scoring by another LLM according to a rubric (LLM-as-judge).72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1101574API
curl https://kongchang.com/api/v1/knowledge/claims/1101574MCP
get_claim(id=1101574)