Glossary

Precision and recall

Precision matters when a false positive is costly; recall matters when a missed positive is costly. A fact-checking tool should report both, by language and claim type.

Why it matters

Two measures of classification performance: how many positive predictions are correct, and how many actual positives are found. Understanding the term is the first step; applying it consistently is the harder part.

Browse the glossary or read the editorial standards.

Related terms

Human-in-the-loop

A design pattern in which a person reviews, approves, or overrides an automated output before it has effect.

Read more

LLM-as-Judge

Using a large language model to score or compare outputs, often as a substitute for human evaluation.

Read more