A historic lightship education desk has two docents independently score a week of generated tour lines for unfair group stereotypes and invented dates. Which monitoring method is that?
Select an answer to reveal the explanation.
Short Explanation
Think of two docents independently scoring a week of tour lines for stereotypes and invented dates. That is a human audit. ROUGE and an endpoint size are not that review.
Full Explanation
Human audits are a practitioner-level way to detect bias, trustworthiness, and truthfulness. Two docents scoring a week of lines is that method. ROUGE, provisioned throughput, and from-scratch training are not audits.