引導式測驗 · 中等 等級

如何進行 AI 偏誤稽核測驗

透過子組分析、文件、補救措施和特定管轄區的要求,從決策範圍和指標計劃偏差審計。

問題 1 的 8

What should an audit define before calculating metrics?

預覽每個問題8 問題

當您參加測驗時,就會出現答案和解釋。

  1. What should an audit define before calculating metrics?
    • Only the model’s parameter count
    • A single fairness ratio
    • The decision, system boundary, affected population, and harm of concern
    • The vendor’s preferred benchmark
  2. Why should an audit report subgroup counts and uncertainty?
    • Small samples can make estimates unstable
    • Percentages are meaningless in every case
    • It replaces legal analysis
    • It makes every metric comparable
  3. What did the Obermeyer study illustrate for auditing health algorithms?
    • Removing all race data guarantees fairness
    • Health data cannot be audited
    • Algorithms always improve care
    • Cost can be a biased proxy for need
  4. Which New York City Local Law 144 requirement applies to covered AEDTs?
    • A federal license
    • An independent bias audit within one year before use and a public summary
    • A ban on all resume ranking
    • A guarantee of equal outcomes
  5. Does a passing fairness metric prove a system is fair and lawful?
    • No; it is evidence limited to chosen metrics, scope, and data
    • 是的,總是
    • Only if the tool is open source
    • Yes, when an auditor signs
  6. Why examine labels and target definitions?
    • They control only display colors
    • They are unrelated to audit results
    • They may measure a proxy rather than the intended construct
    • They reveal source code
  7. What should happen after an audit identifies a problem?
    • Publish only the overall score
    • Assign remediation, change the system or process, and retest
    • Ignore it if the model is accurate
    • Delete the report
  8. Which items should an audit report include?
    • Only the final fairness score
    • 只有模型供應商
    • The names of all applicants
    • Scope, data limitations, metrics, and whether test conditions match actual use