An image generator depicts occupations and regions unevenly.
Assess fairness of the generated content.
Choose two appropriate evaluations.
Compare content, frequency, and quality across diverse attributes and provide stereotype controls, reporting, regeneration, and human review.
Detailed explanation
Underrepresentation and fixed stereotypes can be identified.
Underrepresentation and fixed stereotypes can be identified.
Users can mitigate impact and report issues.
Users can mitigate impact and report issues.
Content and impact are missed.
Content and impact are missed.
The problem cannot be improved.
The problem cannot be improved.
Try it yourself
An example you can run in a temporary verification environment.
AWS公式AIF-C01 Domain 4.1の公平性、バイアス、責任ある生成AIを確認する。Expected result
表象上の偏りを性能指標だけでなく出力内容と利用者影響で評価できる。Key points
- Representation
- Stereotype
- Reports
Notes
- Environment: AWS公式AIF-C01試験ガイドとAWS公式ドキュメントの確認
- Command output formatting can vary slightly by distribution or tool version.
- Run the example in a temporary directory or process when possible.
Foundation review
Read the scope first
Check whether the command acts on the current shell, a new process, an existing process, or a file.
Verify the observable result
Use the supplied command and compare the output with the expected result.