Safety
Bias
Systematic unfairness in a model's outputs, often inherited from patterns in its training data.
Bias can show up in hiring screens, translations or image generation. Testing outputs across groups and languages, including Arabic, helps reveal it.
Frequently asked questions
What does Bias mean?
Systematic unfairness in a model's outputs, often inherited from patterns in its training data. Bias can show up in hiring screens, translations or image generation. Testing outputs across groups and languages, including Arabic, helps reveal it.