Domain 5 of 6
Interpretability and Transparency
Interpretability, what it has established and what it has not, and the documentation that stands in for understanding while the research catches up.
Concepts in this domain
01InterpretabilityWhat the field has established about the inside of a model, what it has not, and why a system that explains itself is not explaining itself.02Transparency and explainabilityWhy an accurate model you cannot explain is sometimes the wrong choice, the difference between the two words, and what a model card is for.Try a question from this domain
A model is asked to show its reasoning before answering, and produces a clear step by step account. What has been obtained?
- AA faithful record of the computation that produced the answer.
- BGenerated text about the answer, which can be fluent and unrelated to what actually drove the output.
- CAn audit trail sufficient to satisfy a right to explanation.
- DNothing useful, since chain of thought does not improve accuracy.
6 questions on this domain.
One per page, with a worked explanation.
Start the set