AI engineering glossary · Evaluation metrics
What is slice-based evaluation?
Slice-based evaluation (also called sliced evaluation, subgroup evaluation): Computing metrics separately for meaningful subsets of the data, such as by language, region, device or demographic group, rather than only overall. A model can look strong on average while failing badly on a slice, so this reveals hidden weaknesses and fairness gaps.
Slice-based evaluation: an example
A speech model has 8% word error rate overall but 21% on Hindi-accented English, which slice-based evaluation reveals.
Related terms
More Evaluation metrics terms
- Spearman's rank correlation
- Specificity
- Symmetric mean absolute percentage error
- Temperature scaling
- Token-level F1
- Translation edit rate
- True negative
- True positive
Where you learn it
Slice-based evaluation is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.