Review
Open access
Aug 2026
Explanation audits reveal silent failures of machine learning models under distribution shift
These results support a scoped monitoring strategy for similar tabular settings: confidence-derived scores are effective for pointwise screening, whereas group-aware explanation audits provide complementary evidence about stable but incorrect feature reliance.
Faraz Masood, Sehba Masood, Arman Rasool Faridi et al.
· Discover Artificial Intellig... · 0 citations