<ul><li>Feature-based methods are commonly used to explain model predictions, but often assume interpretable features are readily available.</li><li>The FIX benchmark, called Features Interpretable to eXperts, aims to measure how well a collection of features aligns with expert knowledge.</li><li>FIXScore is proposed as a unified expert alignment measure applicable to diverse real-world settings across different domains and data modalities.</li><li>Popular feature-based explanation methods perform poorly in terms of alignment with expert-specified knowledge, signaling the need for better methods.</li></ul>

The FIX Benchmark: Extracting Features Interpretable to eXperts

Discover more