ConceptMLP probe
MLP Probe
A probe classifier containing at least one hidden layer and a nonlinear activation function, used to detect whether sensitive attributes remain in representations. It can fit more complex decision boundaries than a linear probe.
Timeline (last 90 days)
Oct 26
Linear concept erasure methods (such as LEACE) can guarantee that no linear classifier can predict the sensitive attribute after erasure, but they cannot prevent MLP probes from recovering the erased information.
Unverified50%