flâneur

CoT monitorability: why g-means and not F1?

substack.com · 1,142 words · saved by 1 readers

It all has to do with separating monitorability from misalignment property.

Figure 3 in “Monitoring Monitorability” (see below) argues why g-mean is better than F1. I originally didn’t get the implication (esp. about Case B figure) until I understood the mathematical differences between them, and what the implications are when it comes to monitoring misbehaving models. You have a binary monitor that says “misbehavior detected” or “no misbehavior.” The ground truth is either positive (bad behavior happened) or negative (it didn’t). The four outcomes are TP, FP, TN, FN as usual and there are 𝒩 samples, then we get the following operations: TPR = TP/(TP+FN) — “of…

saved by

related reading