Probes trained on model activations can detect undesirable behaviors like deception or biases that are difficult to identify from outputs alone. This makes them useful detectors to identify misbehavior. Furthermore, they are also valuable training signals, since they not only reward outputs, but also good internal processes for arriving at that output. However, training against interpretability tools raises a fundamental concern: when a monitor becomes a training target, it may cease to be reliable (Goodhart's Law). We propose two methods for training against probes based on Supervised Fine-tuning and Direct Preference Optimization. We conduct an initial exploration of these methods in a testbed for reducing toxicity and evaluate the amount by which probe accuracy drops when training against them. To retain the accuracy of probe-detectors after training, we attempt (1) to train against an ensemble of probes, (2) retain held-out probes that aren't used for training, and (3) retrain new probes after training. First, probe-based preference optimization unexpectedly preserves probe detectability better than classifier-based methods, suggesting the preference learning objective incentivizes maintaining rather than obfuscating relevant representations. Second, probe diversity provides minimal practical benefit - simply retraining probes after optimization recovers high detection accuracy. Our findings suggest probe-based training can be viable for certain alignment methods, though probe ensembles are largely unnecessary when retraining is feasible.

翻译：暂无翻译