Don't let the LLM speak, just probe it

When an LLM reads "here's some text, here's a criterion - does it satisfy it?", the answer often already exists in its hidden state before it generates a single token. So skip generation entirely: grab the hidden state at the last prompt token (~70% of the way up the model's layers), feed it to a tiny MLP, calibrate the output. Because the training data varies the criterion, you get one frozen model that acts as any classifier you can write in English.