On Reasoning Correctness Directions
Studies hidden-state directions that predict correctness during written arithmetic search traces. Compares linear probes, activation differences, and optimized steering vectors, finding that readable correctness signals do not yield consistent improvements when used to steer generation.
First public: · Added to this list: October 22, 2026
Explore this approach
Analysis and evaluation — Measure how well these methods work, investigate what their internal computation does, and identify where they fail. This includes experiments, studies of model internals, and mathematical results.