Do Thinking Tokens Help with Safety?
Probes whether the first hidden state of a reasoning trace predicts a model’s eventual refusal or compliance. Compares this early signal with partial-trace continuations and thinking-enabled versus direct responses to test whether written deliberation changes safety decisions.
First public: · Added to this list: November 2, 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.