Refusal Calibration in Instruction-Tuned Language Models: When should a model decline, and how well do current models know?
Instruction-tuned models decline requests for many reasons, but little is known about how well their refusals track the actual risk of a request. We build a labelled set of 6,400 requests spanning benign, borderline and harmful categories and measure calibration of refusal decisions across eight open models. Refusal rates correlate only weakly with annotated risk for borderline requests, and over-refusal is concentrated in a handful of phrasing patterns rather than topics. A light-weight calibration step that uses the model's own confidence reduces over-refusal by 31% at no measurable cost to harmful-request refusal. We release the labelled set and the annotation guidelines.