Open access
2026
Auditable LLM Safety-Judge Selection via Confidence-Interval Filtering on Unsafe Recall
A confidence-interval (CI) filtered two-stage judge-screening framework that reduces the rate of selecting judges that fail the unsafe-recall screen by an order of magnitude and emits an explicit low-confidence or abort verdict when no judge has sufficient calibration evidence.
Ji-Xiang Yang, Jun-Fei Yi, Jin-Han Li et al.
· IEEE Access · 0 citations