AUG 11, 2026 · PREPRINT
ProbGuard: Calibrated Safety Risk Estimation from LLM Output Distributions
arXiv
This is an unrefereed preprint describing a novel computational method for LLM safety assessment; it has not undergone peer review and the claims rest on algorithmic performance metrics rather than clinical or validated real-world outcomes.
Reported
Brier score reduction79.6%
ECE reduction71.9%
Maximum attack success rate1%