Provable Limits and Certified Deferral for Verbalized Uncertainty in Small Language Models

In 30 Sekunden

Was passiert ist

Research proves small language models cannot reliably defer to humans using verbalized confidence alone, even with calibration techniques.

Warum es zählt

Engineers deploying small models offline or in cost-sensitive settings need to know when deferral to humans is mathematically safe.

Achtung

Only three of twenty-two model-task pairs achieved certified safe autonomy at twenty percent risk; results assume independent and identically distributed deployment.