가이드 연계 퀴즈 · 하드 레벨

Asking LLMs How Confident They Are Quiz

Tests confidence calibration, ECE, study differences, token likelihoods, task-specific validation, and repeated-answer limits for consequential workflows.

관련 가이드 경로Verbalized Confidence From LLMs
질문 1 의 8

What does a model-generated “80% confident” statement establish by itself?