引導式測驗 · 硬 等級
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.
問題 1 的 8
引導式測驗 · 硬 等級
Tests confidence calibration, ECE, study differences, token likelihoods, task-specific validation, and repeated-answer limits for consequential workflows.