Competence, Not Accuracy: A Diagnostic for Reference-Free Judge Gates in Skill Optimization
A reference-free judge is formalized as a latent solver, and a closed-form bound on discriminability (ROC-AUC) in the judge's competence and answer-space size is yields the result that the marginal AUC is confounded by item difficulty while a within-question estimator is not.
Chenleng Chen, Yangbo Wei, Chao Yao et al.
· 0 citations