JuryProbe: An Empirical Consensus-Risk Diagnostic for Routing Reference-Free Factuality Judge Panels to Grounded Verification
JuryProbe is introduced, an empirical consensus-risk diagnostic for reference-free factuality judge panels, paired with a calibration-based routing policy, which estimates consensus risk from a labeled calibration probe using false-negative-only (FN-only) judge correlation and false-consensus lift.
Tianxing Zhou, Ruixi Lin
· 0 citations