AI RESEARCH
A Finite-Calibration Regime Map for LLM Judge Panels
arXiv CS.CL
•
ArXi:2606.01034v1 Announce Type: new We study when LLM judge panels should be calibrated with low-dimensional stackers versus joint output tables under finite human-label budgets. Low-dimensional stackers have small estimation cost but miss interactions, whereas joint-table calibrators can represent interactions but pay for cell counts and unseen patterns.