Instead of a reward signal based on human preferences (RLHF) or verifiable task rewards (RLVR), RLCD uses a signal that rewards calibration: the probabilities assigned to decisions are optimized against real outcomes so that, over large groups of predictions, they match the observed frequency of correctness. The result is models that return typed decisions (e.g. a choice, a score, a boolean) together with a trustworthy confidence level.
Language models trained for human preferences tend to be overconfident and poorly calibrated, which hinders automated, safe decisions in software; RLCD aims to yield probabilities that reflect genuine uncertainty.
RLCD announced alongside the Jev model in September 2026.
