SOURCE-LINKED INTELLIGENCE

CORDIAL: Calibrating Ordinal LLM Outputs from Few Labels

arXiv · AI, language, vision and robotics · article · Sep 24, 2026 · UTC

A large language model (LLM) can turn a text into a distribution over an ordered scale, but that distribution is a noisy measurement: saturated, compressed or exaggerated, and biased in a consistent direction. We propose CORDIAL, which treats the model's output as a noisy reading of the true label and corrects it with a channel of five interpretable parameters. The channel is small enough for its posterior to be averaged from a handful of labels, and we prove that the resulting calibration preserves first-order stochastic order. On Amazon reviews and CMU-MOSEI transcripts with four LLMs, CORDI

Read original source ↗ Open in workspace

recordType

paper

region

Global