Skip to results
MLSift

Titles, abstracts, or an arXiv ID

← Back to results
AI Safety, Security & AlignmentLogit Bias Auditing2609.05125

Single-Query Black-Box Calibration Auditing via Logit Bias

Roman Plaud, Antoine Saillenfest, Matthieu Labeau, Thomas Bonald, Willem Waegeman

cs.LG

Abstract

Evaluating the calibration of Large Language Models (LLMs) is critical for their safe deployment as zero-shot classifiers. Yet, commercial API providers increasingly hide the continuous output probabilities required by standard calibration metrics. To bypass this opacity, we demonstrate that any LLM API exposing a logit\_bias parameter can be mathematically manipulated to evaluate exact probability thresholds using strictly one query per sample. Leveraging this mechanism, we introduce a novel and provably consistent estimator of the True Calibration Error for binary tasks. Our approach therefore provides an efficient framework for auditing black-box foundation models.

Topics

Classified with taxonomy v2 on Mon, 7 Sept 2026.

Report a classification error

Loading the PDF downloads the document. Open it in your browser's viewer, or load it here.

Open PDF