SOURCE-LINKED INTELLIGENCE
When Confidence Signals Disagree: Local and Global Confidence in Autoregressive Language Models
Modern predictive systems expose multiple quantities that are commonly interpreted as measures of confidence. However, these quantities can summarize different aspects of the predictive process. This distinction matters when confidence is used to evaluate reliability or inform downstream oversight and control. We investigate whether different confidence readouts are empirically interchangeable in an autoregressive language model by comparing local confidence, defined from the probability of the greedy-selected answer token, with global confidence, defined from modal-answer frequency under repe
Read original source ↗ Open in workspace
- recordType
- paper
- region
- Global
Evidence & attribution
- arXiv · AI, language, vision and robotics · 2026-09-15T10:08:48.000Z
First collected: 2026-09-20T08:40:59.508Z. This is not the publication date.