SOURCE-LINKED INTELLIGENCE

When Linguistic and Internal Confidence Diverge in Large Language Models

arXiv · AI, language, vision and robotics · article · Aug 28, 2026 · UTC

Users often ask large language models (LLMs) to report how confident they are, but it is unclear whether such linguistic confidence tracks the model's internal confidence. We study this question across 8 classification tasks, 2 generation tasks and 30 models from three families. For classification, we compare linguistic confidence with logits-based confidence along three axes: association, magnitude agreement and calibration. For generation, we test whether linguistic confidence tracks semantic-entropy-based uncertainty. The axes frequently diverge. Instance-level association is weak on averag

Read original source ↗ Open in workspace

recordType

paper

region

Global