SOURCE-LINKED INTELLIGENCE
How Unlikely Is "Unlikely"? Assessing Verbal Probability Perception Across Large Language Models
Large language models increasingly produce and interpret verbal probability expressions, yet whether these expressions carry consistent meaning across models (or match human perceptions of uncertainty) remains unknown. We present a systematic cross-model evaluation using a word-to-number mapping task grounded in established human benchmarks. Eleven uncertainty expressions were presented to 19 models under two conditions, forced single-number response and explanation elicitation, alongside a novel bidirectional roundtrip test of internal consistency. LLMs track the human benchmark with surprisi
Read original source ↗ Open in workspace
- recordType
- paper
- region
- Global
Evidence & attribution
- arXiv · AI, language, vision and robotics · 2026-08-26T19:00:41.000Z
First collected: 2026-09-21T09:11:58.312Z. This is not the publication date.