Artificial Intelligence · 28.08.2026, 05:32 UTC
How Unlikely Is "Unlikely"? Assessing Verbal Probability Perception Across Large Language Models
| Schweregrad | info |
|---|---|
| Kategorie | Artificial Intelligence |
| Quelle | arXiv cs.AI ↗ |
| Veröffentlicht | 28.08.2026 UTC |
Sicherheitsmeldung mit Schweregrad noch nicht bewertet. Technische Details im Tab „Originaltext“; empfohlene Schritte in der Checkliste.
arXiv:2608.26327v1 Announce Type: cross Abstract: 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 surprising fidelity: word ordering is preserved, three anchor points are recovered, and ``possible'' shows the highest variance and cross-model disagreement of any expression tested, consistent with its documented bimodal interpretation in humans. However, models show a systematic upward bias for negative expressions such as ``unlikely'' and ``improbable.'' Explanation elicitation reduces within-model variance while increasing between-model divergence, stabilizing individual models at the cost of inter-model consensus, and the roundtrip experiment reveals clear stratification, with frontier models maintaining coherent bidirectional representations. LLMs thus reproduce the structure of human verbal probability cognition, including its biases, while diverging systematically at the negative end---with implications for any setting where humans and models exchange probabilistic language.
Maßnahmen
⬇ Als MarkdownVerwandte Beiträge
- info PAWBench: How Far Are We from Probabilistically Aligned World Modeling?
- info LLMs in Digital EDA: A perspective on shifting roles from Generation to Orchestration
- info FaulT-Bench: Towards Benchmarking Network Troubleshooting LLM Agents under Unreliable User Tickets
- info Behavior2Trip: Towards Personalized Travel Planning via User Behavior Trajectory