BeClaude
Research2026-04-27

Verbal Confidence Saturation in 3-9B Open-Weight Instruction-Tuned LLMs: A Pre-Registered Psychometric Validity Screen

Source: Arxiv CS.AI

arXiv:2604.22215v1 Announce Type: cross Abstract: Verbal confidence elicitation is widely used to extract uncertainty estimates from LLMs. We tested whether seven instruction-tuned open-weight models (3-9B parameters, four families) produce verbalised confidence that meets minimal validity criteria...

arxivpapers