Artificial Intelligence #llm#metacognition
How Scale Design Impacts LLM Metacognition and Enterprise AI Reliability
A study on arXiv reveals that the confidence scale used in LLMs (typically 0-100) leads to heavy discretization, with over 78% of responses on three round numbers. Changing the scale to 0-20 improves metacognitive efficiency. The findings have implications for enterprise use of LLMs in supply chain decision-making where confidence calibration is critical.
Jun 16, 2026 1 source