Do Language Models Mirror Human Confidence? Exploring Psychological Insights to Address Overconfidence in LLMs

May 1, 2025·
Chenjun Xu*
,
Bingbing Wen*
,
Bin Han
,
Robert Wolfe
,
Lucy Lu Wang
,
Bill Howe
· 1 min read
Abstract
We investigate whether language models mirror human confidence patterns and explore psychological insights to address overconfidence in large language models.
Type
Publication
ACL 2025 Findings

We investigate whether language models mirror human confidence patterns and explore psychological insights to address overconfidence in large language models. Our work provides new perspectives on understanding and improving confidence calibration in AI systems.

Large Language Models Confidence Calibration Human Psychology Overconfidence