Unverified50% confidenceFactExact time
General-purpose large models commonly suffer from overconfidence issues in confidence calibration, tending to output confidence levels close to 100%.
1
Sources
50%
Confidence
Long-term
Relevance
9/24/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedMany models still exhibit high confidence in incorrect answers, presenting a confidence calibration problem.79% similarUnverifiedResearch shows that when humans assign 90% confidence, their actual accuracy rate is often only around 70%, indicating a systematic overconfidence75% similarUnverifiedPrecision bias refers to the tendency for people to assign higher credibility to statements containing precise numbers; experiments show that subjects rated the credibility of "41.3%" significantly higher than "approximately 40%".73% similarVerifiedWhen samples are severely imbalanced, Accuracy becomes misleading—a model that predicts everyone as healthy can still achieve an accuracy of over 99%.71% similarUnverifiedThere is an essential difference between the probability scores (logprobs) output by LLMs and calibrated confidence; large language models are widely known to be overconfident, particularly on out-of-distribution samples.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/946977API
curl https://kongchang.com/api/v1/knowledge/claims/946977MCP
get_claim(id=946977)