Verified65% confidenceFactExact time
Current mainstream large language models are generally overconfident, partly because the training objective optimizes for the fluency of predicting the next word rather than the actual reliability of the output.
3
Sources
65%
Confidence
Medium-term (~90 days)
Relevance
9/19/2026
First Seen
Valid until: 12/18/2026
Sources
Related Entities
Related Claims
VerifiedEarly large language models suffered from serious overconfidence, tending to give definitive statements even for uncertain answers, which is the hallucination phenomenon.76% similarVerifiedCurrent large language models lack reliable self-introspection capabilities.75% similarUnverifiedOOD detection for autoregressive language models is more difficult than for traditional machine learning because the linguistic compositional space is vast, semantic OOD does not correspond to surface-form OOD, and adversaries can construct inputs that appear statistically in-distribution but semantically trigger OOD behavior.75% similarUnverified大语言模型因知识截止日期机制和新特性语料稀疏（长尾效应），倾向于推荐更老旧但更'自信'的前端写法74% similarUnverifiedLarge language models fine-tuned with RLHF tend to systematically exhibit an overconfidence bias.74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/935807API
curl https://kongchang.com/api/v1/knowledge/claims/935807MCP
get_claim(id=935807)