Verified65% confidenceFactExact time
The confidence output of large language models is fundamentally a product of probability distributions rather than a genuine judgment of factual truth or falsehood, and may express high confidence in incorrect statements.
3
Sources
65%
Confidence
Long-term
Relevance
9/11/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedThe probability figures provided by guided generative models are essentially 'well-constrained inferences' rather than directly verifiable truths.76% similarVerifiedThe hallucination problem in large language models stems from their nature as statistical probability-based sequential prediction systems, where generated tokens are based on conditional probability maximization rather than genuine logical reasoning.75% similarUnverifiedLanguage models tend to smooth vague expressions such as 'plan' into more confident, more fluent assertions, causing facts to be upgraded into less truthful statements during generation.75% similarVerified大模型幻觉的技术本质在于模型在训练时学习的是语言模式的概率分布而非事实本身74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/899279API
curl https://kongchang.com/api/v1/knowledge/claims/899279MCP
get_claim(id=899279)