Unverified50% confidenceFactExact time
Current mainstream large language models exhibit significant deficiencies in both confidence calibration and selective abstention, tend to be overconfident, and when faced with questions outside the training distribution, tend to produce fluent but incorrect answers.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/28/2026
First Seen
Valid until: 12/27/2026
Sources
Related Entities
Related Claims
UnverifiedThe confidence level of a language model and the reliability of its judgments are often not correlated, posing the risk of hallucinatory overconfidence.79% similarUnverifiedWhen a model lacks accurate knowledge of a particular library, it tends to generate syntactically correct but semantically incorrect code—so-called 'confident errors.'76% similarUnverified大模型普遍存在过度自信的问题，需要通过提示词工程和校准策略来校准置信度76% similarUnverified许多开源模型继承教师模型的自信偏差，导致工具调用错误时不愿自我纠正74% similarUnverifiedGeneral-purpose large language models still have significant shortcomings in rigorous logical reasoning and can hallucinate seemingly plausible but actually incorrect proof steps.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/955413API
curl https://kongchang.com/api/v1/knowledge/claims/955413MCP
get_claim(id=955413)