Unverified50% confidenceOpinionExact time
One of the deep root causes of model hallucination is that the model cannot distinguish whether it is retrieving facts or fabricating content, due to a lack of genuine access to its own cognitive state.
1
Sources
50%
Confidence
Long-term
Relevance
9/12/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedPure reasoning chains (Chain-of-Thought) are prone to hallucination because the model cannot obtain feedback from the real world.79% similarUnverifiedAI hallucination includes not only models fabricating non-existent facts, but also denying a fact that truly exists with high confidence.76% similarUnverifiedWhen a model lacks up-to-date information, it may not admit ignorance, but instead fabricate seemingly plausible yet factually incorrect answers (hallucinations).74% similarUnverifiedUllman等人指出模型在错误信念任务经过微小变体修改后便大幅失准，暗示其依赖表面模式而非真正的心智建模74% similarUnverifiedAI hallucination is not a random failure but an inevitable result of low-quality context input; when the input context is sparse, the model lacks a handle to anchor itself to real information.74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/912206API
curl https://kongchang.com/api/v1/knowledge/claims/912206MCP
get_claim(id=912206)