Unverified50% confidenceFactExact time
Researchers refer to the phenomenon of a model filling in statistically probable text rather than admitting uncertainty as 'confident ignorance'.
1
Sources
50%
Confidence
Long-term
Relevance
9/21/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedWhen a model lacks up-to-date information, it may not admit ignorance, but instead fabricate seemingly plausible yet factually incorrect answers (hallucinations).73% similarUnverifiedAcademia refers to the phenomenon of models preferring to fabricate rather than admit ignorance as 'sycophancy'.71% similarUnverifiedAutoregressive language models have never seen 'I don't know' as a high-frequency reasonable output during training, so they are more likely to generate fabricated content at the boundaries of their knowledge than to express uncertainty70% similarUnverifiedWhen a model lacks accurate knowledge of a particular library, it tends to generate syntactically correct but semantically incorrect code—so-called 'confident errors.'70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/938185API
curl https://kongchang.com/api/v1/knowledge/claims/938185MCP
get_claim(id=938185)