Verified75% confidenceFactExact time
The hallucination problem in large language models is typically divided into two categories: intrinsic hallucination and extrinsic hallucination, where intrinsic hallucination refers to generated content that directly contradicts the input data, and extrinsic hallucination refers to generated information not mentioned in the input and impossible to verify.
3
Sources
75%
Confidence
Long-term
Relevance
9/11/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedThe root cause of hallucinations in large language models lies in the Transformer architecture's objective of maximizing probability during text generation, rather than prioritizing factual accuracy.75% similarUnverifiedIn code generation scenarios, hallucination manifests as calling non-existent API methods, generating syntactically correct but logically erroneous code, or incorrectly referencing deprecated library versions.73% similarUnverifiedLarge language models generate fabricated content (hallucinations) with high confidence, including inventing non-existent tool names and forging API return results72% similarVerifiedLarge language models have hallucination defects in code generation scenarios, manifested as referencing non-existent library functions and generating syntactically correct but logically erroneous code.72% similarUnverifiedThe hallucination problem in large language models can lead to the generation of fabricated references that have the correct format but cannot be found in real databases.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/895417API
curl https://kongchang.com/api/v1/knowledge/claims/895417MCP
get_claim(id=895417)