Verified70% confidenceFactExact time
"Hallucination" refers to models generating content that appears authoritative but is factually incorrect, with very high confidence.
4
Sources
70%
Confidence
Long-term
Relevance
7/17/2026
First Seen
Sources
Related Claims
VerifiedLarge models are prone to 'hallucination' when handling professional domain questions, meaning they confidently provide incorrect answers.79% similarVerifiedHallucination refers to content generated by a model that appears plausible but is actually incorrect or fabricated, and is the most intractable technical problem with LLMs.76% similarUnverifiedTool Hallucination refers to the phenomenon in which a model fabricates non-existent tools or incorrectly invokes unrelated tools.70% similarUnverified目标漂移与模型幻觉不同：幻觉指生成事实错误内容，目标漂移指事实层面无明显错误却在意图层面偏离原始任务目标68% similarUnverifiedAI hallucination includes not only models fabricating non-existent facts, but also denying a fact that truly exists with high confidence.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/536441API
curl https://kongchang.com/api/v1/knowledge/claims/536441MCP
get_claim(id=536441)