LLM Reference
Concepts & capability filters
behavior

Hallucination

Hallucination refers to large language models generating plausible but factually incorrect or fabricated information, often confidently presented as true.

Category
behavior
Difficulty
Not classified
Aliases
None tracked
Last reviewed
2026-07-02

Key facts

  • It arises from gaps in training data or overgeneralization and is mitigated by techniques like RAG or grounding.

Models Mentioning Hallucination(12)