Hallucination
When a model generates plausible-sounding but factually incorrect information.
Hallucination occurs because LLMs generate the statistically likely next token rather than retrieving verified facts. A model may confidently cite nonexistent papers, invent API signatures, or fabricate statistics. Mitigation strategies include grounding via RAG, tool use for fact-checking, and choosing models with lower hallucination rates on benchmarks like TruthfulQA.
Related Terms
Enhancing model responses by fetching relevant documents from an external knowledge base at query time.
Connecting model responses to verified, real-world information sources.
The ability for a model to call external functions or APIs to retrieve data or take actions.
The date beyond which a model has no training data and is unaware of events.