Hallucination
Also known as: Confabulation
When a model confidently makes up something that isn't true.
When a language model generates plausible-sounding but factually incorrect information. RAG, grounding, and constrained decoding are common mitigation strategies.
In practice
The headline failure mode for any production LLM app. Be ready to defend a mitigation stack (grounding, citation, eval, abstention) for your specific use case.
How it compares
Hallucination is the failure; RAG is one of the most common mitigations for it.
Comparisons that include Hallucination
Related topics
Questions that mention this term
- How does ReAct differ from pure chain-of-thought, and what does interleaving reasoning with acting provide?
- Best architecture for a chatbot over a frequently updated company knowledge base?
- What is the primary…
- Why 'fine-tune on our company docs' usually fails: and what to do instead
- Select the techniques that genuinely cut hallucination in a RAG answer
- What is a hallucinated tool call and how does a production runtime defend against it?
Related terms
AI System Design
End-to-end design of production LLM systems: ingestion, retrieval, serving, eval, monitoring.
BM25
Classical TF-IDF-style lexical scoring: a surprisingly strong baseline, still the first stage of many hybrid RAG pipelines.
Chatbot Arena
Crowdsourced blind A/B comparisons of LLM responses, aggregated into an Elo leaderboard.
Chunking
Cutting documents into retrievable pieces before embedding them.
Context Engineering
Deciding what makes it into the model's context window (prompt + RAG + history + memory), and why.
Context Window
The max number of tokens a model can attend to at once.