Data
AI Hallucination
AI hallucination is the generation of plausible-sounding but factually incorrect, fabricated, or unverifiable content by a language model. Hallucinations occur because LLMs predict statistically likely token sequences rather than retrieving verified facts — they have no internal 'truth checker.'
Hallucination rates vary by model, task type, and prompt design. Mitigation strategies — in order of reliability — are: grounding to retrieved sources (RAG), structured output with citation requirements, constrained generation using schemas, chain-of-thought reasoning, and self-consistency checks. For high-stakes deployments (clinical, legal, financial), hallucination mitigation is not optional and must be validated with domain-specific evaluation benchmarks before production.
Related terms
- Hallucination — A hallucination is when an AI model generates text that is fluent, confident, and factually wrong.
- Grounding — Grounding is the practice of constraining an AI model's output to verifiable sources — typically by requiring it to cite specific documents, database rows, or tool results.
- RAG (Retrieval-Augmented Generation) — RAG is a pattern in which an AI model retrieves relevant documents from a knowledge base at query time and uses them as additional context to generate its response.
- Responsible AI — Responsible AI is an umbrella term for the operational practices that make AI deployments safe, fair, transparent, accountable, and aligned with human values — covering ethics, governance, security, privacy, and reliability across the full lifecycle.