Skip to content
AImpact
IT EN
Safety Beginner Also known as: Allucinazione · Confabulation

Hallucination

A model response that sounds plausible but is made up: false facts, nonexistent citations, APIs that do not exist, wrong data presented with confidence.

ShareLinkedInX

In practice

It is the number-one issue when putting LLMs in business workflows. Fixes: RAG with sources, asking for citations, double-checking with a second model, validating structured output against rules. Never treat output as gospel without a check.

Related terms

RAG Alignment

Seen in the wild

5 entries mentioning it
  1. OpenAI Safety Evaluations Hub: a public page with model safety test results
    Medium
  2. NIST AI 600-1: the AI RMF profile for generative AI
    Medium
  3. Claude 2.1: 200K context and fewer false statements
    High
  4. Gorilla: a fine-tuned LLaMA for writing API calls
    Medium
  5. Galactica: Meta launches (and pulls in three days) a science LLM
    Medium
← All terms