Skip to content
Back to full roadmap
topicfoundation

Hallucination Anatomy

Why models 'make things up' — root causes and which prompt patterns trigger it.

2 hours3 resources1 prereqs

Hallucination = the model produces something it doesn't know with confidence. Root causes:

  1. Knowledge gap — events after training cutoff, niche domains
  2. Ambiguous prompt — model feels forced to 'guess'
  3. Long output pressure — when requested detail exceeds real knowledge
  4. Bad few-shot — wrong examples are imitated
  5. Contradictory instructions — model forced to pick most-likely interpretation

Mitigation:

  • Add "If you don't know, say I don't know" to system
  • Ground with RAG (external sources)
  • Require citation-style answers + verification step
  • Low temperature for critical tasks
  • LLM-as-judge for post-hoc verification

Why this matters

Hallucination is the #1 enemy of production AI; you can't defend against what you don't understand.

What you'll gain

You can intuitively estimate hallucination risk and apply mitigation layers in the right order.

Prerequisites

Resources(3)

Related steps