Skip to content
Quantoros

What are hallucinations in LLMs and why do they occur?

LLM & AILevel: FoundationHallucinations

What are hallucinations in LLMs and why do they occur?

Hints
  • Clarify the threat: an unsupported fact, an untrusted instruction or an unsafe action?
  • Separate input checks, authority limits and output validation; consider false positives.

Answer

Hallucinations are confident, fluent, and factually incorrect outputs — the model generates text that sounds authoritative but is wrong or fabricated.

Types:

  • Factual hallucination: incorrect facts ("The Eiffel Tower was built in 1892" — it was 1889)
  • Source hallucination: fabricated citations, fake paper titles, non-existent URLs
  • Entity hallucination: wrong names, dates, relationships between entities
  • Reasoning hallucination: correct premises but invalid logical conclusions

Root causes:

  1. Training data contains conflicting or incorrect information
  2. Knowledge cutoff — model extrapolates about post-training events
  3. Models are trained to generate fluent text; they don't have an internal "I don't know" mechanism by default
  4. Sycophancy — models agree with users who state incorrect facts
  5. High temperature increases creativity and hallucination simultaneously

Source and licence: JustInCache & contributors — Awesome AI Interviews · Apache-2.0

Related questions