Survey of Hallucination in Natural Language Generation

Our summary

A broad survey of hallucination across natural-language generation tasks: definitions, taxonomies (intrinsic vs extrinsic), root causes, and evaluation/mitigation methods. A reference map of why generators produce unsupported text.

Why it matters

The orienting overview for the hallucination failure class — useful for situating specific findings within a documented taxonomy.

Cited by these methods

Related findings (2)

• Fabricated citations and referencesHigh

  Models invent plausible-looking but non-existent papers, authors, DOIs and URLs.

• Fabrication instead of admitting uncertaintyHigh

  Asked about something unknown or non-existent, models invent an answer rather than saying 'I don't know'.

Cite this