Name three types of LLM hallucination.
mediumAnswer
- (1) Factual: model states false facts confidently ('Marie Curie was born in 1876' — she was 1867).
- (2) Faithfulness (in RAG): model contradicts or adds beyond the retrieved context.
- (3) Intrinsic: internal contradictions within a single response.
- (4) Extrinsic: plausible-sounding but unverifiable additions (fake citations, fake case law).
- Different failure modes need different mitigations — RAG helps factual + extrinsic; system-prompt discipline helps intrinsic; self-consistency helps most types.
Check yourself — multiple choice
- Only factual errors
- Factual, faithfulness (RAG), intrinsic (self-contradiction), extrinsic (fake citations) — each needs different mitigation
- Same as bias
- Only in fine-tuning
Hallucination taxonomy: factual / faithfulness / intrinsic / extrinsic — each mitigated differently.
#hallucinations#reliability
Practise LLMs & GenAI
214 interview questions in this topic.
Related questions
- Why do LLMs hallucinate and how do you reduce hallucinations?
- What is 'honesty' as an alignment target and how do you train for it?
- How do you detect hallucinations in production?
- What is sycophancy in LLMs and how do you reduce it?
- What is faithfulness in RAG and how do you measure it?
- How do you make an LLM cite its sources reliably?