How do factuality and faithfulness differ when scoring hallucinations?
PICTURE THIS: AN LLM TURN
Simple meaning
Factuality is correctness versus the real world.
WHY — Tokens instead of words?
LLMs use tokens (not full words) because it helps them:
question about Hallucination.
trade-offs, and what you would actually do on a GenAI / LLM project - not buzzwords.
Each piece maps to a number the network can learn.
Fixed pieces are what transformers expect as input.
STEPS — What happens step by step?
Before you speak the answer, walk the interviewer through these steps:
- 1Factuality is correctness versus
the real world.
- 2Faithfulness is consistency with
provided context, which could itself be wrong.
- 3How it works
RAG evals usually optimize faithfulness
- 4a faithful recap of
a bad source still fails the user.
- 5Common mistake
What juniors usually get wrong.
- 6Close
When you pick this over the alternative.
EXAMPLE — See it in action
Here's a short line you can speak, broken into clear beats:
Note: Adapt this scaffold to your own project — keep it under 60–90 seconds.
Key takeaway
Factuality is correctness versus the real world. Faithfulness is consistency with provided context, which could itself be wrong.