Why do LLMs hallucinate?
PICTURE THIS: A SENTENCE BECOMES TOKENS
The model does not read letters like humans. It reads these pieces, then predicts the next one.
Simple meaning
They fill gaps with statistically plausible tokens when evidence is missing or conflicting.
WHY — Hallucination instead of guessing?
Why interviewers care about Hallucination:
on Hallucination.
the situation, the default choice, and one exception - that reads as experience.
Name the idea, why it exists, then one short example.
End with when you use it and one common pitfall.
STEPS — What happens with tokens?
Before the model can read a sentence, it goes through these steps:
- 1They fill gaps with
statistically plausible tokens when evidence is missing or conflicting.
- 2Training also mixes outdated
and noisy web text.
- 3Decoding that favors fluency
can prefer a smooth lie over 'I do not know.'
- 4Context mix
Attention looks at nearby tokens together.
- 5Next token
The model scores what should come next.
- 6Decode
IDs turn back into readable text.
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
They fill gaps with statistically plausible tokens when evidence is missing or conflicting. Training also mixes outdated and noisy web text.