What strategies work when documents exceed the context window?
PICTURE THIS: AN LLM TURN
Simple meaning
Chunk and retrieve, map-reduce summarize, or use a long-context model for the last mile only.
WHY — Tokens instead of words?
LLMs use tokens (not full words) because it helps them:
people who only read docs from people who shipped.
and tied to GenAI / LLM work.
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:
- 1Chunk and retrieve, map-reduce
summarize, or use a long-context model for the last mile only.
- 2Why it exists
Do not paste entire wikis.
- 3Hierarchical summaries preserve coverage
when single-chunk retrieval is too narrow.
- 4Give an example
One tiny concrete case you can say aloud.
- 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
Chunk and retrieve, map-reduce summarize, or use a long-context model for the last mile only. Do not paste entire wikis.