What is reciprocal rank fusion?
PICTURE THIS: AN LLM TURN
Simple meaning
RRF combines ranked lists by summing 1 over k plus rank for each document across systems.
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:
- 1RRF combines ranked lists
by summing 1 over k plus rank for each document across systems.
- 2It needs only ranks,
not comparable scores.
- 3It is a strong
default when merging BM25 and vector results.
- 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
RRF combines ranked lists by summing 1 over k plus rank for each document across systems. It needs only ranks, not comparable scores.