Moderate Hybrid search Question 135 of 223

How do you fuse BM25 hits with vector hits?

GenAI / LLM · Speak this in 60–90 seconds · Faridabad & Delhi NCR

PICTURE THIS: AN LLM TURN

Text inTokens

TransformerAttention

Text outNext token

Simple meaning

Common methods are reciprocal rank fusion, weighted score mixes after normalization, or a learned reranker on the union.

WHY — Tokens instead of words?

LLMs use tokens (not full words) because it helps them:

This is a process

question about Hybrid search.

Panels listen for order,

trade-offs, and what you would actually do on a GenAI / LLM project - not buzzwords.

Stable token IDs

Each piece maps to a number the network can learn.

Fits the model

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:

1
Common methods are reciprocal
rank fusion, weighted score mixes after normalization, or a learned reranker on the union.
2
Raw BM25 and cosine
scores are not on the same scale.
3
Tune fusion on labeled
queries, not by gut feel.
4
Give an example
One tiny concrete case you can say aloud.
5
Common mistake
What juniors usually get wrong.
6
Close
When you pick this over the alternative.

EXAMPLE — See it in action

Here's a short line you can speak, broken into clear beats:

Say this line

“Raw BM25 and cosine scores are not on the same scale.”

Break into beats

RawBM25andcosinescoresare

Speaking order

2987408337471632900

Note: Adapt this scaffold to your own project — keep it under 60–90 seconds.

Key takeaway

Common methods are reciprocal rank fusion, weighted score mixes after normalization, or a learned reranker on the union. Raw BM25 and cosine scores are not on the same scale.