Moderate Embeddings Question 77 of 223

What is the difference between a bi-encoder and a cross-encoder?

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

PICTURE THIS: DATABASE INDEX

Without indexScan every row

With indexJump to keys

CostWrites slower

Simple meaning

A bi-encoder embeds query and document separately so documents can be precomputed.

WHY — Tokens instead of words?

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

They want a clean

contrast on Embeddings, not two memorised paragraphs.

Say what changes for

the developer, then one case where picking wrong hurts.

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 with tokens?

Before the model can read a sentence, it goes through these steps:

1
A bi-encoder embeds query
and document separately so documents can be precomputed.
2
A cross-encoder reads the
pair together and scores relevance more accurately but cannot pre-index millions of docs.
3
Production RAG often retrieves
with a bi-encoder then reranks a shortlist with a cross-encoder.
4
Context mix
Attention looks at nearby tokens together.
5
Next token
The model scores what should come next.
6
Decode
IDs turn back into readable text.

EXAMPLE — See it in action

Let's see how a real sentence is tokenized (tokens may vary by model):

Input text

“A cross-encoder reads the pair together and scores relevance more accurately but”

Tokenized output

Acrossencoderreadsthepair

Token IDs (example)

2987408337471632900

Note: Actual tokens and IDs depend on the tokenizer (e.g., GPT, Llama, etc.).

Key takeaway

A bi-encoder embeds query and document separately so documents can be precomputed. A cross-encoder reads the pair together and scores relevance more accurately but cannot pre-index millions of docs.