Moderate Attention Question 81 of 223

How does self-attention differ from cross-attention?

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

PICTURE THIS: AN LLM TURN

Text inTokens

TransformerAttention

Text outNext token

Simple meaning

Self-attention uses queries, keys, and values from the same sequence.

WHY — Tokens instead of words?

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

This is a process

question about Attention.

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
Self-attention uses queries, keys,
and values from the same sequence.
2
Cross-attention uses queries from
the decoder and keys and values from the encoder or another source.
3
Cross-attention is how encoder-decoder
models condition generation on the input document.
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

“Cross-attention uses queries from the decoder and keys and values from the encod”

Break into beats

Crossattentionusesqueriesfromthe

Speaking order

2987408337471632900

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

Key takeaway

Self-attention uses queries, keys, and values from the same sequence. Cross-attention uses queries from the decoder and keys and values from the encoder or another source.