Moderate Chunking Question 133 of 223

How does chunk size affect retrieval quality?

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

PICTURE THIS: A SENTENCE BECOMES TOKENS

The model does not read letters like humans. It reads these pieces, then predicts the next one.

Simple meaning

Tiny chunks match precisely but lose surrounding meaning.

1

WHY — Tokens instead of words?

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

This is a process

question about Chunking.

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.

2

STEPS — What happens with tokens?

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

  1. 1
    Tiny chunks match precisely

    but lose surrounding meaning.

  2. 2
    Huge chunks match vaguely

    and waste the context window.

  3. 3
    Sweep sizes on a

    labeled retrieval set

  4. 4
    there is no universal

    512-token rule.

  5. 5
    Next token

    The model scores what should come next.

  6. 6
    Decode

    IDs turn back into readable text.

3

EXAMPLE — See it in action

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

Input text
“Huge chunks match vaguely and waste the context window.”
Tokenized output
Hugechunksmatchvaguelyandwaste
Token IDs (example)
2987408337471632900

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

Key takeaway

Tiny chunks match precisely but lose surrounding meaning. Huge chunks match vaguely and waste the context window.

Chat with us