Easy Evals Question 52 of 223

What are LLM evaluations or evals?

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

PICTURE THIS: DATA SPLIT

Train 70%Val 15%Test 15%

Fit on train, tune on val, report on test once.

Simple meaning

Evals are tests that score model or prompt quality on a dataset.

1

WHY — Tokens instead of words?

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

Evals questions separate people

who only read docs from people who shipped.

Keep it short, concrete,

and tied to GenAI / LLM work.

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
    Evals are tests that

    score model or prompt quality on a dataset.

  2. 2
    They can be exact

    match, rubric scores, or LLM-as-judge.

  3. 3
    Without evals, prompt changes

    are guesswork.

  4. 4
    Context mix

    Attention looks at nearby tokens together.

  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
“They can be exact match, rubric scores, or LLM-as-judge.”
Tokenized output
Theycanbeexactmatchrubric
Token IDs (example)
2987408337471632900

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

Key takeaway

Evals are tests that score model or prompt quality on a dataset. They can be exact match, rubric scores, or LLM-as-judge.

Previous question Next question
Chat with us