High RAG Question 156 of 223

How do you evaluate a RAG system end to end, including RAGAS-style metrics?

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

PICTURE THIS: OVERFITTING

UnderfitToo simple

Good fitReal pattern

OverfitMemorised noise

Simple meaning

Score retrieval (recall, MRR), then generation (faithfulness, context precision, answer relevancy).

WHY — Tokens instead of words?

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

This is a process

question about RAG.

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 with tokens?

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

1
Score retrieval (recall, MRR),
then generation (faithfulness, context precision, answer relevancy).
2
RAGAS-style pipelines use LLM
judges plus the retrieved set.
3
Human spot checks remain
necessary because judges inherit model biases.
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

“RAGAS-style pipelines use LLM judges plus the retrieved set.”

Tokenized output

RAGASstylepipelinesuseLLMjudges

Token IDs (example)

2987408337471632900

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

Key takeaway

Score retrieval (recall, MRR), then generation (faithfulness, context precision, answer relevancy). RAGAS-style pipelines use LLM judges plus the retrieved set.