Moderate Fine-tuning vs RAG Question 106 of 223

What is catastrophic forgetting in fine-tuning?

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

Further training on a narrow dataset can erase general skills the base model had.

WHY — Tokens instead of words?

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

Fine-tuning vs RAG 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.

STEPS — What happens step by step?

Before you speak the answer, walk the interviewer through these steps:

1
Further training on a
narrow dataset can erase general skills the base model had.
2
Mix general instruction data,
use smaller learning rates, and prefer adapters.
3
For new facts, RAG
avoids overwriting the base model altogether.
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

“Mix general instruction data, use smaller learning rates, and prefer adapters.”

Break into beats

Mixgeneralinstructiondatausesmaller

Speaking order

2987408337471632900

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

Key takeaway

Further training on a narrow dataset can erase general skills the base model had. Mix general instruction data, use smaller learning rates, and prefer adapters.