Why fine-tuning adapts models to domains in Prompt Engineering / GenAI - Quick Recap

Recall & Review

beginner

What is fine-tuning in machine learning?

Fine-tuning is the process of taking a pre-trained model and training it a bit more on a specific dataset to make it better at a particular task or domain.

beginner

Why do we fine-tune models instead of training from scratch?

Fine-tuning saves time and resources because the model already knows general patterns. It just needs small adjustments to work well in a new domain.

intermediate

How does fine-tuning help a model adapt to a new domain?

Fine-tuning adjusts the model’s knowledge to focus on the specific language, style, or data patterns of the new domain, improving accuracy and relevance.

beginner

What happens if you don’t fine-tune a model for a specific domain?

The model might give less accurate or less relevant results because it only understands general information, not the special details of the new domain.

advanced

Can fine-tuning cause a model to forget what it learned before? What is this called?

Yes, if done too much, fine-tuning can cause the model to forget previous knowledge. This is called "catastrophic forgetting." Careful training helps avoid this.

What is the main goal of fine-tuning a pre-trained model?

A To adapt the model to perform better on a specific domain

B To make the model larger and slower

C To erase all previous knowledge from the model

D To train the model from zero without any prior data

Fine-tuning adjusts a pre-trained model to work better on a specific domain by training it on new, relevant data.

Why is fine-tuning more efficient than training a model from scratch?

A Because it always produces perfect results

B Because it ignores previous training completely

C Because it requires more computing power

D Because it uses less data and less time by building on existing knowledge

Fine-tuning leverages the model’s existing knowledge, so it needs less data and time to adapt to a new domain.

What risk can happen if fine-tuning is done too aggressively?

A The model will stop working completely

B The model will become too general

C The model may forget previous knowledge (catastrophic forgetting)

D The model will become slower but more accurate

Too much fine-tuning can cause the model to lose important general knowledge, a problem called catastrophic forgetting.

Which of these is NOT a reason to fine-tune a model?

A To improve performance on a specific domain

B To reduce the model size drastically

C To adjust to new data styles or language

D To increase relevance of predictions

Fine-tuning focuses on improving performance and relevance, not necessarily reducing model size.

What kind of data is used during fine-tuning?

A Data specific to the target domain

B Random unrelated data

C Only the original training data

D No data is used during fine-tuning

Fine-tuning uses data from the specific domain to help the model learn relevant patterns and details.

Explain in your own words why fine-tuning helps a model perform better in a new domain.

Think about how learning a new skill builds on what you already know.

Describe what could happen if a model is fine-tuned too much on a small dataset.

Consider what happens if you focus too much on one thing and forget others.