Why fine-tuning adapts models to domains in Prompt Engineering / GenAI - Challenge Your Understanding

Challenge - 5 Problems

🧠 Conceptual

intermediate

Why does fine-tuning improve model performance on a specific domain?

Imagine you have a general language model trained on many topics. You want it to work better on medical texts. Why does fine-tuning the model on medical data help?

A Fine-tuning changes the model’s architecture to add new layers for medical terms.

B Fine-tuning removes all previous knowledge so the model only knows medical data.

C Fine-tuning increases the model size to handle more data.

D Fine-tuning adjusts the model’s knowledge to focus on patterns and vocabulary specific to the medical domain.

💡 Hint

Think about how learning new examples helps a student focus on a topic.

Fine-tuning updates the model’s parameters so it better recognizes and predicts patterns in the new domain, without losing all previous knowledge.

❓ Predict Output

intermediate

What is the output after fine-tuning on domain data?

Given a simple model predicting sentiment, after fine-tuning on movie reviews, what will the prediction be for a new movie review?

Prompt Engineering / GenAI

class SimpleSentimentModel:
    def __init__(self):
        self.positive_words = {'good', 'great', 'fun'}
    def predict(self, text):
        return 'Positive' if any(word in text.split() for word in self.positive_words) else 'Negative'

model = SimpleSentimentModel()
# Fine-tuning adds 'amazing' to positive words
model.positive_words.add('amazing')

print(model.predict('The movie was amazing and fun'))

A Negative

B Positive

C Error: 'amazing' not recognized

D Neutral

💡 Hint

Check if the new word added during fine-tuning is in the input text.

Fine-tuning added 'amazing' to the positive words set, so the model predicts 'Positive' for the input containing 'amazing'.

❓ Model Choice

advanced

Which model is best suited for fine-tuning to a new domain?

You want to adapt a language model to a specialized domain with limited data. Which model type is best to fine-tune?

A A model trained from scratch on the new domain data

B A small model trained only on the new domain data

C A large pre-trained model with general knowledge

D A model with no pre-training

💡 Hint

Think about using existing knowledge and adapting it.

Large pre-trained models have broad knowledge and can be fine-tuned efficiently on small domain data, improving performance without starting from zero.

❓ Hyperparameter

advanced

Which hyperparameter setting helps prevent overfitting during fine-tuning?

When fine-tuning a model on a small domain dataset, which hyperparameter adjustment helps avoid overfitting?

A Use a smaller learning rate

B Use a larger batch size without change

C Remove dropout layers

D Increase the number of training epochs drastically

💡 Hint

Think about making smaller, careful updates to the model.

A smaller learning rate makes the model update weights gently, reducing the risk of overfitting to small data.

❓ Metrics

expert

Which metric best shows improved domain adaptation after fine-tuning?

You fine-tune a model on a new domain. Which metric best indicates the model learned domain-specific patterns?

A Higher accuracy on domain-specific test data

B Lower training loss on original general data

C Increased model size after fine-tuning

D Faster training time during fine-tuning

💡 Hint

Think about how well the model performs on new domain examples.

Higher accuracy on domain-specific test data shows the model adapted well to the new domain after fine-tuning.