Few-shot learning with prompts in NLP - Practice Problems & Coding Challenges

Challenge - 5 Problems

🧠 Conceptual

intermediate

What is the main advantage of few-shot learning with prompts?

Few-shot learning with prompts allows a model to perform new tasks with very few examples. What is the primary advantage of this approach compared to traditional supervised learning?

A It ignores the context of the input data.

B It requires a large labeled dataset for every new task.

C It trains the model from scratch for each new task.

D It enables the model to generalize to new tasks with minimal labeled data.

💡 Hint

Think about how few-shot learning reduces the need for large datasets.

Few-shot learning with prompts helps models adapt to new tasks using only a few examples, reducing the need for large labeled datasets.

❓ Predict Output

intermediate

Output of a few-shot prompt example

Given the following prompt to a language model, what is the expected output?

NLP

prompt = '''Translate English to French:

English: "I love apples."
French: "J'aime les pommes."

English: "She is happy."
French: '''

# Model generates the French translation for "She is happy."

A "Elle est content."

B "Elle est heureuse."

C "Elle est triste."

D "Elle est faim."

💡 Hint

Consider the correct French translation for "She is happy."

The correct French translation of "She is happy." is "Elle est heureuse." which matches option B.

❓ Model Choice

advanced

Choosing a model for few-shot learning with prompts

You want to perform few-shot learning on a text classification task using prompts. Which model type is best suited for this?

A A large pretrained language model like GPT-3.

B A small CNN trained from scratch on the task data.

C A simple logistic regression on bag-of-words features.

D A decision tree trained on handcrafted features.

💡 Hint

Few-shot learning with prompts works best with large pretrained language models.

Large pretrained language models like GPT-3 have learned broad language patterns and can adapt to new tasks with few examples using prompts.

❓ Hyperparameter

advanced

Key hyperparameter affecting few-shot prompt performance

When using few-shot learning with prompts, which hyperparameter most directly affects how many examples are shown in the prompt?

A Learning rate

B Batch size

C Number of shots

D Dropout rate

💡 Hint

Think about the term that describes how many examples you provide in the prompt.

The number of shots refers to how many example input-output pairs are included in the prompt to guide the model.

❓ Metrics

expert

Evaluating few-shot prompt learning performance

You have a few-shot prompt-based model for sentiment classification. Which metric is most appropriate to evaluate its performance on a balanced test set?

A Accuracy

B Perplexity

C Mean Squared Error (MSE)

D BLEU score

💡 Hint

Consider the task is classification and the test set is balanced.

Accuracy measures the proportion of correct predictions and is suitable for balanced classification tasks.