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.

Practice

1. What is the main idea behind few-shot learning with prompts in NLP?

easy

A. Fine-tuning a model with many epochs on labeled data

B. Training a model with a large dataset from scratch

C. Using no examples and relying only on model pretraining

D. Using a few examples in a prompt to teach a model a new task

Solution

1. Step 1: Understand few-shot learning concept

   Few-shot learning means teaching a model with only a few examples instead of large datasets.

2. Step 2: Identify the role of prompts

   Prompts provide examples and instructions to guide the model on the new task.

3. Final Answer:

   Using a few examples in a prompt to teach a model a new task -> Option D

4. Quick Check:

   Few-shot learning = few examples + prompt [OK]

Hint: Few-shot means few examples in prompt, not full training [OK]

Common Mistakes:

• Confusing few-shot with full training
• Thinking no examples are used
• Mixing few-shot with fine-tuning

2. Which of the following is the correct way to format a few-shot prompt for sentiment analysis?

easy

A. "Sentiment: Positive Review: I love this movie!\nSentiment: Negative Review: This was bad.\nSentiment: Neutral Review: The plot was..."

B. "Review: I love this movie! Sentiment: Positive\nReview: This was bad. Sentiment: Negative\nReview: The plot was..."

C. "I love this movie! Positive\nThis was bad. Negative\nThe plot was... Neutral"

D. "Review: Positive I love this movie!\nReview: Negative This was bad.\nReview: Neutral The plot was..."

Solution

1. Step 1: Check prompt structure for clarity

   The prompt should clearly separate examples with labels and inputs, like 'Review: ... Sentiment: ...'.

2. Step 2: Identify correct example formatting

   "Review: I love this movie! Sentiment: Positive\nReview: This was bad. Sentiment: Negative\nReview: The plot was..." uses a consistent pattern: input first, then label, separated by new lines.

3. Final Answer:

   "Review: I love this movie! Sentiment: Positive\nReview: This was bad. Sentiment: Negative\nReview: The plot was..." -> Option B

4. Quick Check:

   Clear input-label pairs = "Review: I love this movie! Sentiment: Positive\nReview: This was bad. Sentiment: Negative\nReview: The plot was..." [OK]

Hint: Use clear input-label pairs separated by new lines [OK]

Common Mistakes:

• Mixing label before input
• Not separating examples clearly
• Omitting labels or inputs

3. Given this few-shot prompt for a model:

"Translate English to French:\nEnglish: Hello\nFrench: Bonjour\nEnglish: Thank you\nFrench: Merci\nEnglish: Good night\nFrench:"

What is the most likely model output?

medium

A. Bonne nuit

B. Bonsoir

C. Salut

D. Au revoir

Solution

1. Step 1: Understand prompt pattern

   The prompt shows English phrases with their French translations, ending with English: Good night and expecting French output.

2. Step 2: Recall correct French translation

   The French for "Good night" is "Bonne nuit", matching the pattern of direct translation.

3. Final Answer:

   Bonne nuit -> Option A

4. Quick Check:

   Good night = Bonne nuit [OK]

Hint: Match prompt pattern and translate phrase literally [OK]

Common Mistakes:

• Choosing a greeting instead of night farewell
• Confusing similar French words
• Ignoring prompt pattern

4. You wrote this few-shot prompt for a model to classify animals:

"Animal: Dog\nType: Mammal\nAnimal: Eagle\nType: Bird\nAnimal: Salmon\nType:"

The model outputs "Dog" instead of the expected animal type. What is the likely error?

medium

A. The prompt repeats the animal name instead of type

B. The model was not given any examples

C. The prompt lacks clear separation between examples

D. The model cannot handle few-shot prompts

Solution

1. Step 1: Analyze prompt structure

   The prompt shows pairs of Animal and Type, but the last line expects the type for Salmon.

2. Step 2: Identify output mismatch

   The model outputs "Dog" (an animal) instead of a type, likely because the prompt repeats animal names where types should be.

3. Final Answer:

   The prompt repeats the animal name instead of type -> Option A

4. Quick Check:

   Output animal instead of type = prompt error [OK]

Hint: Check if prompt asks for correct label, not repeated input [OK]

Common Mistakes:

• Assuming model can't handle few-shot
• Ignoring prompt formatting errors
• Thinking examples are missing

5. You want to build a few-shot prompt to classify movie reviews as Positive or Negative. Which approach will most likely improve model accuracy?

hard

A. Use only one example of a positive review to keep prompt short

B. Avoid giving any examples and rely on model knowledge

C. Include clear examples with both positive and negative reviews and their labels

D. Add unrelated text to make prompt longer

Solution

1. Step 1: Understand few-shot prompt impact

   Providing clear examples of both classes helps the model learn the task better.

2. Step 2: Evaluate options for accuracy

   Include clear examples with both positive and negative reviews and their labels gives balanced examples, improving accuracy; others reduce clarity or add noise.

3. Final Answer:

   Include clear examples with both positive and negative reviews and their labels -> Option C

4. Quick Check:

   Balanced examples = better accuracy [OK]

Hint: Use clear, balanced examples for best few-shot results [OK]

Common Mistakes:

• Using too few or unbalanced examples
• Relying on no examples
• Adding irrelevant information