Bias and fairness in NLP - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to load a pre-trained NLP model for bias analysis.

NLP

from transformers import pipeline
nlp = pipeline([1])

Drag options to blanks, or click blank then click option'

A"token-classification"

B"text-generation"

C"translation"

D"sentiment-analysis"

Attempts:

3 left

💡 Hint

Common Mistakes

Choosing 'text-generation' which creates text but doesn't analyze bias.

Using 'translation' which changes language but doesn't detect bias.

The sentiment-analysis pipeline is commonly used to analyze bias in text by detecting positive or negative sentiment.

2fill in blank

medium

Complete the code to calculate bias metric using word embeddings.

NLP

import numpy as np
bias_score = np.dot(embedding1, [1])

Drag options to blanks, or click blank then click option'

Aembedding2

Bembedding4

Cembedding3

Dembedding5

Attempts:

3 left

💡 Hint

Common Mistakes

Using an unrelated embedding that doesn't correspond to the comparison concept.

Confusing the embeddings and using the same embedding twice.

The dot product between two embeddings measures similarity, which helps quantify bias.

3fill in blank

hard

Fix the error in the code to remove gender bias from word embeddings.

NLP

def debias_embedding(embedding, gender_direction):
    corrected = embedding - embedding[1]gender_direction) * gender_direction
    return corrected

Drag options to blanks, or click blank then click option'

A*

B.dot(

C-

D+

Attempts:

3 left

💡 Hint

Common Mistakes

Using multiplication (*) instead of dot product for projection.

Using addition (+) which increases bias instead of removing it.

The dot product (embedding.dot(gender_direction)) projects the embedding onto the gender direction for removal.

4fill in blank

hard

Fill both blanks to create a dictionary comprehension that filters biased words.

NLP

biased_words = {word: score for word, score in scores.items() if score [1] threshold and len(word) [2] 3}

Drag options to blanks, or click blank then click option'

A>

B<

C>=

D<=

Attempts:

3 left

💡 Hint

Common Mistakes

Using '<' for score which selects low bias scores.

Using '<=' for length which includes very short words.

We filter words with scores greater than the threshold and length greater or equal to 3 to focus on meaningful biased words.

5fill in blank

hard

Fill all three blanks to create a fairness evaluation function.

NLP

def evaluate_fairness(predictions, labels):
    correct = sum(1 for p, l in zip(predictions, labels) if p [1] l)
    total = len(labels)
    fairness_score = correct [2] total
    return fairness_score [3] 1.0

Drag options to blanks, or click blank then click option'

A==

B/

C<=

D>=

Attempts:

3 left

💡 Hint

Common Mistakes

Using assignment '=' instead of comparison '=='.

Using multiplication '*' instead of division '/' for accuracy.

Checking fairness_score <= 1.0 which is incorrect for minimum fairness.

We count correct predictions (p == l), calculate accuracy (correct / total), and check if fairness_score is at least 1.0 (>= 1.0).

Practice

1. What does bias in NLP models usually mean?

easy

A. The model always predicts correctly

B. Unfair treatment of some groups by the model

C. The model runs faster on some data

D. The model uses more memory for some inputs

Solution

1. Step 1: Understand the meaning of bias in NLP

   Bias refers to when a model treats some groups unfairly, often due to skewed training data or design.

2. Step 2: Compare options to definition

   Only Unfair treatment of some groups by the model describes unfair treatment, which matches the definition of bias in NLP.

3. Final Answer:

   Unfair treatment of some groups by the model -> Option B

4. Quick Check:

   Bias = Unfair treatment [OK]

Hint: Bias means unfairness in model predictions [OK]

Common Mistakes:

• Confusing bias with model speed or memory use
• Thinking bias means always correct predictions

2. Which of the following is the correct way to check fairness in an NLP model?

easy

A. Count the number of layers in the model

B. Check if the model uses GPU acceleration

C. Compare accuracy across different demographic groups

D. Measure the model's training time

Solution

1. Step 1: Identify fairness checking methods

   Fairness is checked by comparing performance metrics like accuracy across groups to ensure equal treatment.

2. Step 2: Evaluate options

   Only Compare accuracy across different demographic groups relates to fairness by comparing accuracy across groups; others are unrelated to fairness.

3. Final Answer:

   Compare accuracy across different demographic groups -> Option C

4. Quick Check:

   Fairness check = Compare accuracy by group [OK]

Hint: Fairness means equal accuracy for all groups [OK]

Common Mistakes:

• Confusing fairness with model speed or architecture
• Ignoring group-based performance differences

3. Consider this Python code snippet checking fairness metrics:

group_accuracies = {'groupA': 0.85, 'groupB': 0.60}
if abs(group_accuracies['groupA'] - group_accuracies['groupB']) > 0.2:
    print('Fairness issue detected')
else:
    print('No fairness issue')

What will this code print?

medium

A. KeyError

B. No fairness issue

C. SyntaxError

D. Fairness issue detected

Solution

1. Step 1: Calculate difference in accuracies

   The difference is |0.85 - 0.60| = 0.25, which is greater than 0.2.

2. Step 2: Evaluate the if condition

   Since 0.25 > 0.2, the condition is true, so it prints 'Fairness issue detected'.

3. Final Answer:

   Fairness issue detected -> Option D

4. Quick Check:

   Difference 0.25 > 0.2 = Fairness issue [OK]

Hint: Check if accuracy difference > threshold for fairness [OK]

Common Mistakes:

• Miscomputing the absolute difference
• Confusing greater than with less than
• Expecting syntax or key errors

4. This code tries to calculate fairness but has a bug:

metrics = {'group1': {'accuracy': 0.9}, 'group2': {'accuracy': 0.85}}
diff = metrics['group1']['accuracy'] - metrics['group3']['accuracy']
if abs(diff) > 0.05:
    print('Bias detected')

What is the error and how to fix it?

medium

A. KeyError because 'group3' does not exist; fix by checking keys first

B. SyntaxError due to missing colon; fix by adding colon

C. TypeError because accuracy is not a number; fix by converting to float

D. No error; code runs fine

Solution

1. Step 1: Identify the error cause

   The code accesses metrics['group3'], which is not in the dictionary, causing a KeyError.

2. Step 2: Suggest fix

   Check if 'group3' exists in metrics before accessing or handle missing keys to avoid error.

3. Final Answer:

   KeyError because 'group3' does not exist; fix by checking keys first -> Option A

4. Quick Check:

   Missing key access = KeyError [OK]

Hint: Check dictionary keys before access to avoid KeyError [OK]

Common Mistakes:

• Assuming all keys exist without checking
• Confusing KeyError with SyntaxError or TypeError

5. You have an NLP sentiment model that predicts positive or negative sentiment. You notice it predicts positive sentiment 90% for group A but only 60% for group B, though both groups have similar real sentiment. What is the best way to improve fairness?

hard

A. Collect more balanced training data including both groups equally

B. Increase model size to improve overall accuracy

C. Use a faster optimizer to train the model

D. Remove group B data from training to avoid confusion

Solution

1. Step 1: Understand the fairness problem

   The model predicts differently for groups with similar real sentiment, indicating bias likely from unbalanced data.

2. Step 2: Choose the best fix

   Collecting balanced data ensures the model learns equally from both groups, improving fairness.

3. Final Answer:

   Collect more balanced training data including both groups equally -> Option A

4. Quick Check:

   Balanced data improves fairness [OK]

Hint: Balanced data helps fix bias in predictions [OK]

Common Mistakes:

• Thinking bigger models fix bias automatically
• Ignoring data imbalance as cause of unfairness
• Removing data from minority groups