Bias in generative models in Prompt Engineering / GenAI - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to load a pre-trained generative model.

Prompt Engineering / GenAI

model = load_model('[1]')

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

Abert-base-uncased

Bgpt2

Cresnet50

Dvgg16

Attempts:

3 left

💡 Hint

Common Mistakes

Choosing image models like resnet50 or vgg16 which are not generative text models.

Selecting bert-base-uncased which is mainly for understanding text, not generation.

The gpt2 model is a popular generative language model used for text generation.

2fill in blank

medium

Complete the code to generate text from the model.

Prompt Engineering / GenAI

output = model.generate(input_ids, max_length=[1])

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

A10

B0

C50

D-1

Attempts:

3 left

💡 Hint

Common Mistakes

Using 0 or negative numbers which prevent generation.

Choosing too small a number like 10 which limits output length.

Setting max_length to 50 allows the model to generate up to 50 tokens of text.

3fill in blank

hard

Fix the error in the code to detect bias in generated text.

Prompt Engineering / GenAI

if '[1]' in generated_text.lower():
    print('Potential bias detected')

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

Aoffensive

Bgendered words

Cbias

Dstereotypes

Attempts:

3 left

💡 Hint

Common Mistakes

Checking for generic words like 'bias' which may not appear literally.

Using 'gendered words' which is too specific without context.

Checking for stereotypes helps identify biased content in generated text.

4fill in blank

hard

Fill both blanks to filter out biased words from generated output.

Prompt Engineering / GenAI

filtered_output = [word for word in generated_text.split() if word.lower() [1] biased_words and word.lower() [2] biased_words]

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

Anot in

Bin

C==

D!=

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'in' which would keep biased words instead of filtering them out.

Using '==' which would only keep biased words.

We want to keep words that are not in the biased words list and are not equal to any biased word.

5fill in blank

hard

Fill all three blanks to calculate bias score from generated text.

Prompt Engineering / GenAI

bias_score = sum(1 for word in generated_text.split() if word.lower() [1] biased_words) / [2](generated_text.split())
if bias_score > [3]:
    print('High bias detected')

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

Ain

Blen

C0.1

Dnot in

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'not in' which counts non-biased words instead.

Using a threshold too high or too low for bias detection.

The code counts biased words (in biased_words), divides by total words (len), and checks if the bias score is greater than 0.1.

Practice

1. What is the main cause of bias in generative AI models?

easy

A. The speed of the computer

B. The programming language used

C. The data used to train the model

D. The color of the user interface

Solution

1. Step 1: Understand what bias means in generative models

   Bias means the model gives unfair or unbalanced results.

2. Step 2: Identify the source of bias

   Bias mainly comes from the data used to train the model, as it reflects existing patterns or prejudices.

3. Final Answer:

   The data used to train the model -> Option C

4. Quick Check:

   Bias source = training data [OK]

Hint: Bias mostly comes from training data, not code or hardware [OK]

Common Mistakes:

• Thinking bias comes from programming language
• Blaming hardware speed for bias
• Confusing UI design with bias

2. Which of the following is the correct way to describe bias in generative models?

easy

A. Bias means the model produces unfair or unbalanced outputs

B. Bias means the model always predicts correctly

C. Bias means the model runs faster on some computers

D. Bias means the model uses more memory

Solution

1. Step 1: Define bias in the context of generative models

   Bias refers to unfair or unbalanced outputs, not performance or resource use.

2. Step 2: Match the correct description

   Bias means the model produces unfair or unbalanced outputs correctly states bias as unfair or unbalanced outputs.

3. Final Answer:

   Bias means the model produces unfair or unbalanced outputs -> Option A

4. Quick Check:

   Bias = unfair outputs [OK]

Hint: Bias is about fairness in output, not speed or memory [OK]

Common Mistakes:

• Confusing bias with model accuracy
• Mixing bias with hardware performance
• Thinking bias relates to memory use

3. Consider a generative model trained on text data mostly from one culture. What is likely to happen when it generates stories about other cultures?

medium

A. It may produce biased or stereotyped stories about other cultures

B. It will generate perfectly balanced stories about all cultures

C. It will refuse to generate any story about other cultures

D. It will generate stories faster for other cultures

Solution

1. Step 1: Understand training data influence

   The model learns patterns from its training data, so if data is mostly from one culture, it lacks diversity.

2. Step 2: Predict output behavior

   When asked about other cultures, the model may produce biased or stereotyped stories due to limited or skewed data.

3. Final Answer:

   It may produce biased or stereotyped stories about other cultures -> Option A

4. Quick Check:

   Limited data causes biased outputs [OK]

Hint: Limited data diversity causes biased outputs [OK]

Common Mistakes:

• Assuming model is unbiased regardless of data
• Thinking model refuses to generate unknown topics
• Confusing speed with bias

4. You notice your generative model outputs biased text favoring one gender. Which step can help fix this issue?

medium

A. Use a smaller batch size during training

B. Increase the model's learning rate

C. Reduce the number of training epochs

D. Add more balanced and diverse training data

Solution

1. Step 1: Identify cause of bias

   Bias often comes from unbalanced training data that favors one group.

2. Step 2: Choose corrective action

   Adding more balanced and diverse data helps the model learn fairer patterns and reduce bias.

3. Final Answer:

   Add more balanced and diverse training data -> Option D

4. Quick Check:

   Balanced data reduces bias [OK]

Hint: Fix bias by improving training data diversity [OK]

Common Mistakes:

• Changing learning rate without addressing data
• Adjusting batch size unrelated to bias
• Reducing epochs without fixing data

5. A company wants to reduce bias in its generative model that creates job descriptions. Which combined approach is best to improve fairness?

hard

A. Remove all rare words from the training data

B. Use diverse training data and add fairness constraints during model training

C. Train the model faster with fewer epochs

D. Only increase the model size without changing data

Solution

1. Step 1: Understand bias reduction methods

   Bias can be reduced by improving data diversity and applying fairness rules during training.

2. Step 2: Evaluate options

   Use diverse training data and add fairness constraints during model training combines better data and fairness constraints, which is more effective than just changing model size or training speed.

3. Final Answer:

   Use diverse training data and add fairness constraints during model training -> Option B

4. Quick Check:

   Data + fairness constraints = less bias [OK]

Hint: Combine diverse data with fairness rules for best bias fix [OK]

Common Mistakes:

• Thinking bigger model alone fixes bias
• Speeding training reduces bias (it doesn't)
• Removing rare words harms data diversity