Bias in generative models in Prompt Engineering / GenAI - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is bias in generative models?

Bias in generative models means the model produces outputs that unfairly favor or discriminate against certain groups or ideas, often reflecting stereotypes or imbalanced data.

beginner

How can biased training data affect a generative model?

If the training data has more examples from one group or viewpoint, the model learns to generate outputs that reflect that imbalance, leading to unfair or inaccurate results.

intermediate

Name one common source of bias in generative AI models.

One common source is historical or social biases present in the data used to train the model, such as stereotypes or underrepresentation of certain groups.

beginner

Why is it important to detect and reduce bias in generative models?

Because biased outputs can harm people by spreading stereotypes, misinformation, or unfair treatment, reducing trust and causing real-world negative effects.

intermediate

What is one method to reduce bias in generative models?

One method is to carefully curate and balance the training data to represent diverse groups fairly, or to use techniques that adjust the model’s outputs to be more neutral.

What does bias in a generative model usually come from?

A Imbalanced or biased training data

B Random noise in the model

C Too many layers in the neural network

D Using a GPU for training

Bias mostly comes from the data the model learns from, especially if it is not balanced or contains stereotypes.

Which of these is a risk of biased generative models?

A Using more memory

B Producing unfair or harmful content

C Running slower on computers

D Generating random numbers

Biased models can create outputs that are unfair or harmful, affecting people negatively.

How can we check if a generative model is biased?

A By counting the number of layers

B By checking the file size

C By measuring training speed

D By analyzing its outputs for fairness and diversity

We look at the model’s outputs to see if they treat groups fairly and represent diversity.

Which approach helps reduce bias in generative models?

A Balancing training data

B Adding more hidden layers

C Increasing batch size

D Using a different optimizer

Balancing the data helps the model learn fairly about all groups.

Why might a generative model reflect stereotypes?

A Because the model uses too much memory

B Because the model is too simple

C Because stereotypes exist in the training data

D Because the model is trained on random noise

If stereotypes are in the data, the model can learn and repeat them.

Explain what bias in generative models is and why it matters.

Think about how unfair outputs can affect people.

Describe one way to detect and one way to reduce bias in generative AI.

Consider both looking at results and changing the data or model.

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