Bias in generative models in Prompt Engineering / GenAI - Model Pipeline Trace

Model Pipeline - Bias in generative models

This pipeline shows how bias can enter and affect a generative AI model. It starts with data collection, moves through preprocessing and training, and ends with biased or fair generated outputs.

Data Flow - 5 Stages

1Data Collection

10000 text samples→Gather text data from internet sources→10000 text samples

"The doctor said...", "She is a nurse...", "He is a programmer..."

↓

2Preprocessing

10000 text samples→Clean text, remove duplicates, tokenize→10000 tokenized samples

[['The', 'doctor', 'said'], ['She', 'is', 'a', 'nurse']]

↓

3Feature Engineering

10000 tokenized samples→Convert tokens to embeddings→10000 samples x 300 embedding dimensions

[[0.12, -0.05, ..., 0.33], [0.07, 0.11, ..., -0.02]]

↓

4Model Training

10000 samples x 300 embedding dimensions→Train generative model to predict next tokens→Trained generative model

Model learns patterns like 'doctor' often followed by 'he' or 'she'

↓

5Generation

Prompt text→Generate new text based on learned patterns→Generated text

"The nurse said she will help you."

Training Trace - Epoch by Epoch

Loss
2.3 |****
2.0 |*** 
1.7 |**  
1.4 |*   
1.1 |****
     Epochs -> 1 3 5 7

Epoch	Loss ↓	Accuracy ↑	Observation
1	2.3	0.25	Model starts learning basic language patterns
3	1.8	0.40	Model improves but still biased towards frequent patterns
5	1.4	0.55	Model captures more complex patterns, bias remains
7	1.1	0.65	Model converges, bias in data reflected in outputs

Prediction Trace - 4 Layers

Layer 1: Input Prompt

Layer 2: Embedding Layer

Layer 3: Generative Model Prediction

Layer 4: Output Generation

Model Quiz - 3 Questions

At which stage can bias first enter the generative model pipeline?

A Model Training

B Generation

C Data Collection

D Prediction

Key Insight

Bias in generative models often comes from the data they learn from. Even if the model learns well (loss decreases), it can reproduce biases present in the training data. Understanding each pipeline stage helps identify and reduce bias.

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