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.