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.