Hallucination detection in Prompt Engineering / GenAI - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to import the library used for natural language processing.

Prompt Engineering / GenAI

import [1]

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

Amatplotlib

Bnumpy

Ctensorflow

Dtransformers

Attempts:

3 left

💡 Hint

Common Mistakes

Importing unrelated libraries like numpy or matplotlib.

Using tensorflow which is more general for deep learning but not specific for language models.

The 'transformers' library is commonly used for working with language models, which are essential for hallucination detection.

2fill in blank

medium

Complete the code to load a pre-trained language model for hallucination detection.

Prompt Engineering / GenAI

model = transformers.AutoModelForSequenceClassification.from_pretrained('[1]')

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

Aresnet50

Bbert-base-uncased

Cgpt2

Dvgg16

Attempts:

3 left

💡 Hint

Common Mistakes

Choosing image models like resnet50 or vgg16.

Choosing GPT-2 which is a generative model, not directly for classification.

The 'bert-base-uncased' model is a common choice for sequence classification tasks like hallucination detection.

3fill in blank

hard

Fix the error in the code to tokenize input text correctly for the model.

Prompt Engineering / GenAI

inputs = tokenizer('[1]', return_tensors='pt')

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

A['This is a test']

B['This', 'is', 'a', 'test']

C'This is a test'

DThis is a test

Attempts:

3 left

💡 Hint

Common Mistakes

Passing a list of words instead of a string.

Passing a list containing the string.

The tokenizer expects a string input, so the text should be passed as a string, not a list or tokens.

4fill in blank

hard

Fill both blanks to compute the model's prediction and extract the predicted label.

Prompt Engineering / GenAI

outputs = model(**[1])
prediction = outputs.logits.[2](dim=1).argmax()

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

Ainputs

Bsoftmax

Csigmoid

Dinput_ids

Attempts:

3 left

💡 Hint

Common Mistakes

Passing raw input_ids instead of the full inputs dictionary.

Using sigmoid instead of softmax for multi-class classification.

The model expects the tokenized inputs as keyword arguments, and softmax converts logits to probabilities before argmax finds the predicted label.

5fill in blank

hard

Fill all three blanks to create a function that detects hallucination by thresholding the prediction score.

Prompt Engineering / GenAI

def detect_hallucination(text):
    inputs = tokenizer(text, return_tensors='pt')
    outputs = model(**[1])
    probs = torch.nn.functional.[2](outputs.logits, dim=1)
    score = probs[0][[3]].item()
    return score > 0.5

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

Ainputs

Bsoftmax

C1

Dsigmoid

Attempts:

3 left

💡 Hint

Common Mistakes

Using sigmoid instead of softmax for multi-class outputs.

Indexing the wrong class probability.

Passing raw text instead of tokenized inputs to the model.

The function uses the tokenized inputs, applies softmax to get probabilities, and checks the probability of class 1 to decide if hallucination is detected.

Practice

1. What is the main goal of hallucination detection in AI models?

easy

A. To improve the speed of AI responses

B. To find when AI says things that are not true

C. To increase the size of AI training data

D. To reduce the cost of running AI models

Solution

1. Step 1: Understand the term 'hallucination' in AI context

   Hallucination means AI generates false or made-up information.

2. Step 2: Identify the purpose of detection

   Hallucination detection aims to find these false outputs to improve trust.

3. Final Answer:

   To find when AI says things that are not true -> Option B

4. Quick Check:

   Hallucination detection = find false AI outputs [OK]

Hint: Hallucination means false info; detection finds it [OK]

Common Mistakes:

• Confusing hallucination with model speed or size
• Thinking it improves training data
• Assuming it reduces cost directly

2. Which of the following is a correct simple method to detect hallucination in AI output?

easy

A. Compare AI output with trusted information using similarity scores

B. Increase the AI model size to reduce hallucination

C. Train AI with random noise data

D. Ignore output and only check input data

Solution

1. Step 1: Recall simple hallucination detection methods

   Simple methods compare AI output to trusted facts using similarity measures.

2. Step 2: Evaluate options

   Only Compare AI output with trusted information using similarity scores describes this correct approach; others are unrelated or incorrect.

3. Final Answer:

   Compare AI output with trusted information using similarity scores -> Option A

4. Quick Check:

   Simple detection = compare output to facts [OK]

Hint: Check AI output against trusted info for quick detection [OK]

Common Mistakes:

• Thinking bigger models reduce hallucination automatically
• Using random noise data for training
• Ignoring output in detection

3. Given this Python code snippet for hallucination detection, what is the output?

trusted_facts = ['Paris is the capital of France']
ai_output = 'Paris is the capital of France'

similarity_score = 1.0 if ai_output in trusted_facts else 0.0
print(similarity_score)

medium

A. 1.0

B. 0.0

C. Error

D. None

Solution

1. Step 1: Check if AI output matches trusted facts

   The string 'Paris is the capital of France' is exactly in the trusted_facts list.

2. Step 2: Determine similarity score

   Since the output is found, similarity_score is set to 1.0 and printed.

3. Final Answer:

   1.0 -> Option A

4. Quick Check:

   Output matches fact = 1.0 [OK]

Hint: If output in facts, similarity = 1.0 [OK]

Common Mistakes:

• Confusing list membership with substring check
• Expecting 0.0 if exact match
• Thinking code raises error

4. Find the error in this hallucination detection code snippet:

trusted_facts = ['Water boils at 100 degrees Celsius']
ai_output = 'Water boils at 90 degrees Celsius'

if ai_output == trusted_facts:
    print('No hallucination')
else:
    print('Possible hallucination')

medium

A. ai_output should be a list, not string

B. Missing import statement for list

C. Comparing string to list directly causes wrong result

D. Syntax error in if statement

Solution

1. Step 1: Analyze the comparison in if statement

   The code compares a string (ai_output) to a list (trusted_facts) using ==, which is always False.

2. Step 2: Understand impact on hallucination detection

   This causes the code to always print 'Possible hallucination' even if output matches a fact.

3. Final Answer:

   Comparing string to list directly causes wrong result -> Option C

4. Quick Check:

   String == list comparison is incorrect [OK]

Hint: Compare string to string, not string to list [OK]

Common Mistakes:

• Thinking syntax error exists
• Assuming ai_output must be list
• Missing import statements

5. You want to detect hallucinations in AI-generated medical advice. Which approach best combines accuracy and reliability?

hard

A. Trust AI output without verification to save time

B. Only check if AI output length is less than 100 characters

C. Randomly accept or reject AI output

D. Use advanced fact-checking models comparing AI output to verified medical databases

Solution

1. Step 1: Consider the importance of accuracy in medical advice

   Medical advice must be accurate and reliable to avoid harm.

2. Step 2: Evaluate detection methods

   Advanced fact-checking against verified databases ensures correctness and reduces hallucination risk.

3. Step 3: Reject unreliable or random methods

   Ignoring verification or random acceptance risks dangerous errors.

4. Final Answer:

   Use advanced fact-checking models comparing AI output to verified medical databases -> Option D

5. Quick Check:

   Fact-checking with trusted data = best for medical AI [OK]

Hint: Use trusted databases for fact-checking medical AI output [OK]

Common Mistakes:

• Ignoring verification for speed
• Using output length as accuracy measure
• Random acceptance of AI output