Temperature and sampling in NLP - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to apply temperature scaling to logits before sampling.

NLP

scaled_logits = logits / [1]

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

Asoftmax

Blogits

Ctemperature

Dsampling

Attempts:

3 left

💡 Hint

Common Mistakes

Using logits directly without scaling.

Multiplying logits by temperature instead of dividing.

Temperature is used to scale logits before sampling to control randomness.

2fill in blank

medium

Complete the code to sample an index from the probability distribution after softmax.

NLP

probabilities = softmax(scaled_logits)
sampled_index = [1](len(probabilities), p=probabilities)

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

Anp.random.choice

Bargmax

Crandom.choice

Dmax

Attempts:

3 left

💡 Hint

Common Mistakes

Using argmax which always picks the highest probability.

Using max which returns the maximum value, not an index.

np.random.choice can sample an index based on given probabilities.

3fill in blank

hard

Fix the error in the code to correctly apply temperature and sample from logits.

NLP

def sample_with_temperature(logits, temperature):
    scaled = logits * [1]
    probs = softmax(scaled)
    return np.random.choice(len(probs), p=probs)

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

Alogits

B1/temperature

Ctemperature

Dnp.exp

Attempts:

3 left

💡 Hint

Common Mistakes

Multiplying logits directly by temperature instead of dividing.

Not scaling logits before softmax.

Logits must be divided by temperature, which is equivalent to multiplying by 1/temperature.

4fill in blank

hard

Fill both blanks to create a function that returns probabilities after temperature scaling.

NLP

def temperature_scaled_probs(logits, [1]):
    scaled_logits = logits / [2]
    return softmax(scaled_logits)

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

Atemperature

Blogits

Dprobabilities

Attempts:

3 left

💡 Hint

Common Mistakes

Using logits as parameter instead of temperature.

Not dividing logits by temperature.

The function takes temperature as input and divides logits by it before softmax.

5fill in blank

hard

Fill all three blanks to implement sampling with temperature scaling and softmax.

NLP

def sample(logits, [1]):
    scaled = logits / [2]
    probs = softmax([3])
    return np.random.choice(len(probs), p=probs)

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

Atemperature

Cscaled

Dlogits

Attempts:

3 left

💡 Hint

Common Mistakes

Using logits instead of scaled logits in softmax.

Not dividing logits by temperature.

The function uses temperature to scale logits, applies softmax to scaled logits, then samples.

Practice

1. What does increasing the temperature parameter in text generation usually do?

easy

A. Makes the output more predictable and repetitive

B. Stops the model from generating any text

C. Makes the output more random and creative

D. Always selects the most probable next word

Solution

1. Step 1: Understand temperature effect on randomness

   Temperature controls how much randomness is added to the word selection process in text generation.

2. Step 2: Relate temperature to creativity

   Higher temperature increases randomness, making the output more creative and less predictable.

3. Final Answer:

   Makes the output more random and creative -> Option C

4. Quick Check:

   Higher temperature = more randomness [OK]

Hint: Higher temperature means more randomness in output [OK]

Common Mistakes:

• Thinking higher temperature makes output more predictable
• Confusing temperature with model size
• Assuming temperature stops generation

2. Which of the following code snippets correctly applies temperature scaling to logits before sampling in Python?

easy

A. probs = softmax(logits / temperature)

B. probs = softmax(logits * temperature)

C. probs = softmax(logits + temperature)

D. probs = softmax(logits - temperature)

Solution

1. Step 1: Recall temperature scaling formula

   Temperature is applied by dividing logits by temperature before softmax to adjust randomness.

2. Step 2: Identify correct operation

   Dividing logits by temperature scales the logits correctly; multiplying or adding is incorrect.

3. Final Answer:

   probs = softmax(logits / temperature) -> Option A

4. Quick Check:

   Divide logits by temperature before softmax [OK]

Hint: Divide logits by temperature before softmax [OK]

Common Mistakes:

• Multiplying logits by temperature instead of dividing
• Adding temperature to logits
• Subtracting temperature from logits

3. Given logits = [2.0, 1.0, 0.1] and temperature = 0.5, what is the approximate probability of the first token after applying softmax with temperature scaling?

medium

A. About 0.30

B. About 0.60

C. About 0.50

D. About 0.84

Solution

1. Step 1: Scale logits by dividing by temperature

   Divide each logit by 0.5: [2.0/0.5=4.0, 1.0/0.5=2.0, 0.1/0.5=0.2]

2. Step 2: Calculate softmax probabilities

   Compute exp values: exp(4.0)=54.6, exp(2.0)=7.39, exp(0.2)=1.22; sum=63.21; probability first token = 54.6/63.21 ≈ 0.86 (approx 0.86 considering rounding)

3. Final Answer:

   About 0.86 -> Option D

4. Quick Check:

   Lower temperature sharpens distribution, first token ~0.86 [OK]

Hint: Divide logits by temperature, then softmax to find probabilities [OK]

Common Mistakes:

• Multiplying logits by temperature instead of dividing
• Skipping exponentiation step
• Using temperature incorrectly in softmax

4. A developer writes this code to sample a token with temperature 1.5 but always gets the same token. What is the likely bug?

scaled_logits = logits * temperature
probs = softmax(scaled_logits)
sampled_token = sample_from(probs)

medium

A. They should divide logits by temperature, not multiply

B. They forgot to apply softmax

C. Temperature should be zero to get randomness

D. Sampling function is incorrect

Solution

1. Step 1: Identify temperature scaling mistake

   The code multiplies logits by temperature, which is incorrect; it should divide logits by temperature.

2. Step 2: Explain effect of wrong scaling

   Multiplying by temperature >1 increases logits, making softmax peakier and less random, causing same token output.

3. Final Answer:

   They should divide logits by temperature, not multiply -> Option A

4. Quick Check:

   Divide logits by temperature for correct scaling [OK]

Hint: Divide, don't multiply logits by temperature [OK]

Common Mistakes:

• Multiplying instead of dividing logits
• Setting temperature to zero
• Ignoring softmax step

5. You want to generate text that balances creativity and coherence. Which temperature value and sampling strategy combination is best?

hard

A. Temperature 0.1 with greedy sampling

B. Temperature around 0.7 with top-k sampling

C. Temperature 2.0 with random sampling

D. Temperature 1.5 with no sampling (always pick max)

Solution

1. Step 1: Understand temperature impact on creativity

   Temperature ~0.7 balances randomness and predictability, avoiding too repetitive or too random output.

2. Step 2: Choose sampling method for balance

   Top-k sampling limits choices to top probable tokens, improving coherence while allowing creativity.

3. Final Answer:

   Temperature around 0.7 with top-k sampling -> Option B

4. Quick Check:

   Moderate temperature + top-k = balanced creativity [OK]

Hint: Use moderate temperature and top-k for balanced text [OK]

Common Mistakes:

• Using very low temperature causing boring text
• Using very high temperature causing nonsense
• Ignoring sampling method effects