Temperature and sampling in NLP

Introduction

Temperature and sampling help control how creative or random a language model's text predictions are.

When you want the model to give more varied and creative text instead of always the most likely word.

When generating stories or poems where surprise and diversity are good.

When you want to balance between safe and risky word choices in chatbot replies.

When exploring different possible next words to understand model behavior.

When tuning text generation to be more predictable or more random.

Syntax

NLP

def sample_with_temperature(logits, temperature=1.0):
    import numpy as np
    logits = logits / temperature
    exp_logits = np.exp(logits - np.max(logits))
    probs = exp_logits / np.sum(exp_logits)
    return np.random.choice(len(probs), p=probs)

Temperature is a positive number; lower than 1 makes output more focused, higher than 1 makes it more random.

Sampling means picking the next word based on probabilities, not just the highest one.

Examples

Lower temperature makes the model pick more confident words, less random.

NLP

sample_with_temperature(logits, temperature=0.5)

Temperature 1 means normal sampling from the original probabilities.

NLP

sample_with_temperature(logits, temperature=1.0)

Higher temperature makes the model pick more surprising or rare words.

NLP

sample_with_temperature(logits, temperature=2.0)

Sample Model

This code shows how changing temperature affects which index (word) is picked from logits representing word scores.

NLP

import numpy as np

def sample_with_temperature(logits, temperature=1.0):
    logits = logits / temperature
    exp_logits = np.exp(logits - np.max(logits))
    probs = exp_logits / np.sum(exp_logits)
    return np.random.choice(len(probs), p=probs)

# Example logits for 5 possible next words
logits = np.array([2.0, 1.0, 0.1, 0.5, 0.0])

print('Sampling with temperature 0.5:')
for _ in range(5):
    idx = sample_with_temperature(logits, temperature=0.5)
    print(f'Chosen index: {idx}')

print('\nSampling with temperature 1.0:')
for _ in range(5):
    idx = sample_with_temperature(logits, temperature=1.0)
    print(f'Chosen index: {idx}')

print('\nSampling with temperature 2.0:')
for _ in range(5):
    idx = sample_with_temperature(logits, temperature=2.0)
    print(f'Chosen index: {idx}')

Important Notes

Temperature close to zero makes the model almost always pick the highest scoring word.

Sampling with temperature helps avoid boring or repetitive text.

Try different temperatures to find the best balance for your task.

Summary

Temperature controls randomness in text generation.

Lower temperature = more predictable, higher temperature = more creative.

Sampling picks words based on adjusted probabilities, not just the top choice.

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