Why Temperature and sampling in NLP? - Purpose & Use Cases

The Big Idea

Discover how a simple setting can turn boring text into creative stories!

The Scenario

Imagine you want to write a story by picking each next word yourself from a huge list of possibilities. You try to guess the best word every time, but it takes forever and feels like a guessing game.

The Problem

Choosing each word manually is slow and tiring. You might pick boring or repetitive words, or get stuck because you can't explore creative options easily. It's hard to balance between safe and exciting choices.

The Solution

Temperature and sampling let the computer pick words for you in a smart way. Temperature controls how bold or safe the choices are, and sampling helps pick words based on their chance of fitting well. This makes text generation faster, more creative, and less stuck.

Before vs After

✗ Before

next_word = max(possible_words, key=probability)

✓ After

next_word = sample(possible_words, temperature=0.7)

What It Enables

It enables generating creative and varied text automatically, balancing between safe and surprising word choices.

Real Life Example

When chatbots write replies, temperature and sampling help them sound natural and interesting instead of repeating the same phrases.

Key Takeaways

Picking words manually is slow and limited.

Temperature adjusts how bold or safe word choices are.

Sampling helps pick words based on their chance, making text creative and varied.

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