Temperature and sampling in NLP - ML Experiment: Train & Evaluate

Experiment - Temperature and sampling

Problem:You have a text generation model that uses sampling with temperature to create sentences. Currently, the model uses a temperature of 1.0 and produces repetitive or dull text.

Current Metrics:Sampled text shows low diversity and repetitiveness; qualitative evaluation indicates low creativity.

Issue:The model's output lacks variety and creativity due to suboptimal temperature settings during sampling.

Your Task

Adjust the temperature parameter during sampling to increase the diversity and creativity of generated text without making it nonsensical.

Do not change the underlying language model architecture.

Only modify the temperature parameter and sampling method.

Keep the sampling code runnable and simple.

Hint 1

Hint 2

Hint 3

Solution

NLP

import numpy as np

def sample_with_temperature(logits, temperature=1.0):
    # Convert logits to probabilities with temperature
    scaled_logits = logits / temperature
    exp_logits = np.exp(scaled_logits - np.max(scaled_logits))
    probs = exp_logits / np.sum(exp_logits)
    # Sample from the probability distribution
    return np.random.choice(len(probs), p=probs)

# Example logits for a vocabulary of 5 tokens
logits = np.array([2.0, 1.0, 0.1, 0.5, 1.5])

# Sample tokens with different temperatures
for temp in [0.5, 1.0, 1.5]:
    print(f"Sampling with temperature={temp}:")
    samples = [sample_with_temperature(logits, temperature=temp) for _ in range(10)]
    print(samples)

Added a temperature parameter to scale logits before converting to probabilities.

Implemented sampling from the adjusted probability distribution.

Demonstrated sampling at temperatures 0.5, 1.0, and 1.5 to show effect on output diversity.

Results Interpretation

Before: Sampling at temperature 1.0 produced repetitive tokens with low diversity.

After: Sampling at temperature 0.5 reduced randomness, focusing on likely tokens, while temperature 1.5 increased randomness, producing more diverse but sometimes less sensible tokens.

Adjusting temperature during sampling controls randomness: lower temperature makes output more predictable, higher temperature increases creativity but risks nonsense. This helps balance diversity and coherence in text generation.

Bonus Experiment

Try implementing top-k sampling combined with temperature to further control output diversity.

💡 Hint

Limit sampling to the top k tokens with highest probabilities after applying temperature scaling, then sample from this smaller set.

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