Frequency vs Presence penalty, what’s the difference? — OpenAI API

Frequency Penalty:
Frequency Penalty helps us avoid using the same words too often. It’s like telling the computer, “Hey, don’t repeat words too much.”

• Frequency Penalty helps avoid using the same words too often, by adding a value to the log-probability of a token each time it occurs in the generated text.
• It encourages the model to avoid repeating the same word too frequently within the text.

Presence Penalty:
Presence Penalty, on the other hand, encourages using different words. It’s like saying, “Hey, use a variety of words, not just the same ones.”

• Presence Penalty nudges the model to include a wide variety of tokens in the generated text, by subtracting a value from the log-probability of a token each time it is generated.
• It encourages the model to favor tokens that haven't been used frequently in the generated text, promoting diversity.

Difference Between Frequency and Presence Penalty:
Frequency Penalty helps avoid repetition while Presence Penalty encourages variety, making the text more interesting.

They work differently but help make the text more interesting, like two different sides of the same coin.