# Uncertainty

Understand Galileo’s Uncertainty Metric

* Definition__:* Measures how much the model is deciding randomly between multiple ways of continuing the output.

*Uncertainty*is measured at both the token level and the response level. Higher uncertainty means the model is less certain.

* Calculation__: Uncertainty* at the token level tells us how confident the model is of the next token given the preceding tokens.

*Uncertainty*at the response level is simply the maximum token-level

*Uncertainty,*over all the tokens in the model’s response. It is calculated using OpenAI’s Davinci models.

**What to do when uncertainty is low?**

Our research has found high uncertainty scores correlate with hallucinations, made up facts, and citations. Looking at highly uncertain responses can flag areas where your model is struggling.

Was this page helpful?