Relevance Scores

When you run a search, each answer has a relevance score that reflects the model's confidence in it. Learn more about what the score tells you.

What's It For?

Relevance scores tell you how correct the answers are. If a model has a relevance score of 90%, you can expect that its predictions are correct in 9 out of 10 cases.

Relevance scores are particularly useful if you need your search results to meet a particular accuracy threshold.

Data Alignment

If the data that the model was trained on strongly differs from the data used for search, the relevance score may not reflect the model's accuracy. You need to fine-tune the model on a specific dataset in such a case.


Related Links