defog-ai / sql-eval

Evaluate the accuracy of LLM generated outputs
Apache License 2.0
485 stars 52 forks source link

Added idk questions so we can query them more easily #146

Closed rishsriv closed 2 months ago

rishsriv commented 2 months ago

Not adding improvements around "false negatives" in the IDK questions for! We can now easily eyeball them via the eval-visualizer, so not worth it to spend additional dev time on that!