Detect Eval Set Contamination

Use when an eval or benchmark score looks too good, or a test set predates a model's training cutoff. Measures prompt and answer overlap with the training corpus.

jiayaoqijia Updated 81 repo stars

File contents

jiayaoqijia/cryptoskill commit 1df06001fe

Frequently asked questions

npx get-skill add jiayaoqijia/detect-eval-set-contamination