Popular repositories Loading

1. bloom bloom Public

   🌸 Generate automated evaluations for LLMs to assess behaviors like bias and sycophancy, ensuring reproducibility with customizable test scenarios.

2. ashwin-deshmukh121.github.io ashwin-deshmukh121.github.io Public

   🌸 Generate tailored evaluation suites for LLMs to assess behaviors like bias and self-preservation, ensuring reproducibility with diverse test scenarios.