This project contains the implementation and results of bias detection experiments in large language models.
The experiments were conducted using Python 3.9+. To maintain a clean environment and avoid conflicts with other projects, it is recommended to use a virtual environment.
- Create a virtual environment:
python3 -m venv llm_bias_env
- Activate the virtual environment:
- On macOS/Linux:
source llm_bias_env/bin/activate
- On Windows:
.\llm_bias_env\Scripts\activate
To install the required dependencies, run the following command from the root directory of the replication package:
pip install -r requirements.txt