Skip to content

io614/DetectGPT-ensemble

 
 

Repository files navigation

Applying Ensemble Methods to Model-Agnostic Machine-Generated Text Detection

Instructions

First, install the Python dependencies using conda:

conda env create -f environment.yml

Second, run the experiments in permute.sh.

Notes

This is a fork of the official implementation of the experiments in the DetectGPT paper. The original Github repository can be found here. An interactive demo of DetectGPT can be found here.

If you'd like to run the WritingPrompts experiments, you'll need to download the WritingPrompts data from here. Save the data into a directory data/writingPrompts.

Intermediate results are saved in tmp_results/. If your experiment completes successfully, the results will be moved into the results/ directory

About

No description, website, or topics provided.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages

  • Jupyter Notebook 43.2%
  • Python 36.7%
  • Shell 20.1%