This repository contains the datasets and evaluation framework for the paper "Bot or Human? Detecting ChatGPT Imposters with A Single Question". The paper proposes a new framework named FLAIR (Finding Large Language Model Authenticity via a Single Inquiry and Response) to detect conversational bots in an online manner. The approach aims to differentiate human users from bots using single-question scenarios.
We welcome contributions to expand the dataset and improve the detection of conversational bots. If you have a new question that you believe can effectively differentiate human users from bots, please feel free to contribute to the dataset via submitting a pull request to this repo.
Please cite our paper if you find this repository helpful in your research or you use our data:
@article{FLAIR,
title={Bot or Human? Detecting ChatGPT Imposters with A Single Question},
author={Wang, Hong and Luo, Xuan and Wang, Weizhi and Yan, Xifeng},
journal={arXiv preprint arXiv:2305.06424},
year={2023}
}