README.md

---
license: apache-2.0
---
# AIGC Detector (MPU)

[[arXiv]](https://arxiv.org/abs/2305.18149) [[Codes (Model Links, Other Detector Versions)]](https://github.com/YuchuanTian/AIGC_text_detector)

The AIGC Detector (MPU) in our paper "Multiscale Positive-Unlabeled Detection of AI-Generated Texts".

Paper Link: https://arxiv.org/pdf/2305.18149.pdf

*BibTex* formatted citation:

```
@misc{tian2023multiscale,
      title={Multiscale Positive-Unlabeled Detection of AI-Generated Texts}, 
      author={Yuchuan Tian and Hanting Chen and Xutao Wang and Zheyuan Bai and Qinghua Zhang and Ruifeng Li and Chao Xu and Yunhe Wang},
      year={2023},
      eprint={2305.18149},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}
```

## Version: Zh_v2

Zh_v2: This model is trained with MPU from a pretrained Chinese-RoBERTa-wwm-ext, but the standard training setting in the paper is not followed. This model demonstrates comparable performance to SOTA closed-source Chinese detectors on various domains.