---
license: apache-2.0
language:
- en
metrics:
- roc_auc
base_model:
- EleutherAI/gpt-neo-2.7B
pipeline_tag: text-classification
tags:
- machine-text-detection
- machine-revised-text-detection
---
Imitate Before Detect: Aligning Machine Stylistic Preference for Machine-Revised Text Detection
Jiaqi Chen*, Xiaoye Zhu*, Tianyang Liu*, Ying Chen, Xinhui Chen,
Yiwen Yuan, Chak Tou Leong, Zuchao Liโ , Tang Long, Lei Zhang,
Chenyu Yan, Guanghao Mei, Jie Zhangโ , Lefei Zhangโ
*Equal contribution.
โ Equal contribution of corresponding author.
Detecting **machine-revised text** remains a challenging task as it often involves subtle style changes embedded within human-originated content. The ImBD framework introduces a novel approach to tackle this problem, leveraging **style preference optimization (SPO)** and **Style-CPC** to effectively capture machine-style phrasing. Our method achieves state-of-the-art performance in detecting revisions by open-source and proprietary LLMs like GPT-3.5 and GPT-4o, demonstrating significant efficiency with minimal training data.
We are excited to share our code and data to support further exploration in detecting machine-revised text. We welcome your feedback and invite collaborations to advance this field together!
![Main Figure](https://machine-text-detection.github.io/ImBD/static/images/method.png)
## ๐ฅ News
- **[2024, Dec 16]** Our online [demo](https://huggingface.co/spaces/machine-text-detection/ImBD) is available on hugging-face now!
- **[2024, Dec 13]** Our [model](https://huggingface.co/xyzhu1225/ImBD/tree/main) and local inference code are available.
- **[2024, Dec 9]** ๐๐ Our paper has been accepted by AAAI 25!
- **[2024, Dec 7]** We've released our [website](https://machine-text-detection.github.io/ImBD).