Update README.md
Browse files
README.md
CHANGED
|
@@ -22,17 +22,6 @@ tags:
|
|
| 22 |
*Equal contribution.<br> †Equal contribution of corresponding author.
|
| 23 |
</p>
|
| 24 |
|
| 25 |
-
<p align="center">
|
| 26 |
-
<a href="https://www.python.org/downloads/release/python-3100/"><img src="https://img.shields.io/badge/python-3.10-blue.svg" alt="Python Version 3.10"></a>
|
| 27 |
-
<a href="https://github.com/Jiaqi-Chen-00/ImBD/issues"><img src="https://img.shields.io/github/issues/Jiaqi-Chen-00/ImBD" alt="GitHub Issues"></a>
|
| 28 |
-
<a href="https://github.com/Jiaqi-Chen-00/ImBD/stargazers"><img src="https://img.shields.io/github/stars/Jiaqi-Chen-00/ImBD" alt="GitHub Stars"></a>
|
| 29 |
-
<a href="https://github.com/Jiaqi-Chen-00/ImBD/network/members"><img src="https://img.shields.io/github/forks/Jiaqi-Chen-00/ImBD" alt="GitHub Forks"></a>
|
| 30 |
-
</p>
|
| 31 |
-
|
| 32 |
-
<p align="center">
|
| 33 |
-
| <img src="https://img.icons8.com/color/48/000000/internet.png" alt="Platform" width="15" height="15" style="vertical-align: middle;"/><a href="https://machine-text-detection.github.io/ImBD/"><b>Website</b></a> | <img src="https://img.icons8.com/?size=100&id=13580&format=png&color=000000" alt="Paper" width="15" height="15" style="vertical-align: middle;"/> <a href="https://drive.google.com/file/d/1bVJIE94AxfSfJVIVUhdcntRSlseM06Lw/view?usp=sharing"><b>Paper</b></a> | <img src="https://img.icons8.com/?size=100&id=1475&format=png&color=90CAF9" alt="Data" width="15" height="15" style="vertical-align: middle;"/> <a href="https://github.com/Jiaqi-Chen-00/ImBD/tree/main/data"><b>Data</b></a> | <img src="https://img.icons8.com/?size=100&id=sop9ROXku5bb&format=png&color=000000" alt="Data" width="15" height="15" style="vertical-align: middle;"/> <a href="https://huggingface.co/xyzhu1225/ImBD/tree/main"><b>Model</b></a> |
|
| 34 |
-
</p>
|
| 35 |
-
|
| 36 |
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.
|
| 37 |
|
| 38 |
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!
|
|
|
|
| 22 |
*Equal contribution.<br> †Equal contribution of corresponding author.
|
| 23 |
</p>
|
| 24 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
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.
|
| 26 |
|
| 27 |
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!
|