README.md

---
license: apache-2.0
task_categories:
- text-classification
language:
- en
tags:
- aigc-detection
- text-classification
- qwen
base_model: Qwen/Qwen3-8B
---

# REVEAL_think_2class

**REVEAL-think-2class** is a reasoning-driven AI-Generated Content (AIGC) detection model based on Qwen3-8B. It uses a **Think-then-Answer** paradigm, generating a transparent reasoning chain (`<think>...</think>`) before outputting the final binary classification (`<answer>...</answer>`).

This model is introduced in the paper: **[Reasoning-Aware AIGC Detection via Alignment and Reinforcement](https://arxiv.org/abs/2604.19172)**.

🔗 **Project Homepage & Code:** [https://aka.ms/reveal](https://aka.ms/reveal)  
📚 **Associated Dataset:** [AIGC-text-bank](https://huggingface.co/datasets/bmbgsj/AIGC-text-bank)

## 🌟 Model Overview

This model discriminates between two categories:
- **Human**: Authentic human-authored text.
- **AI**: Machine-generated text (includes both fully AI-generated content and human drafts polished by AI).

## 🚀 How to Use

To run inference, simply use the [`think.py`](https://github.com/microsoft/AnthropomorphicIntelligence/blob/main/REVEAL/inference/think.py) script provided in our GitHub repository. It handles prompt formatting, `vLLM` acceleration, and automatically extracts the final prediction along with fine-grained confidence scores.

```bash
python think.py \
    --model_path "bmbgsj/REVEAL_think_2class" \
    --text "The rapid advancement of Large Language Models has ushered in an era where AI-generated content is increasingly pervasive..."
```

## 📖 Citation

If you use this model in your research, please cite:

```bibtex
@misc{wang2026reasoningawareaigcdetectionalignment,
      title={Reasoning-Aware AIGC Detection via Alignment and Reinforcement}, 
      author={Zhao Wang and Max Xiong and Jianxun Lian and Zhicheng Dou},
      year={2026},
      eprint={2604.19172},
      archivePrefix={arXiv},
      primaryClass={cs.AI},
      url={https://arxiv.org/abs/2604.19172}, 
}
```