Rearag 9B

🚀 ReaRAG-9B

ReaRAG-9B is trained on glm-4-9b, enhancing the ability to generate knowledge-guided reasoning chains for iterative RAG, with a context window of up to 8k tokens.

🤗 Dataset • 💻 GitHub • 📃 Paper

🚀 Quick Start

ReaRAG-9B is trained based on glm-4-9b. It has an enhanced capability to generate knowledge-guided reasoning chains for iterative RAG. The model supports a context window of up to 8k tokens.

For detailed usage, please refer to the Inference section in the GitHub repository.

📚 Documentation

Dataset

📚 Citation

If you use this dataset in your research or projects, please consider citing our work:

@article{lee2025rearag,
  title={ReaRAG: Knowledge-guided Reasoning Enhances Factuality of Large Reasoning Models with Iterative Retrieval Augmented Generation},
  author={Lee, Zhicheng and Cao, Shulin and Liu, Jinxin and Zhang, Jiajie and Liu, Weichuan and Che, Xiaoyin and Hou, Lei and Li, Juanzi},
  journal={arXiv preprint arXiv:2503.21729},
  year={2025}
}