README.md

---
title: README
emoji: 🐢
colorFrom: purple
colorTo: purple
sdk: static
pinned: false
---

# QAFD-RAG

Official data and pre-built knowledge graphs for [QAFD-RAG](https://github.com/Tarzanagh/QAFD-RAG) (Query-Aware Flow Diffusion for Graph-Based RAG with Retrieval Guarantees), published at **ICLR 2026**.

- **Paper**: [OpenReview](https://openreview.net/pdf?id=n28wnc2QTc)
- **Code**: [GitHub](https://github.com/Tarzanagh/QAFD-RAG)
- **Website**: [qafd-rag.github.io](https://qafd-rag.github.io)

## Datasets

| Dataset | Description |
|---------|-------------|
| [qafd/kg](https://huggingface.co/datasets/qafd/kg) | Pre-built knowledge graphs for all benchmarks (UltraDomain, Multi-hop QA, Text-to-SQL, Summarization) |

## Citation

```bibtex
@inproceedings{zhou2026qafd,
  title={Query-Aware Flow Diffusion for Graph-Based RAG with Retrieval Guarantees},
  author={Zhuoping Zhou and Davoud Ataee Tarzanagh and Sima Didari and Wenjun Hu
          and Baruch Gutow and Oxana Verkholyak and Masoud Faraki and Heng Hao
          and Hankyu Moon and Seungjai Min},
  booktitle={International Conference on Learning Representations (ICLR)},
  year={2026}
}