DRAGON: Domain-specific Robust Automatic Data Generation for RAG Optimization

Haiyang Shen, Hang Yan, Zhongshi Xing, Mugeng Liu, Yue Li, Zhiyang Chen, Yuxiang Wang, Jiuzheng Wang, Yun Ma

Abstract

Retrieval-augmented generation (RAG) can substantially enhance the performance of LLMs on knowledge-intensive tasks. Various RAG paradigms - including vanilla, planning-based, and iterative RAG - all depend on a robust retriever, yet existing retrievers rely heavily on public knowledge and often falter when faced with domain-specific queries. To address these limitations, we introduce DRAGON, a framework that combines a data-construction modeling approach with a scalable synthetic data-generation pipeline, specifically designed to optimize domain-specific retrieval performance and bolster retriever robustness. To evaluate RAG performance on domain-specific RAGs, we propose DRAGONBench, a benchmark spanning 8 domain-specific document collections across 4 distinct fields and featuring a wide spectrum of query complexities, answerability, and hop numbers. Leveraging DRAGON, we generate a large-scale synthetic dataset - encompassing both single-hop and multi-hop queries - to enrich retriever training. Extensive experiments demonstrate that retrievers trained on this data yield significant performance gains and exhibit strong cross-domain generalization. Moreover, when our optimized retrievers are integrated into vanilla, planning-based, and iterative RAG paradigms, we observe consistent end-to-end improvements in system accuracy.
BibTeX
@inproceedings{shen2026dragon,
  author = {Haiyang Shen and Hang Yan and Zhongshi Xing and Mugeng Liu and Yue Li and Zhiyang Chen and Yuxiang Wang and Jiuzheng Wang and Yun Ma},
  title = {{DRAGON: Domain-specific Robust Automatic Data Generation for RAG Optimization}},
  booktitle = {EACL (Findings)},
  year = {2026},
  doi = {10.18653/v1/2026.findings-eacl.56},
}

Loading related content...

Figure