@inproceedings{shen-etal-2026-dragon,
    title = "{DRAGON}: Domain-specific Robust Automatic Data Generation for {RAG} Optimization",
    author = "Shen, Haiyang  and
      Yan, Hang  and
      Xing, Zhongshi  and
      Liu, Mugeng  and
      Li, Yue  and
      Chen, Zhiyang  and
      Wang, Yuxiang  and
      Wang, Jiuzheng  and
      Ma, Yun",
    editor = "Demberg, Vera  and
      Inui, Kentaro  and
      Marquez, Llu{\'i}s",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EACL} 2026",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-eacl/2026.findings-eacl.56/",
    pages = "1065--1078",
    ISBN = "979-8-89176-386-9",
    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 hops. 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."
}