用合成数据提升领域专用检索器性能，让大模型问答更准。
DRAGON: Domain-specific Robust Automatic Data Generation for RAG Optimization
- 构建合成数据生成框架，专为领域知识优化检索器
- 在8个领域、多跳查询上显著提升检索准确率
- 适合需要高精度领域问答的工业应用
检索增强生成（RAG）能显著提升大模型在知识密集型任务中的表现。现有RAG范式——包括基础型、规划型和迭代型——均依赖稳健的检索器，但现有检索器严重依赖公开知识，在面对领域特定查询时表现不佳。为此，我们提出DRAGON框架，结合数据构建建模与可扩展的合成数据生成管道，专门用于优化领域特定检索性能并增强检索器鲁棒性。为评估领域特定RAG性能，我们构建了DRAGONBench基准，涵盖4个不同领域下的8个领域文档集合，包含多样化的查询复杂度、可回答性和多跳数量。利用DRAGON，我们生成大规模合成数据集，涵盖单跳与多跳查询，用于丰富检索器训练。大量实验表明，基于该数据训练的检索器性能显著提升，并具备强跨领域泛化能力。当这些优化后的检索器集成至基础型、规划型和迭代型RAG范式中时，系统整体准确性持续提高。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。