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

TL;DR

DRAGON introduces a domain-specific data generation framework and benchmark to improve retrieval-augmented generation (RAG) performance, robustness, and cross-domain generalization in knowledge-intensive tasks.

Contribution

It presents a novel data-construction and synthetic data-generation pipeline tailored for domain-specific RAG, along with DRAGONBench, a comprehensive benchmark for evaluation.

Findings

Retrievers trained on DRAGON-generated data show significant performance improvements.

The approach enhances cross-domain generalization of RAG systems.

Integrated optimized retrievers improve accuracy across various RAG paradigms.

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.