DRAGON: Domain-specific Robust Automatic Data Generation for RAG Optimization
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915782502383616 |
|---|---|
| author | Shen, Haiyang Yan, Hang Xing, Zhongshi Liu, Mugeng Li, Yue Chen, Zhiyang Wang, Yuxiang Wang, Jiuzheng Ma, Yun |
| author_facet | Shen, Haiyang Yan, Hang Xing, Zhongshi Liu, Mugeng Li, Yue Chen, Zhiyang Wang, Yuxiang Wang, Jiuzheng Ma, Yun |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_10989 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DRAGON: Domain-specific Robust Automatic Data Generation for RAG Optimization Shen, Haiyang Yan, Hang Xing, Zhongshi Liu, Mugeng Li, Yue Chen, Zhiyang Wang, Yuxiang Wang, Jiuzheng Ma, Yun Artificial Intelligence 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. |
| title | DRAGON: Domain-specific Robust Automatic Data Generation for RAG Optimization |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2505.10989 |