EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

HiRAG: A Hierarchical Retrieval-Augmented Generation Framework via Intent Routing and Small-Model Refinement

Sunjia Zhang

Journal of Artificial Intelligence and Technology · 31.10.2026

DOI: 10.37965/jait.2026.1569 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Artificial Intelligence and Technology, online erschienen am 31.10.2026. Verfasst von Sunjia Zhang. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

While retrieval-augmented generation (RAG) mitigates large language model (LLM) hallucinations, traditional flat vector retrieval in massive, heterogeneous databases suffers from high latency and noise interference. To address this, we propose HiRAG, a hierarchical RAG framework. Offline, HiRAG builds a “classification-summary” dual-layer index to structurally organize data. Online, a lightweight bidirectional encoder representations from transformers (BERT)-based router identifies query intent to dynamically prune the search space. A cascaded pipeline then uses hybrid retrieval and Small-LLM reranking for coarse-to-fine de-noising. Experiments on the Microsoft Machine Reading Comprehension (MS MARCO) and Multi-Domain Enterprise Knowledge Base (MDE-KB) datasets demonstrate that HiRAG outperforms traditional baselines. Specifically on MDE-KB, HiRAG improves Recall@5 by 14.5 percentage points over Naive RAG and achieves a retrieval augmented generation assessment (RAGAS) Answer Relevance score of 0.92, while reducing average query latency by 28%. HiRAG provides a viable, efficient solution for large-scale knowledge bases.

Zitieren

APA

Zhang, S. (2026). HiRAG: A Hierarchical Retrieval-Augmented Generation Framework via Intent Routing and Small-Model Refinement. Journal of Artificial Intelligence and Technology. https://doi.org/10.37965/jait.2026.1569

Vancouver

Zhang S. HiRAG: A Hierarchical Retrieval-Augmented Generation Framework via Intent Routing and Small-Model Refinement. Journal of Artificial Intelligence and Technology. 2026. doi:10.37965/jait.2026.1569

BibTeX
@article{Zhang2026,
  author = {Zhang, Sunjia},
  title = {HiRAG: A Hierarchical Retrieval-Augmented Generation Framework via Intent Routing and Small-Model Refinement},
  journal = {Journal of Artificial Intelligence and Technology},
  year = {2026},
  doi = {10.37965/jait.2026.1569}
}
Kostenlos starten →