EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

DMAR: Dynamic Multi-Anchor Retrieval with Structure-Aware Query Reformulation for Knowledge-Augmented Generation

Zhou Lei, Yanqi Xu, Shengbo Chen

Applied Sciences · 19.04.2026 · 16 (8) · 3963

DOI: 10.3390/app16083963 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 19.04.2026. Verfasst von Zhou Lei und 2 weiteren Autor:innen. Die Arbeit nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Education industry–university cooperative education project, Shanghai University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Retrieval-Augmented Generation (RAG) has become an important paradigm for knowledge-intensive natural language processing, as it enables Large Language Models (LLMs) to access external evidence beyond their parametric memory. However, existing RAG pipelines often rely on static user queries and predominantly semantic matching, which makes them less effective in data-intensive scenarios that require structured knowledge and multi-hop evidence aggregation. To address these limitations, we propose DMAR, a dynamic multi-anchor retrieval framework for retrieval refinement in knowledge-augmented generation. DMAR first identifies high-confidence anchor documents from an initial candidate pool through a dual-path evaluator that combines semantic relevance with knowledge-graph-based structural association. The selected anchors are then used to guide generative query reformulation, producing an enriched query for second-stage retrieval, followed by fidelity-controlled reranking to preserve alignment with the user’s original intent. We further model structural relevance using Subgraph Shapley Values and a learnable Siamese GNN-based similarity module. Experiments on five knowledge-intensive benchmarks, covering open-domain question answering, multi-hop reasoning, and fact verification, show that DMAR consistently improves retrieval and downstream answer quality over strong baselines. For example, DMAR achieves an F1 score of 62.5% on HotpotQA and 79.0% on TriviaQA. These results demonstrate that dynamically integrating semantic retrieval, structural knowledge, and query reformulation is an effective approach for robust knowledge-augmented NLP systems.

Förderung

  • Ministry of Education industry–university cooperative education project
  • Shanghai University

Zitieren

APA

Lei, Z., Xu, Y., & Chen, S. (2026). DMAR: Dynamic Multi-Anchor Retrieval with Structure-Aware Query Reformulation for Knowledge-Augmented Generation. Applied Sciences, 16(8), 3963. https://doi.org/10.3390/app16083963

Vancouver

Lei Z, Xu Y, Chen S. DMAR: Dynamic Multi-Anchor Retrieval with Structure-Aware Query Reformulation for Knowledge-Augmented Generation. Applied Sciences. 2026;16(8):3963. doi:10.3390/app16083963

BibTeX
@article{Lei2026,
  author = {Lei, Zhou and Xu, Yanqi and Chen, Shengbo},
  title = {DMAR: Dynamic Multi-Anchor Retrieval with Structure-Aware Query Reformulation for Knowledge-Augmented Generation},
  journal = {Applied Sciences},
  year = {2026},
  volume = {16},
  number = {8},
  pages = {3963},
  doi = {10.3390/app16083963}
}
Kostenlos starten →