HiSem-RAG: A Hierarchical Semantic-Driven Retrieval-Augmented Generation Method
Applied Sciences · 15.01.2026 · 16 (2) · 903
DOI: 10.3390/app16020903 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 15.01.2026. Verfasst von Dongju Yang und 1 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Traditional retrieval-augmented generation (RAG) methods struggle with hierarchical documents, often causing semantic fragmentation, structural loss, and inefficient retrieval due to fixed strategies. To address these challenges, this paper proposes HiSem-RAG, a hierarchical semantic-driven RAG method. It comprises three key modules: (1) hierarchical semantic indexing, which preserves boundaries and relationships between sections and paragraphs to reconstruct document context; (2) a bidirectional semantic enhancement mechanism that incorporates titles and summaries to facilitate two-way information flow; and (3) a distribution-aware adaptive threshold strategy that dynamically adjusts retrieval scope based on similarity distributions, balancing accuracy with computational efficiency. On the domain-specific EleQA dataset, HiSem-RAG achieves 82.00% accuracy, outperforming HyDE and RAPTOR by 5.04% and 3.98%, respectively, with reduced computational costs. On the LongQA dataset, it attains a ROUGE-L score of 0.599 and a BERT_F1 score of 0.839. Ablation studies confirm the complementarity of these modules, particularly in long-document scenarios.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Yang, D., & Wang, J. (2026). HiSem-RAG: A Hierarchical Semantic-Driven Retrieval-Augmented Generation Method. Applied Sciences, 16(2), 903. https://doi.org/10.3390/app16020903
Vancouver
Yang D, Wang J. HiSem-RAG: A Hierarchical Semantic-Driven Retrieval-Augmented Generation Method. Applied Sciences. 2026;16(2):903. doi:10.3390/app16020903
BibTeX
@article{Yang2026,
author = {Yang, Dongju and Wang, Junming},
title = {HiSem-RAG: A Hierarchical Semantic-Driven Retrieval-Augmented Generation Method},
journal = {Applied Sciences},
year = {2026},
volume = {16},
number = {2},
pages = {903},
doi = {10.3390/app16020903}
}
EUVIMED