SPR-RAG: Semantic Parsing Retriever-Enhanced Question Answering for Power Policy
Algorithms · 17.12.2025 · 18 (12) · 802
DOI: 10.3390/a18120802 ↗Kurz gefasst
Fachartikel in der Zeitschrift Algorithms, online erschienen am 17.12.2025. Verfasst von Yufang Wang und 2 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: China Postdoctoral Science Foundation, National Natural Science Foundation of China, Startup Foundation for Introducing Talent of Nanjing University of Information Science and Technology.
Abstract (Originalsprache)
To address the limitations of Retrieval-Augmented Generation (RAG) systems in handling long policy documents, mitigating information dilution, and reducing hallucinations in engineering-oriented applications, this paper proposes SPR-RAG, a retrieval-augmented framework designed for knowledge-intensive vertical domains such as electric power policy analysis. With practicality and interpretability as core design goals, SPR-RAG introduces a Semantic Parsing Retriever (SPR), which integrates community detection–based entity disambiguation and transforms natural language queries into logical forms for structured querying over a domain knowledge graph, thereby retrieving verifiable triple-based evidence. To further resolve retrieval bias arising from diverse policy writing styles and inconsistencies between user queries and policy text expressions, a question-repository–based indirect retrieval mechanism is developed. By generating and matching latent questions, this module enables more robust retrieval of non-structured contextual evidence. The system then fuses structured and unstructured evidence into a unified dual-source context, providing the generator with an interpretable and reliable grounding signal. Experiments conducted on real electric power policy corpora demonstrate that SPR-RAG achieves 90.01% faithfulness—representing a 5.26% improvement over traditional RAG—and 76.77% context relevance, with a 5.96% gain. These results show that SPR-RAG effectively mitigates hallucinations caused by ambiguous entity names, textual redundancy, and irrelevant retrieved content, thereby improving the verifiability and factual grounding of generated answers. Overall, SPR-RAG demonstrates strong deployability and cross-domain transfer potential through its “Text → Knowledge Graph → RAG” engineering paradigm. The framework provides a practical and generalizable technical blueprint for building high-trust, industry-grade question–answering systems, offering substantial engineering value and real-world applicability.
Förderung
- China Postdoctoral Science Foundation
- National Natural Science Foundation of China
- Startup Foundation for Introducing Talent of Nanjing University of Information Science and Technology
- the Open Fund Program of State Key Laboratory of Trauma and Chemical Poisoning
Zitieren
APA
Wang, Y., Xu, T., & Zhu, Y. (2025). SPR-RAG: Semantic Parsing Retriever-Enhanced Question Answering for Power Policy. Algorithms, 18(12), 802. https://doi.org/10.3390/a18120802
Vancouver
Wang Y, Xu T, Zhu Y. SPR-RAG: Semantic Parsing Retriever-Enhanced Question Answering for Power Policy. Algorithms. 2025;18(12):802. doi:10.3390/a18120802
BibTeX
@article{Wang2025,
author = {Wang, Yufang and Xu, Tongtong and Zhu, Yihui},
title = {SPR-RAG: Semantic Parsing Retriever-Enhanced Question Answering for Power Policy},
journal = {Algorithms},
year = {2025},
volume = {18},
number = {12},
pages = {802},
doi = {10.3390/a18120802}
}
EUVIMED