Dense retrieval and reranking for referenced provisions in electric power audit systems
PLOS One · 13.03.2026 · 21 (3) · e0344683
DOI: 10.1371/journal.pone.0344683 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, online erschienen am 13.03.2026. Verfasst von Qinglin Meng und 6 weiteren Autor:innen. Beteiligte Einrichtung: Green Power Research Institute, Tianjin Renai College, Tianjin, China. Hauptthemen laut MEDLINE: Information Storage and Retrieval, Electric Power Supplies. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 20 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Zhejiang Lab.
Abstract (Originalsprache)
Electric power audits require practitioners to describe an audit issue and justify the final opinion by citing an appropriate referenced provision. In practice, the referenced provision should be retrieved from an authoritative provision corpus rather than generated, because correctness and traceability are critical in audit workflows. This paper proposes a dense retrieval and reranking framework for referenced provision retrieval in electric power audit systems. The method follows a two-stage pipeline: a two-tower dense retriever efficiently recalls a small candidate set (top-20) from a large provision corpus, and a one-tower scoring model performs fine-grained reranking by jointly modeling the audit problem description and each candidate provision. To strengthen semantic matching under audit-specific contexts, the audit issue category is incorporated into the reranking input. Experiments are conducted on a Chinese electric power audit text dataset, demonstrating that the proposed retrieval–reranking design provides an effective and practical solution for accurate referenced provision retrieval.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Green Power Research Institute, Tianjin Renai College, Tianjin, China.
- College of Intelligence and Computing, Tianjin University, Tianjin, China.
- School of Electrical and Information Engineering, Tianjin University, Tianjin, China.
- State Grid Tianjin Electric Power Company, State Grid Corporation of China, Tianjin, China.
- China Electric Power Research Institute, State Grid Corporation of China, Beijing, China.
- Tianjin Electric Power Technology Development Co., Ltd, State Grid Corporation of China, Tianjin, China.
ORCID-Profile: Qinglin Meng, Sheharyar Hussain
Förderung
- Zhejiang Lab
Zitieren
APA
Meng, Q., He, Y., Hussain, S., Zhou, F., Xu, J., Zhao, G., & Xiong, D. (2026). Dense retrieval and reranking for referenced provisions in electric power audit systems. PLOS One, 21(3), e0344683. https://doi.org/10.1371/journal.pone.0344683
Vancouver
Meng Q, He Y, Hussain S, Zhou F, Xu J, Zhao G, et al. Dense retrieval and reranking for referenced provisions in electric power audit systems. PLOS One. 2026;21(3):e0344683. doi:10.1371/journal.pone.0344683
BibTeX
@article{Meng2026,
author = {Meng, Qinglin and He, Ying and Hussain, Sheharyar and Zhou, Fei and Xu, Jianbin and Zhao, Guanqiao and Xiong, Deyi},
title = {Dense retrieval and reranking for referenced provisions in electric power audit systems},
journal = {PLOS One},
year = {2026},
volume = {21},
number = {3},
pages = {e0344683},
doi = {10.1371/journal.pone.0344683}
}
EUVIMED