Evidence-Grounded Vision–Language Reporting for Underground Cable Inspection via Claim Verification and Preference Adaptation
Algorithms · 10.11.2026 · 19 (11) · 986
DOI: 10.3390/a19110986 ↗Kurz gefasst
Fachartikel in der Zeitschrift Algorithms, online erschienen am 10.11.2026. Verfasst von Jianrong Zhang und 5 weiteren Autor:innen. Die Arbeit nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: State Grid Science and Technology Project.
Abstract (Originalsprache)
Underground cable inspection requires reliable reports that describe visible defects while avoiding unsupported engineering conclusions and omissions. Existing detector-based workflows provide localized observations but lack integrated verification of heterogeneous claims and explicit control of report completeness. We hypothesize that claim-type-aware evidence verification, dependency reasoning, and coverage-aware preference adaptation can jointly improve reporting accuracy and completeness. Accordingly, we propose an evidence-grounded vision–language framework that verifies visual and engineering claims using detector evidence and source-traceable technical knowledge, propagates upstream uncertainty, and constructs reliability–coverage-guided preferences for parameter-efficient adaptation. On a simulated dataset containing 528 images and 1025 annotated defect instances, the proposed method improves Claim Macro-F1 from 0.548 (ordinary DPO) to 0.743, reduces the unsupported claim rate from 0.196 to 0.153, and decreases detector-referenced Defect Omission from 0.311 to 0.116. The Claim Macro-F1 difference from deterministic detector-and-rule-based reporting is not statistically significant. These findings support evidence-guided preliminary inspection reporting within the evaluated setting, while external validation in operating cable tunnels remains necessary.
Förderung
- State Grid Science and Technology Project
Zitieren
APA
Zhang, J., Wei, S., Chen, Y., Wang, S., Chen, X., & Cui, Q. (2026). Evidence-Grounded Vision–Language Reporting for Underground Cable Inspection via Claim Verification and Preference Adaptation. Algorithms, 19(11), 986. https://doi.org/10.3390/a19110986
Vancouver
Zhang J, Wei S, Chen Y, Wang S, Chen X, Cui Q. Evidence-Grounded Vision–Language Reporting for Underground Cable Inspection via Claim Verification and Preference Adaptation. Algorithms. 2026;19(11):986. doi:10.3390/a19110986
BibTeX
@article{Zhang2026,
author = {Zhang, Jianrong and Wei, Siming and Chen, Yang and Wang, Shimin and Chen, Xu and Cui, Qiushi},
title = {Evidence-Grounded Vision–Language Reporting for Underground Cable Inspection via Claim Verification and Preference Adaptation},
journal = {Algorithms},
year = {2026},
volume = {19},
number = {11},
pages = {986},
doi = {10.3390/a19110986}
}
EUVIMED