EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Lightweight Adapted Retrieval-Augmented Inference Network for Legal Issues

Hongting Qian, Jiaxin Lin, Jing Tang, Houkeng Zhou, Yun Peng, Lei Liu, Xiao Liu

Electronics · 08.07.2026 · 15 (14) · 2996

DOI: 10.3390/electronics15142996 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 08.07.2026. Verfasst von Hongting Qian und 6 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 21 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Adaptive Transformation of Digital Technology Platforms in 2025.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Legal text generation and legal question-and-answer tasks impose stringent requirements on factual accuracy, evidence traceability and normative consistency. Conventional dynamic retrieval-augmented generation methods are difficult to directly adapt to legal task demands such as legal provision citation, terminology standardization and case evidence organization. Following the DRAGIN paradigm, this paper proposes LARIN (Lightweight Adapted Retrieval-Augmented Inference Network for Legal Issues), an adaptive retrieval-augmented reasoning framework tailored for legal scenarios. While maintaining the mainstream dynamic retrieval workflow, LARIN makes targeted optimizations in three key modules: retrieval triggering, query construction and evidence fusion. Specifically, LINDA identifies retrieval trigger points by comprehensively considering uncertainty, attention influence and semantic importance; JUDGE rewrites queries for legal terms and statutory expressions; MERF conducts relevance ranking, redundancy elimination and evidence fusion for legal provisions and case materials. In the CAIL2018 Chinese legal judgment prediction task, LARIN achieves a charge prediction exact-match accuracy of 0.3316, a micro-F1 score of 0.3837, and a precision of 0.3951, while the sentencing exact-match accuracy reaches 0.1575. Meanwhile, its average retrieval frequency is 1.81 and average token consumption stands at 373.15. Experimental results on CAIL2018 demonstrate that legal-oriented adaptation based on DRAGIN improves retrieval-augmented reasoning in this Chinese legal judgment prediction setting while maintaining low retrieval overhead. Cross-dataset robustness on additional legal QA or judgment benchmarks remains to be further validated.

Förderung

  • Adaptive Transformation of Digital Technology Platforms in 2025

Zitieren

APA

Qian, H., Lin, J., Tang, J., Zhou, H., Peng, Y., Liu, L., & Liu, X. (2026). Lightweight Adapted Retrieval-Augmented Inference Network for Legal Issues. Electronics, 15(14), 2996. https://doi.org/10.3390/electronics15142996

Vancouver

Qian H, Lin J, Tang J, Zhou H, Peng Y, Liu L, et al. Lightweight Adapted Retrieval-Augmented Inference Network for Legal Issues. Electronics. 2026;15(14):2996. doi:10.3390/electronics15142996

BibTeX
@article{Qian2026,
  author = {Qian, Hongting and Lin, Jiaxin and Tang, Jing and Zhou, Houkeng and Peng, Yun and Liu, Lei and Liu, Xiao},
  title = {Lightweight Adapted Retrieval-Augmented Inference Network for Legal Issues},
  journal = {Electronics},
  year = {2026},
  volume = {15},
  number = {14},
  pages = {2996},
  doi = {10.3390/electronics15142996}
}
Kostenlos starten →