EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

AI Legal Assistant for Saudi Commercial Law

Omar Alobaid, Saud Alkathery, Abdulaziz Alamri, Abdulmajeed Alzouman, Raid Almousa, Emad Alaskar, Meshal Alfarhood

Electronics · 19.11.2026 · 15 (22) · 5404

DOI: 10.3390/electronics15225404 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 19.11.2026. Verfasst von Omar Alobaid und 6 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Access to legal information in Saudi Arabia remains challenging despite the public availability of its laws, particularly in commercial disputes where relevant provisions are distributed across multiple legal frameworks and expressed in formal language that can be difficult for non-specialists to interpret. This paper presents an AI-powered legal advisory system for Saudi commercial cases that uses Retrieval-Augmented Generation (RAG) to provide legal guidance grounded directly in statutory text. Given a complaint written in natural Arabic, the system identifies the relevant Saudi laws, retrieves the applicable legal articles, and generates a structured legal opinion covering an analysis of the case, a direct answer to the user’s question, the supporting legal provisions, the user’s rights, and an assessment of the strength of the user’s legal position. Unlike general-purpose legal assistants, the system does not rely on unsupported legal knowledge or attempt to predict judicial outcomes; its substantive claims are grounded in retrieved legal provisions. The system was evaluated on 200 real commercial cases from the Saudi Ministry of Justice judicial portal, for which actual court rulings and judge-cited articles were available as references. Three independent large language models—Claude Sonnet 4.5, DeepSeek, and GPT-4o—were tested as candidate generation models, achieving overall scores of 76.0%, 81.9%, and 87.0%, respectively. GPT-4o was selected as the primary generation model following this benchmark evaluation using different metrics such as retrieval coverage, article coverage, ruling accuracy, legal justification, and completeness. The results demonstrate the potential of retrieval-based legal systems to provide traceable and accessible legal guidance for Arabic-speaking users in the Saudi commercial law domain. The proposed solution has also been integrated into a live application, demonstrating its practical applicability and potential to provide accessible legal guidance to the general public.

Zitieren

APA

Alobaid, O., Alkathery, S., Alamri, A., Alzouman, A., Almousa, R., Alaskar, E., & Alfarhood, M. (2026). AI Legal Assistant for Saudi Commercial Law. Electronics, 15(22), 5404. https://doi.org/10.3390/electronics15225404

Vancouver

Alobaid O, Alkathery S, Alamri A, Alzouman A, Almousa R, Alaskar E, et al. AI Legal Assistant for Saudi Commercial Law. Electronics. 2026;15(22):5404. doi:10.3390/electronics15225404

BibTeX
@article{Alobaid2026,
  author = {Alobaid, Omar and Alkathery, Saud and Alamri, Abdulaziz and Alzouman, Abdulmajeed and Almousa, Raid and Alaskar, Emad and Alfarhood, Meshal},
  title = {AI Legal Assistant for Saudi Commercial Law},
  journal = {Electronics},
  year = {2026},
  volume = {15},
  number = {22},
  pages = {5404},
  doi = {10.3390/electronics15225404}
}
Kostenlos starten →