AI Legal Assistant for Saudi Commercial Law

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.

Authors

Institutions

Publication Details

Journal
Electronics
Published
2026-11-19
DOI
https://doi.org/10.3390/electronics15225404
Primary Topic
Artificial Intelligence in Law
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

AI Legal Assistant for Saudi Commercial Law

Omar Alobaid, Meshal Alfarhood, Abdulaziz Alamri, Emad Alaskar et al.
Electronics
Artificial Intelligence in Law
article

AI Legal Assistant for Saudi Commercial Law

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

Abstract

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.

ElectronicsVol. 15(22)
King Saud University (SA)
Artificial Intelligence in Law
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon