03434nam a2200337 a 4500 20260817161320.0 260224s20259999th mm 000 0 eng d .b12479317 AIT PJPR PMDS no.25-04 Nguyen Le Quang A hybrid architecture for legal reasoning : integrating retrieval-augmented generation and prompt compliance filtering Pathum Thani, Thailand : Asian Institute of Technology, 2025 46 leaves : ill.+ 1 online resource Project ; no. PJPR PMDS-25-04 A project report submitted in partial fulfillment of the requirements for the Degree of Master of Science (Professional) in Data Science and Artificial Intelligence Applications Master of Science (Professional) - Asian Institute of Technology, 2025 In the evolving landscape of legal technology, the application of Large Language Models (LLMs) presents new opportunities for automating legal reasoning, document understanding, and case-based decision support. However, traditional LLMs often lack factual grounding and suffer from hallucinations, posing risks in high-stakes legal contexts. To address these challenges, this thesis proposes a hybrid architecture that integrates Retrieval-Augmented Generation (RAG) with a prompt compliance filtering mechanism to build a robust and trustworthy legal assistant system.The architecture leverages a combination of cutting-edge LLMs, including GPT-4 (OpenAI, 2024), Qwen3 (Team, 2025), and Llama (Llama Team, 2024), as the generative core. These models are dynamically augmented with context retrieved from a comprehensive legal corpus comprising statutes, regulations, and historical legal cases. A dense retriever module queries relevant documents from the legal knowledge base, which are then combined with the user{u2019}s prompt to form a retrieval-augmented input for the generator. To ensure domain-specific compliance and output integrity, a template-based prompt-validation gateway is applied at both the input and output stages. This layer enforces structured syntax, filters unsafe or incomplete queries, and verifies legal accuracy and tone in the generated responses.The system is evaluated on tasks such as legal case prediction, statute-based question answering, and legal argument synthesis. Experimental results demonstrate that the hybrid approach improves factual consistency, legal relevance, and prompt adherence compared to baseline LLM outputs. The architecture is modular, scalable, and adaptable to multilingual legal systems, positioning it as a practical framework for future intelligent legal assistants. Information retrieval Automation Generative artificial intelligence Chaklam Silpasuwanchai, Chairperson Chutiporn Anutariya, Examination Committee Chantri Polprasert, Examination Committee Asian Institute of Technology. Project ; no. PJPR PMDS-25-04 Full-Text http://203.159.5.9/ait-thesis/detail.php?q=B23688 .b12479317 mnarc a 260317 0 260310 m h a 0 mnarc 67 Barcode : - CREATED : 2026-02-24 RECORD # : i1357629x LPATRON : 0 LCHKIN : - # RENEWALS : 0 # OVERDUE : 0 IUSE3 : 0 TOT CHKOUT : 0 TOT RENEW : 0 823 823 0 0 0 0 MAIN MAIN mnarc 2026-08-17 0 AIT PJPR PMDS no.25-04 2026-08-17 16:13:20 1 2026-08-17 67