TY  - BOOK
AU  - Nguyen Le Quang
AU  - Chaklam Silpasuwanchai,
AU  - Chutiporn Anutariya,
AU  - Chantri Polprasert,
TI  - A hybrid architecture for legal reasoning: integrating retrieval-augmented generation and prompt compliance filtering
T2  - Project
PY  - 2025///
CY  - Pathum Thani, Thailand
PB  - Asian Institute of Technology
KW  - Information retrieval
KW  - Automation
KW  - Generative artificial intelligence
N1  - 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
N2  - 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.
UR  - http://203.159.5.9/ait-thesis/detail.php?q=B23688
ER  -