Leveraging Graph-RAG and Prompt Engineering to Enhance LLM-Based Automated Requirement Traceability and Compliance Checks

TL;DR

This paper presents a novel approach combining Graph-RAG and advanced prompt engineering to improve automated requirement traceability and compliance checks using large language models, especially in regulated industries.

Contribution

It introduces an integrated Graph-RAG framework with prompt engineering techniques to enhance LLM performance in requirement traceability and compliance tasks.

Findings

Improved accuracy and context-awareness over baseline methods

Significant performance enhancements with Graph-RAG and prompt engineering

Challenges include high cost and data dependency

Abstract

Ensuring that Software Requirements Specifications (SRS) align with higher-level organizational or national requirements is vital, particularly in regulated environments such as finance and aerospace. In these domains, maintaining consistency, adhering to regulatory frameworks, minimizing errors, and meeting critical expectations are essential for the reliable functioning of systems. The widespread adoption of large language models (LLMs) highlights their immense potential, yet there remains considerable scope for improvement in retrieving relevant information and enhancing reasoning capabilities. This study demonstrates that integrating a robust Graph-RAG framework with advanced prompt engineering techniques, such as Chain of Thought and Tree of Thought, can significantly enhance performance. Compared to baseline RAG methods and simple prompting strategies, this approach delivers more accurate and context-aware results. While this method demonstrates significant improvements in performance, it comes with challenges. It is both costly and more complex to implement across diverse contexts, requiring careful adaptation to specific scenarios. Additionally, its effectiveness heavily relies on having complete and accurate input data, which may not always be readily available, posing further limitations to its scalability and practicality.