用图谱增强检索与思维链提示，提升需求一致性检查准确率
Leveraging Graph-RAG and Prompt Engineering to Enhance LLM-Based Automated Requirement Traceability and Compliance Checks
- 结合图谱RAG与思维链提示，提升大模型对需求的推理能力
- 相比基线方法，关键需求匹配准确率提升显著（未给出具体数值）
- 适合金融、航空航天等强监管领域的自动化合规审查
确保软件需求规格（SRS）与组织或国家层面要求的一致性，在金融、航空航天等受监管领域至关重要。这些领域需保障系统一致性、遵循法规框架、减少错误并满足关键预期。尽管大语言模型（LLMs）潜力巨大，但在信息检索和推理能力方面仍有提升空间。本研究证明，将稳健的Graph-RAG框架与先进提示工程（如Chain of Thought、Tree of Thought）结合，能显著提升性能。相比基线RAG方法和简单提示策略，该方法产生更准确、更具上下文感知的结果。然而，该方法成本高、实现复杂，需针对不同场景精细适配；其效果高度依赖输入数据的完整性和准确性，这限制了其可扩展性与实用性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。