面向需求获取教育的检索增强自动化干系人：一项比较研究
A Retrieval-Augmented Automated Stakeholder for Requirements Elicitation Education: A Comparative Study
浏览论文内容
中文总结 AI 辅助
本研究针对需求工程教育中角色扮演受资源限制及LLM幻觉问题，采用基于LangChain的检索增强生成模拟干系人，实验表明其能提升需求获取问题质量与特征识别完整性。
中文摘要 AI 辅助
培养需求工程学生进行有效需求获取访谈所需的技能至关重要且具有挑战性，因为这除了需要技术知识外，还需要发展软技能。角色扮演在需求工程教育中被广泛采用以支持这些技能的发展，但常常受到时间和资源限制的约束。尽管大型语言模型（LLMs）的最新进展使得自动化和交互式的干系人模拟成为可能，但它们在需求工程教育中的应用仍受到幻觉和不一致响应的限制。为解决这些局限性，本研究探讨了使用检索增强生成（RAG），通过LangChain框架实现，以支持需求工程课程中的需求获取活动。我们与69名学生进行了对照实验，比较了与非技术教师角色扮演者互动的小组和与基于RAG的模拟干系人互动的小组。结果表明，虽然学生认为受邀的干系人更真实且更具吸引力，但基于RAG的自动化干系人产生了更高质量的获取问题和更完整的特征识别。
英文摘要
Developing the skills required for requirements engineering students to conduct effective requirements elicitation interviews is critical yet challenging, as it requires the development of soft skills in addition to technical knowledge. Role-playing is widely adopted in requirements engineering education to support the development of these skills but is often constrained by time and resource limitations. Although recent advances in large language models (LLMs) enable automated and interactive stakeholder simulations for role-playing, their application in requirements engineering education remains limited by hallucinations and inconsistent responses. To address these limitations, this study investigates the use of retrieval-augmented generation (RAG), implemented using the LangChain framework, to support requirements elicitation activities in a requirements engineering course. We conducted controlled experiments with 69 students, comparing cohorts who interacted with non-technical faculty role-players and those who engaged with RAG-based simulated stakeholders. The results indicate that while students perceived invited stakeholders as more realistic and engaging, the RAG-based automated stakeholder produced higher-quality elicitation questions and more complete feature identification.
发表机构
- King Saud University（沙特国王大学）
机构由 AI 辅助整理，请以论文原文为准。
