Generative AI-Based Virtual Assistant using Retrieval-Augmented Generation: An evaluation study for bachelor projects
Generative AI-Based Virtual Assistant using Retrieval-Augmented Generation: An evaluation study for bachelor projects
基于检索增强生成（RAG）的生成式 AI 虚拟助手：针对学士学位项目的评估研究
Abstract: Large Language Models have been increasingly employed in the creation of Virtual Assistants due to their ability to generate human-like text and handle complex inquiries. While these models hold great promise, challenges such as hallucinations, missing information, and the difficulty of providing accurate and context-specific responses persist, particularly when applied to highly specialized content domains.
摘要： 大型语言模型（LLM）因其能够生成类人文本并处理复杂查询的能力，正越来越多地被应用于虚拟助手的开发中。尽管这些模型前景广阔，但仍面临诸多挑战，例如幻觉问题、信息缺失，以及在高度专业化的内容领域中难以提供准确且符合上下文的响应。
In this paper, we focus on addressing these challenges by developing a virtual assistant designed to support students at Maastricht University in navigating project-specific regulations. We propose a virtual assistant based on a Retrieval-Augmented Generation system that enhances the accuracy and reliability of responses by integrating up-to-date, domain-specific knowledge.
在本文中，我们致力于通过开发一款虚拟助手来解决这些挑战，该助手旨在支持马斯特里赫特大学（Maastricht University）的学生处理项目相关的特定规章制度。我们提出了一种基于检索增强生成（RAG）系统的虚拟助手，通过整合最新的领域特定知识，提高了响应的准确性和可靠性。
Through a robust evaluation framework and real-life testing, we demonstrate that our virtual assistant can effectively meet the needs of students while addressing the inherent challenges of applying Large Language Models to a specialized educational context. This work contributes to the ongoing discourse on improving LLM-based systems for specific applications and highlights areas for further research.
通过稳健的评估框架和实际测试，我们证明了该虚拟助手能够有效满足学生的需求，同时解决了将大型语言模型应用于专业教育环境时所固有的挑战。这项工作为改进针对特定应用的大型语言模型系统提供了参考，并指出了未来研究的方向。
Paper Details:
- Authors: Dumitru Verşebeniuc, Martijn Elands, Sara Falahatkar, Chiara Magrone, Mohammad Falah, Martijn Boussé, Aki Härmä
- Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Information Retrieval (cs.IR)
- Submission Date: 1 Apr 2026
- DOI: 10.48550/arXiv.2604.25924
论文详情：
- 作者： Dumitru Verşebeniuc, Martijn Elands, Sara Falahatkar, Chiara Magrone, Mohammad Falah, Martijn Boussé, Aki Härmä
- 学科分类： 计算与语言 (cs.CL)；人工智能 (cs.AI)；信息检索 (cs.IR)
- 提交日期： 2026年4月1日
- DOI： 10.48550/arXiv.2604.25924