发表机构
Dhillon School of Business, University of Lethbridge（莱斯布里奇大学迪隆商学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对商科校园AI辅导器，提出本地多课程RAG系统CourseChat，通过软硬件权衡选型，保留8B模型并验证其工程可行性，但未证实学习增益。
AI 中文摘要
基于检索增强生成（RAG）的校园AI辅导器必须将答案限定在指定课程材料中，同时将教科书和学生对话保留在机构基础设施内。我们提出了CourseChat，一个面向本科商科教育的本地化、多课程RAG辅导器，部署在校园网络网关之后，并旨在嵌入Moodle中使用。六个独立的课程，每个由各自的课程参考编号（CRN）标识，共享双边缘AI主机，运行FastAPI服务、本地向量数据库和由Ollama提供的本地大语言模型（LLM）。我们报告了两轮生成模型对比测试、一次独立的固定证据源保真度比较，以及对话和测验审计。几个较大的模型未通过课堂速度门槛，但一个12B模型和一个7B替代模型通过了。一个单独的混合专家候选模型改善了某些修正，但引入了新的事实和连续性错误。因此，我们保留8B生产模型，等待整体改进的证明，而不是声称8B普遍最优。软件更改改善了后续主题解析，同时保持了课程范围；65个模块中的435个预建问题将练习与实时生成解耦。结果支持将模型选择、证据选择、服务兼容性和产品设计视为联合工程决策。它们并未确立学习收益：教师评分、峰值负载能力和完整的公共网关接受度仍是单独的评估需求。
英文摘要
Campus AI tutors based on retrieval-augmented generation (RAG) must ground answers in assigned course materials while keeping textbooks and student dialogue on institutional infrastructure. We present CourseChat, an on-premises, multi-course RAG tutor for undergraduate business education, deployed behind a campus web gateway and intended for use embedded in Moodle. Six isolated course offerings, each keyed by its own course reference number (CRN), share twin-edge AI hosts running a FastAPI service, a local vector database, and a local large language model (LLM) served by Ollama. We report two generation-model bake-off rounds, a separate fixed-evidence source-fidelity comparison, and conversation and quiz audits. Several larger models failed the classroom speed gate, but a 12B model and a 7B alternative passed. A separate mixture-of-experts candidate improved some corrections while introducing new factual and continuity errors. We therefore retain the 8B production model pending a demonstrated overall improvement, rather than claiming that 8B is universally optimal. Software changes improved follow-up topic resolution while preserving course scope; 435 prebuilt questions across 65 modules decouple practice from live generation. The results support treating model choice, evidence selection, serving compatibility, and product design as a joint engineering decision. They do not establish learning gains: faculty ratings, peak-load capacity, and complete public-gateway acceptance remain separate evaluation needs.
Comments23 pages, 3 figures, 4 tables
