AI-大学：一个基于大语言模型的平台，旨在实现科学课堂的教学一致性

AI-University: An LLM-based platform for instructional alignment to scientific classrooms

April 11, 2025

作者: Mostafa Faghih Shojaei, Rahul Gulati, Benjamin A. Jasperson, Shangshang Wang, Simone Cimolato, Dangli Cao, Willie Neiswanger, Krishna Garikipati

cs.AI

摘要

我们推出AI大学（AI-U），这是一个灵活的人工智能驱动课程内容传递框架，能够适应教师的教学风格。AI-U的核心在于通过检索增强生成（RAG）技术微调大型语言模型（LLM），从讲座视频、笔记和教材中生成与教师教学理念一致的回答。以研究生层次的有限元方法（FEM）课程为例，我们展示了一个可扩展的流程，系统地构建训练数据，利用低秩适应（LoRA）微调开源LLM，并通过基于RAG的合成优化其回答。我们的评估结合了余弦相似度、基于LLM的评估和专家评审，显示出与课程材料的强一致性。我们还开发了一个原型网络应用程序，访问地址为https://my-ai-university.com，该应用通过将AI生成的回答链接到相关课程材料的具体部分及开放访问视频讲座的时间戳实例，增强了可追溯性。我们的专家模型在86%的测试案例中与参考资料的余弦相似度更高。LLM评估者也发现，我们的专家模型在大约五分之四的情况下优于基础Llama 3.2模型。AI-U为AI辅助教育提供了一种可扩展的方法，为高等教育中的更广泛应用铺平了道路。在此，我们的框架以FEM课程为背景进行了展示——该课程是培养工程科学博士和硕士研究生的核心内容。然而，这一背景是更广泛情境中的一个特例：即针对科学研究内容微调LLM。

English

We introduce AI University (AI-U), a flexible framework for AI-driven course content delivery that adapts to instructors' teaching styles. At its core, AI-U fine-tunes a large language model (LLM) with retrieval-augmented generation (RAG) to generate instructor-aligned responses from lecture videos, notes, and textbooks. Using a graduate-level finite-element-method (FEM) course as a case study, we present a scalable pipeline to systematically construct training data, fine-tune an open-source LLM with Low-Rank Adaptation (LoRA), and optimize its responses through RAG-based synthesis. Our evaluation - combining cosine similarity, LLM-based assessment, and expert review - demonstrates strong alignment with course materials. We also have developed a prototype web application, available at https://my-ai-university.com, that enhances traceability by linking AI-generated responses to specific sections of the relevant course material and time-stamped instances of the open-access video lectures. Our expert model is found to have greater cosine similarity with a reference on 86% of test cases. An LLM judge also found our expert model to outperform the base Llama 3.2 model approximately four times out of five. AI-U offers a scalable approach to AI-assisted education, paving the way for broader adoption in higher education. Here, our framework has been presented in the setting of a class on FEM - a subject that is central to training PhD and Master students in engineering science. However, this setting is a particular instance of a broader context: fine-tuning LLMs to research content in science.