AI University: An LLM-Powered Learning Assistant for Engineering—A Finite Element Method Case Study

TMLR Paper6151 Authors

Abstract: We introduce AI University (AI-U), a flexible framework for AI-driven course content delivery that adapts to the classes' instructional styles. At its core, AI-U combines a fine-tuned large language model (LLM) with retrieval-augmented generation (RAG) and a reasoning synthesis model to generate instructional style-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, expert review, and user studies—demonstrates strong alignment with course materials. We have also developed a prototype web application, available at (link removed for anonymous submission), that enhances the instructional content of the AI-generated responses with references to relevant sections of the course material and clickable links to time-stamped instances of the open-access video lectures. Our expert model is found to be higher scoring by a quantitative measure on 86% of test cases. An LLM judge also found our expert model to outperform state-of-the-art open source models approximately four times out of five. Human evaluation by advanced users showed a preference for our expert model approximately twice as often as for the competing open-source model. AI-U offers a scalable approach to AI-assisted education, paving the way for broader adoption in higher education. By presenting our framework in the setting of a class on FEM—a subject that is central to training PhD and Master students in engineering science—we offer a template with potential for extension across STEM fields.

Submission Length: Regular submission (no more than 12 pages of main content)

Assigned Action Editor: ~Sarath_Chandar1

Submission Number: 6151