ARIA: Adaptive Retrieval Intelligence Assistant -- A Multimodal RAG Framework for Domain-Specific Engineering Education
Yue Luo, Dibakar Roy Sarkar, Rachel Herring Sangree, Somdatta Goswami

TL;DR
ARIA is a multimodal retrieval-augmented generation framework that enhances domain-specific educational support by accurately processing complex materials and outperforming general-purpose LLMs in engineering courses.
Contribution
The paper introduces ARIA, a novel multimodal RAG framework combining document analysis, formula recognition, and diagram interpretation for effective engineering education support.
Findings
97.5% accuracy in domain-specific question filtering
ARIA answered all 20 relevant course questions correctly
90.9% precision and 100% recall in question relevance detection
Abstract
Developing effective, domain-specific educational support systems is central to advancing AI in education. Although large language models (LLMs) demonstrate remarkable capabilities, they face significant limitations in specialized educational applications, including hallucinations, limited knowledge updates, and lack of domain expertise. Fine-tuning requires complete model retraining, creating substantial computational overhead, while general-purpose LLMs often provide inaccurate responses in specialized contexts due to reliance on generalized training data. To address this, we propose ARIA (Adaptive Retrieval Intelligence Assistant), a Retrieval-Augmented Generation (RAG) framework for creating intelligent teaching assistants across university-level courses. ARIA leverages a multimodal content extraction pipeline combining Docling for structured document analysis, Nougat for…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
