用多模态检索增强生成，让AI教工程课更准更稳。
ARIA: Adaptive Retrieval Intelligence Assistant -- A Multimodal RAG Framework for Domain-Specific Engineering Education
- 结合文档、公式、图表解析，动态检索匹配课程内容
- 在20个相关问题上全答对，非相关问题拒答率达96.7%
- 适合高校工程教育智能助教，可快速部署于各类课程
构建高效的领域专用教育支持系统是推动教育AI发展的关键。尽管大语言模型（LLMs）表现出强大能力，但在专业教育场景中仍面临幻觉、知识更新受限和领域专长不足等问题。微调需重训练模型，计算开销大；通用模型因依赖泛化数据，在专业场景下常给出错误回答。为此，我们提出ARIA（自适应检索智能助手），一种用于高校课程的多模态检索增强生成（RAG）框架。ARIA采用多模态内容提取管道，结合Docling进行结构化文档分析、Nougat识别数学公式、GPT-4 Vision API解析图表，并使用e5-large-v2嵌入模型实现高语义性能与低延迟。通过设计提示与响应控制，保障教学一致性。我们在约翰霍普金斯大学大二级《静力学与材料力学》课程资料上评估ARIA，对比ChatGPT-5。结果表明，其在领域特定问题过滤中准确率达97.5%，正确回答全部20个相关问题，拒绝58/60个非相关查询，实现90.9%精确率、100%召回率及4.89/5.0平均响应质量。这些结果证明ARIA的课程无关架构具备可扩展性，适用于领域专用教育AI部署。
原文摘要 · Abstract (English)
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 mathematical formula recognition, and GPT-4 Vision API for diagram interpretation, with the e5-large-v2 embedding model for high semantic performance and low latency. This enables accurate processing of complex educational materials while maintaining pedagogical consistency through engineered prompts and response controls. We evaluate ARIA using lecture material from Statics and Mechanics of Materials, a sophomore-level civil engineering course at Johns Hopkins University, benchmarking against ChatGPT-5. Results demonstrate 97.5% accuracy in domain-specific question filtering and superior pedagogical performance. ARIA correctly answered all 20 relevant course questions while rejecting 58 of 60 non-relevant queries, achieving 90.9% precision, 100% recall, and 4.89/5.0 average response quality. These findings demonstrate that ARIA's course-agnostic architecture represents a scalable framework for domain-specific educational AI deployment.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。