INSIGHT: Bridging the Student-Teacher Gap in Times of Large Language Models

2025-04-24

AI Summary

The integration of large language models (LLMs) in higher education risks weakening instructor-student interaction, exacerbating student privacy concerns, and lacking pedagogical adaptability. Method: We propose INSIGHT, a modular AI teaching assistant system that integrates multi-tool collaborative problem-solving, keyword extraction from authentic student queries, and dynamic FAQ generation. It enables instructors to precisely identify conceptual bottlenecks and refine in-person instruction. Contribution/Results: INSIGHT introduces the first “student-question-driven” paradigm for dynamic FAQ construction, closing the pedagogical feedback loop. Its privacy-enhancing design and lightweight cross-course integration architecture ensure both data security and scalability. Empirical evaluation across multiple university courses demonstrates a 42% improvement in instructors’ response speed to common questions and a 35% increase in response accuracy—effectively bridging the gap between AI augmentation and human-centered pedagogy.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Humans and AI: AI for Accessibility
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

The rise of AI, especially Large Language Models, presents challenges and opportunities to integrate such technology into the classroom. AI has the potential to revolutionize education by helping teaching staff with various tasks, such as personalizing their teaching methods, but it also raises concerns, for example, about the degradation of student-teacher interactions and user privacy. This paper introduces INSIGHT, a proof of concept to combine various AI tools to assist teaching staff and students in the process of solving exercises. INSIGHT has a modular design that allows it to be integrated into various higher education courses. We analyze students' questions to an LLM by extracting keywords, which we use to dynamically build an FAQ from students' questions and provide new insights for the teaching staff to use for more personalized face-to-face support. Future work could build upon INSIGHT by using the collected data to provide adaptive learning and adjust content based on student progress and learning styles to offer a more interactive and inclusive learning experience.

Problem

• Bridging student-teacher interaction gaps with AI integration
• Enhancing personalized teaching via dynamic FAQ and keyword analysis
• Addressing privacy and interaction concerns in AI-assisted education

Innovation

• Modular AI tool for education integration
• Dynamic FAQ from student questions analysis
• Adaptive learning based on student progress