Mitigating AI Risks in Computing Education via LLM-Driven Lecture Video Curation

2026-08-17

AI Summary

This study addresses the risks of hallucination and cognitive bypass associated with generative AI in programming education by proposing a constrained video retrieval paradigm as an alternative to open-ended text generation. Through LLM-based temporal retrieval, automated evaluation, and multi-model benchmarking, the approach ensures instructional accuracy and reliability. Experimental results demonstrate that proprietary model responses achieve expert-level quality, while a 900-participant pilot confirms high engagement and effective support for foundational concept review in novice courses. Ultimately, this research enables the safe, high-fidelity integration of AI into programming pedagogy, offering an innovative solution to mitigate critical educational risks inherent in current generative systems.

Abstract

This study evaluates the effectiveness of utilising large language models (LLMs) to retrieve targeted segments from delivered video recordings to answer student questions in introductory programming environments. By restricting AI to identifying existing, educator-verified media rather than generating open-ended text, this approach aims to mitigate common pedagogical risks such as generative hallucinations and cognitive bypassing. We benchmarked three distinct models, two proprietary (Gemini 3.1 Pro and GPT 5.4 Pro) and one open-weight (Qwen3.5 397B), against a human lecturer's manual video selections. An automated judging framework subsequently assessed the outputs for relevance, sufficiency, redundancy, and the presence of extraneous material. While the AI-retrieved timestamps rarely shared exact overlaps with the human baseline, the proprietary models achieved near-parity with the expert in delivering sufficient and highly relevant answers. Furthermore, a pilot deployment of this retrieval system in a large C programming cohort (n~=900) demonstrated strong user engagement, with students primarily utilising the tool to review foundational concepts. By leveraging AI to retrieve established lecture material, this approach shows potential for a reliable, high-fidelity pathway for safely integrating LLMs into novice computing courses.

Problem

• AI risks
• computing education
• generative hallucinations
• cognitive bypassing
• lecture video curation

Innovation

• LLM-driven video retrieval
• hallucination mitigation
• cognitive bypassing prevention
• automated evaluation framework
• computing education