Metraipolis › archive › dc_8ba348a45bd0

Mitigating AI Risks in Computing Education via LLM-Driven Lecture Video Curation — arXiv:2608.16131

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.16131
License (as archived)
CC0-1.0
Archived
2026-10-18T19:07:32.289Z
SHA-256 of the archived text
3c8c1028974ddb53772aacc8d260ef737e0fd4f13bd5839ca4223355796728c8
Stable URL of this page
https://metraipolis.com/documento/dc_8ba348a45bd0

How to cite

Mitigating AI Risks in Computing Education via LLM-Driven Lecture Video Curation — arXiv:2608.16131 — arXiv (en), https://arxiv.org/abs/2608.16131 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8ba348a45bd0 (Metraipolis archive dc_8ba348a45bd0, sha256 3c8c1028974ddb53772aacc8d260ef737e0fd4f13bd5839ca4223355796728c8)
BibTeX
@misc{dc8ba348a45bd0,
  title = {Mitigating AI Risks in Computing Education via LLM-Driven Lecture Video Curation — arXiv:2608.16131},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.16131},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8ba348a45bd0; sha256 3c8c1028974ddb53772aacc8d260ef737e0fd4f13bd5839ca4223355796728c8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16131. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: governance digitale e beni comuni (retro-catalogo arXiv: annunci del 2026-08-18 in cs.CY).
Categorie arXiv: Computers and Society (cs.CY).
Pagina del lavoro: https://arxiv.org/abs/2608.16131 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T18:12:36.544Z dalla pagina https://arxiv.org/catchup/cs.CY/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).