Can Small Language Models With Retrieval-Augmented Generation Replace Large Language Models When Learning Computer Science?
Suqing Liu, Zezhu Yu, Feiran Huang, Yousef Bulbulia, Andreas Bergen, Michael Liut
Abstract
Leveraging Large Language Models (LLMs) for personalized learning and support is becoming a promising tool in computing education. AI Assistants can help students with programming, problem-solving, converse with them to clarify course content, explain error messages to help with debugging, and much more. However, using cloud-based LLMs poses risks around data security, privacy, but also control of the overarching system.
Topics & Concepts
Computer scienceLanguage modelNatural language processingArtificial intelligenceUniversal Networking LanguageInformation retrievalNatural languageComprehension approachTopic ModelingNatural Language Processing TechniquesMultimodal Machine Learning Applications