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 · 2024

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.

Read the paper · More papers on PaperTik