Tailoring Chatbots for Higher Education: Some Insights and Experiences

TL;DR

This paper discusses the practical process and benefits of customizing large language models to improve their relevance and accuracy for educational tasks in higher education, based on experiences at ETH Zurich.

Contribution

It provides insights and practical experiences on customizing large language models specifically for higher education institutions.

Findings

Customization improves response relevance in educational contexts

Practical strategies for tailoring language models are outlined

Enhanced educational experiences through tailored AI tools

Abstract

The general availability of general-purpose Large Language Models continues to impact on higher education, yet they may not always be useful for specialized tasks. When using these models, oftentimes the need for particular domain knowledge becomes quickly apparent, and the desire for customized bots arises. Customization holds the promise of leading to more accurate and contextually relevant responses, enhancing the educational experience. This report relates insights and experiences from one particular technical university in Switzerland, ETH Zurich, to describe what "customizing" Large Language Models means in practical terms for higher education institutions.