Panel: Large Language Models in Education Assessment

Panelists: Mark Gierl, Okan Bulut, Jinnie Shin, Tahereh Firoozi, Seyma Nur Yildirim Erbasili
Large language models (LLMs), such as OpenAI’s GPT-3, are increasingly being used in educational assessment to help evaluate students’ knowledge and skills. Some innovative applications of LLMs in educational assessment include automated essay scoring, automatic item and feedback generation, generation of learning materials, and conversation-based assessment. In this panel, we will talk about different applications of LLMs in educational assessment and then discuss how to overcome significant challenges jeopardizing the positive impact of LLMs on educational outcomes. Each panelist has extensive research experience working with LLMs and other types of language models in the context of educational assessment.