Join us for an exciting new event series exploring the role of artificial intelligence (AI) in assessment and science education. Engage with speakers from across the Faculty of Science (and beyond) as they share their insights on AI's design, opportunities, limitations, evidence of impact, applications in teaching, learning, and assessment, and much more. This series offers a unique opportunity expand and leverage your understanding of AI, build connections with colleagues, and be part of growing, innovative AI community at the Faculty of Science and UBC.
Series Organizer:
- If you have any questions about this series, please reach out to us at skylight@science.ubc.ca.
Previous Events
February 2025
Should an LLM Grade Your Students' Exams?
When: Wednesday, February 26th, 2025 | 12:00pm-1:00pm
Where: Earth Sciences Building (ESB), Room 5104 (map)
Presenter:
- Dr. Vered Shwartz, Assistant Professor (Department of Computer Science, UBCV)
Description:
Evaluating and grading students’ work is a difficult and time-consuming task. The general-purpose nature of large language models (LLMs), along with their vast knowledge across a wide range of domains, positions them as a strong candidate for automatic assessment of free-text answers. However, there are various limitations pertaining to the reliability of LLMs as evaluators and fairness issues that arise from LLM-based automated assessment. This talk will discuss several factors that need to be considered when deciding whether and how to utilize LLMs for this task.