Location: Nueces B (The Commons)

Description: This workshop offers a comprehensive exploration of Large Language Models (LLMs) and their application within the field of learning analytics. It covers a range of topics from the basics of chat and text models, embeddings, and fine-tuning to more advanced areas such as retrieval-augmented generation (RAG) and automating tasks using LLM APIs. Participants will learn about the use of LLMs in educational contexts, including creating synthetic datasets for research, automating feedback in real-time, and employing embeddings for educational use-cases. The tutorial is designed to showcase the potential of LLMs to revolutionize educational tools and strategies, enhancing both teaching and learning experiences through data-driven insights and automation.

Activities: Prompt Engineering: one-shot, many-shot prompting to optimize LLM interactions.

Intended Audience:

The workshop is ideal for a diverse audience, including educators, researchers, and technology enthusiasts with an interest in the intersection of AI and education. No prior knowledge of LLMs or programming is required, making it accessible to beginners, while also providing actionable insights for those with more experience in the field. It is particularly suited for individuals looking to leverage LLMs to enhance educational practices, develop innovative learning tools, and conduct educational research.

Preparation:

Pankiewicz, M., Baker, R.S. (2023) Large Language Models (GPT) for automating feedback on programming assignments. Proceedings of the 31st International Conference on Computers in Education. Zambrano, A.F., Liu, X., Barany, A., Baker, R.S., Kim, J., Nasiar, N. (2023) From nCoder to ChatGPT: From Automated Coding to Refining Human Coding. Proceedings of the International Conference on Quantitative Ethnography.

Tutorial Leader: Maciej Pankiewicz, University of Pennsylvania