Leveraging Large Language Models in R: Practical Applications with {ellmer}
Regular talk, 9:40 - 10:40 AM
As Large Language Models (LLMs) become more accessible they offer R developers new opportunities to automate and enhance text analysis and generation tasks. For mixed-methods researchers LLMs can improve efficiency in both deductive and inductive coding for content analysis making them a valuable tool for streamlining qualitative research workflows.
This session will introduce practical applications of LLMs in R using the {ellmer} package focusing on three key use cases: image-to-text generation text classification and summarization. Through hands-on examples attendees will learn how to integrate LLMs into their workflows and evaluate the trade-offs between using local models versus cloud-based models.
Beyond technical implementation the session will cover essential prompt engineering techniques—providing actionable strategies for optimizing LLM outputs—as well as ethical considerations including bias interpretability and current limitations.
By the end of this session participants will be equipped with practical tools best practices and insights into the evolving role of LLMs in R development. Attendees will leave with a clear understanding of how to apply these techniques to enhance the quality and efficiency of their own analytical work.
 |
Pronouns:Portland, OR, USAYan Liu is a data analyst from Center for Outcomes Research and Education (CORE), where she leverages her expertise in survey work, data analysis and data visualization to drive impactful insights in healthcare. Yan is looking forward to sharing her latest findings on implementing large language models with R with real world examples. |