Tuning LLMs for Text Analysis

Abstract

This one-day workshop provides hands-on, research-oriented training in fine-tuning large language models (LLMs) for extracting reliable, domain-specific insights from text data. Aimed at researchers across disciplines, it combines conceptual clarity with guided Jupyter notebooks, teaching participants how to fine-tune open-source models, apply efficient techniques like LoRA, and evaluate performance with reproducible workflows. No coding background is required — just curiosity and readiness to engage with code. By the end of the day, participants will leave with practical notebooks, evaluation pipelines, and a clear understanding of when and how to fine-tune (or when to rely on prompt engineering) for robust, ethical, and reproducible research.