Watch a 17-minute conference talk exploring the potential of prefix-tuning as a lightweight alternative to fine-tuning Large Language Models (LLMs) for data wrangling tasks. Learn how this parameter-efficient approach automatically learns continuous prompts without updating original LLM parameters, allowing for reuse across tasks while maintaining comparable performance. Discover the evaluation results across common data wrangling tasks like entity matching, error detection, and data imputation, where prefix-tuning achieves within 2.3% of fine-tuning performance while using only 0.39% of the parameter updates. Presented by David Vos, an MSc graduate in Artificial Intelligence, at the Dutch Seminar on Data Systems Design (DSDSD), this talk demonstrates how prefix-tuning offers a storage-efficient solution for automating data integration and cleaning tasks with LLMs.