LLM Workshop: Learn How To Use AI to Analyse Your Corpus

Join us for an engaging and accessible workshop tailored for non-technical researchers eager to get the most out of their text data. In this hands-on session, we will show how to use open-source large language models to extract information from your datasets. Whether you're new to the world of text analysis or seeking to get up to date with potential applications of recent models, this workshop provides a basic introduction to key concepts, including prompt engineering and best practices in validation. 

The primary focus of this workshop is structured information extraction. By applying structure to texts, data can be reorganized into a tabular format for subsequent analyses. To make the concept more concrete, consider the following examples

• Applying labels to sections or paragraphs in a corpus of academic papers related to environmental science, such as "Climate Change," "Biodiversity," "Renewable Energy," and so on 

• Attributing quotes to speakers in press releases, and extracting those speaker's affiliations and positions

A significant portion of the workshop will be dedicated to guiding you through the application of these methods to your own text datasets.

Programme

• 9.00 walk-in
• 9.30 start: intro notebook, how to use Colab
• 10.00 present slides
• 10.30 - 11.15 hands-on session
• 11.15 - 11.30 coffee break
• 11.30 hands-on session
• 12.00 - 12.30 reflection and feedback

Sign up before the 28th of March using the button below.