
Using LLMs to Extract Structured Data from PDFs
February 13 @ 9:00 pm - 10:00 pm
This workshop is part of Stanford’s Love Data Week 2025. The topic is the use of large language models (LLMs) to extract structured data from PDFs or other data. Imagine that you have a PDF with some tabular data in it, like a table. You want that data to work in a computable form (like CSV) for use in Excel or other tools. Large language models (LLMs) might be able to help with this task. The Stanford AI Playground provides an easy mechanism to experiment with LLMs to help with data extraction or manipulation.
Please register here to reserve your spot for this workshop!
Location: Zoom and Velma Denning Room (120F), Green Library
Date and Time: 1:00PM to 2:00PM PT on Thursday, February 13, 2025
Instructor: Peter Mangiafico (Product Manager and Software Engineer, Digital Library Systems and Services)
This hybrid event will be held at Green Library. To access the library, please bring your Stanford ID or a valid government-issued ID.