Explore a thought-provoking conference talk that examines the intersection of Large Language Models (LLMs) and database systems, delivered by Professor Carsten Binnig from TU Darmstadt. Delve into the limitations of using LLMs like GPT-4-turbo for query answering over multi-model data, including issues such as hallucinations and performance overhead. Learn about an alternative approach that builds upon existing database technology, augmented with LLMs where necessary, to efficiently handle user queries across multi-model data. Gain insights from Binnig's extensive experience as a Full Professor at TU Darmstadt and Visiting Researcher at Google Systems Research Group, whose work has earned multiple accolades including a Google Faculty Award and Best Paper awards. The presentation, part of the Dutch Seminar on Data Systems Design series, offers valuable perspectives on the future of database systems and their integration with emerging AI technologies.
Overview
Syllabus
We hold bi-weekly talks on Fridays from PM to 5 PM CET for and by researchers and practitioners designing and implementing data systems. The objective is to establish a new forum for the Dutch Data Systems community to unite, foster collaborations between its members, and bring in high-quality international speakers. We would like to invite all researchers, especially PhD students, who are working on related topics to join the events. It is an excellent opportunity to receive feedback early on from researchers in your field.
Taught by
DSDSD - Dutch Seminar on Data Systems Design
Related Courses
-
Leveraging Generative AI for Data Processing and Database Management
-
LingoDB: An Open Compilation and Optimization Framework for Sustainable Data Processing
-
Efficient CSV Parsing - On the Complexity of Simple Things
-
C3: Compressing Correlated Columns - A Framework for Multi-Column Data Compression
-
Lambda Functions and List Operations in DuckDB SQL
-
Parameter-Efficient Automation of Data Wrangling Tasks with Prefix-Tuning
