Hey there!
We're excited to announce our very first LLM Practitioners Meetup Karlsruhe, happening on May 13th, 2025 at 6:30 PM in the SteamWork Coworking Space (Roonstraße 23a, 76137 Karlsruhe).
Our schedule (please read the talk descriptions at the bottom):
6:30 pm: Get together and short introduction of the meetup
7:00 pm: Session #1: How to Evaluate Fairness and Safety in LLM Applications?* (Talk by Sebastian Krauß)
7:30 pm: Break with pizza and drinks
8:00 pm: Session #2: Summarizing Large Documents Fast with Semantic Clustering** (Interactive Session by Manuel Naujoks)
8:30 pm: Discussions, pizza and drinks (until approx. 10 pm)
Also, please let us know what you're currently working on and/or which LLM-related topics you’d like to see discussed. This helps us get a better sense of your interests and tailor this and the upcoming events accordingly.
We’re looking forward to meeting you all and diving into all things LLMs together!
Best,
Leon & Ian
--------
Talk descriptions:
*) Talk #1: How to Evaluate Fairness and Safety in LLM Applications? (Sebastian Krauß)
„Fairness and safety are fundamental criteria for building trustworthy and high-quality AI systems, whether they are credit scoring models, hiring assistants, or healthcare chatbots. But what does it truly mean for an AI system to be fair and safe? In this talk, I will explore the potential risks and challenges associated with these principles and introduce various approaches and techniques for evaluating AI systems. The discussion will center on applications powered by Large Language Models (LLMs).“
**) Talk #2: Summarizing Large Documents Fast with Semantic Clustering (Manuel Naujoks)
„Summarizing large documents is challenging. Even though token windows keep increasing, there will always be documents too large for the naive approach.
Even if an entire document fits into the context, recall is affected by the primacy and recency effects. Content gets "lost in the middle".
Exhaustive use of a large context window also impacts costs.
In my presentation you will learn how to summarize large documents efficiently utilizing semantic clustering. I will also share a Google Colab notebook, so please bring your device, your OpenAI API key and a large document in your Google Drive.“
