Efficient Information Retrieval – Part III

A RAG system may produce good results – but how can it be optimised to meet the exact requirements and quality standards of a specific application?

In Part III of the workshop series, you will learn how to systematically improve RAG systems with the help of human feedback. The goal is to create a system that is more accurate, robust and better adapted to real-world usage scenarios.

Key topics:

· Core principles of Reinforcement Learning with Human Feedback (RLHF) in the context of RAG

· Creating and evaluating feedback datasets

· Adjusting retrieval parameters based on human judgments

· Retrieval optimisation vs. generation optimisation

· Practical tools for feedback loops and logging

You will evaluate real RAG answers, run small optimisation cycles and observe how the system measurably improves.

👉 Part III bridges the gap between technical RAG design (Parts I & II) and productive assistance systems (Part IV).
After the workshop, you will know how to optimise RAG systems with the help of human feedback.

Requirements:
Participation in Part I & II of the workshop series
or equivalent experience with programming and RAG systems.

Registration & participation

Registration is binding. If you are unable to attend, please cancel your ticket in good time to allow other participants to take your place.

Important Information

Photographs, audio recordings and films will be made during the event. By participating in the event, you agree that photos, audio and video recordings in which you are recognizable may be published as part of the public relations work of the AI Service Center Berlin-Brandenburg and the HPI.

The is a project of the Federal Ministry of Research, Technology and Space. Its aim is to lower the barriers for using AI in business and society.

Are you interested in our free workshops and other events that we offer? Then sign up for our newsletter.

Also check out other Workshops in Potsdam, Entertainment events in Potsdam.