Explainability in practice: NHR Süd-West
We cordially invite you to our Explainability in Practice workshop, organized by Saarland University. The workshop will be held online on June 3rd, 2026, from 13:00 to 16:00.
by Israel A. Azime and Paloma García-de-Herreros
In this workshop, we will focus on hands-on exercises that demonstrate how to analyze and interpret the predictions of machine learning models. The session is designed to be practical and interactive, allowing participants to explore model behavior through guided examples and real datasets.
Participants will work through a series of practical tasks across different machine learning settings, learning how to examine model decisions, understand the contribution of input features, and gain insights into why models produce particular predictions.
All materials used during the workshop are available here: https://gitlab.cs.uni-saarland.de/hpc/workshops/llm-expl
The workshop will include the following practical sessions:
-
Explainability on Tree Ensemble Models
-
Hands-on exercise using tabular data
-
Understanding how input features influence model predictions
-
-
Explainability in Language Models
-
Practical exercise on emotion classification
-
Interpreting how textual inputs contribute to the model’s predicted emotion
-
These exercises will guide participants step-by-step through the process of analyzing model predictions and understanding the factors that influence machine learning decisions.