5 citations · 18 across the 11 of their papers we have counts for
12 papers
ActivationReasoning: Logical Reasoning in Latent Activation Spaces
Lukas Helff, Ruben Härle, Wolfgang Stammer +6
Large language models (LLMs) excel at generating fluent text, but their internal reasoning remains opaque and difficult to control. Sparse autoencoders (SAEs) make hidden activatio…
Learning by Self-Explaining
Wolfgang Stammer, Felix Friedrich, David Steinmann +3
Much of explainable AI research treats explanations as a means for model inspection. Yet, this neglects findings from human psychology that describe the benefit of self-explanation…
Learning to Intervene on Concept Bottlenecks
David Steinmann, Wolfgang Stammer, Felix Friedrich +1
While deep learning models often lack interpretability, concept bottleneck models (CBMs) provide inherent explanations via their concept representations. Moreover, they allow users…
V-LoL: A Diagnostic Dataset for Visual Logical Learning
Lukas Helff, Wolfgang Stammer, Hikaru Shindo +2
Despite the successes of recent developments in visual AI, different shortcomings still exist; from missing exact logical reasoning, to abstract generalization abilities, to unders…
Boosting Object Representation Learning via Motion and Object Continuity
Quentin Delfosse, Wolfgang Stammer, Thomas Rothenbacher +2
Recent unsupervised multi-object detection models have shown impressive performance improvements, largely attributed to novel architectural inductive biases. Unfortunately, they ma…
Revision Transformers: Instructing Language Models to Change their Values
Felix Friedrich, Wolfgang Stammer, Patrick Schramowski +1
Current transformer language models (LM) are large-scale models with billions of parameters. They have been shown to provide high performances on a variety of tasks but are also pr…
Leveraging Explanations in Interactive Machine Learning: An Overview
Stefano Teso, Öznur Alkan, Wolfang Stammer +1
Explanations have gained an increasing level of interest in the AI and Machine Learning (ML) communities in order to improve model transparency and allow users to form a mental mod…
A Typology for Exploring the Mitigation of Shortcut Behavior
Felix Friedrich, Wolfgang Stammer, Patrick Schramowski +1
As machine learning models become increasingly larger, trained weakly supervised on large, possibly uncurated data sets, it becomes increasingly important to establish mechanisms f…
Interactive Disentanglement: Learning Concepts by Interacting with their Prototype Representations
Wolfgang Stammer, Marius Memmel, Patrick Schramowski +1
Learning visual concepts from raw images without strong supervision is a challenging task. In this work, we show the advantages of prototype representations for understanding and r…
SLASH: Embracing Probabilistic Circuits into Neural Answer Set Programming
Arseny Skryagin, Wolfgang Stammer, Daniel Ochs +2
The goal of combining the robustness of neural networks and the expressivity of symbolic methods has rekindled the interest in neuro-symbolic AI. Recent advancements in neuro-symbo…
Right for the Right Concept: Revising Neuro-Symbolic Concepts by Interacting with their Explanations
Wolfgang Stammer, Patrick Schramowski, Kristian Kersting
Most explanation methods in deep learning map importance estimates for a model's prediction back to the original input space. These "visual" explanations are often insufficient, as…
Making deep neural networks right for the right scientific reasons by interacting with their explanations
Patrick Schramowski, Wolfgang Stammer, Stefano Teso +5
Deep neural networks have shown excellent performances in many real-world applications. Unfortunately, they may show "Clever Hans"-like behavior -- making use of confounding factor…