4 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…
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…
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…