collaborators

9 papers

cs.LG2026

Uncertainty Estimation for Heterophilic Graphs Through the Lens of Information Theory

Dominik Fuchsgruber, Tom Wollschläger, Johannes Bordne +1

While uncertainty estimation for graphs recently gained traction, most methods rely on homophily and deteriorate in heterophilic settings. We address this by analyzing message pass…

cs.LG2026

The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independence

Tom Wollschläger, Jannes Elstner, Simon Geisler +3

The safety alignment of large language models (LLMs) can be circumvented through adversarially crafted inputs, yet the mechanisms by which these attacks bypass safety barriers rema…

cs.LG2026

The Illusion of Certainty: Uncertainty Quantification for LLMs Fails under Ambiguity

Tim Tomov, Dominik Fuchsgruber, Tom Wollschläger +1

Accurate uncertainty quantification (UQ) in Large Language Models (LLMs) is critical for trustworthy deployment. While real-world language is inherently ambiguous, reflecting aleat…

cs.LG2025

Diffusion LLMs are Natural Adversaries for any LLM

David Lüdke, Tom Wollschläger, Paul Ungermann +2

We introduce a novel framework that transforms the resource-intensive (adversarial) prompt optimization problem into an \emph{efficient, amortized inference task}. Our core insight…

cs.LG2025

Attacking Large Language Models with Projected Gradient Descent

Simon Geisler, Tom Wollschläger, M. H. I. Abdalla +2

Current LLM alignment methods are readily broken through specifically crafted adversarial prompts. While crafting adversarial prompts using discrete optimization is highly effectiv…

cs.LG2025

Uncertainty for Active Learning on Graphs

Dominik Fuchsgruber, Tom Wollschläger, Bertrand Charpentier +2

Uncertainty Sampling is an Active Learning strategy that aims to improve the data efficiency of machine learning models by iteratively acquiring labels of data points with the high…