9 papers
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…
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…
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…
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…
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…
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…