167 citations · 643 across the 64 of their papers we have counts for
16 papers · 1 filter
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…
Long-Range Graph Wavelet Networks
Filippo Guerranti, Fabrizio Forte, Simon Geisler +1
Modeling long-range interactions, the propagation of information across distant parts of a graph, is a central challenge in graph machine learning. Graph wavelets, inspired by mult…
Scalable Object Detection in the Car Interior With Vision Foundation Models
Sebastian Schmidt, Bálint Mészáros, Ahmet Firintepe +1
AI tasks in the car interior like identifying and localizing externally introduced objects is crucial for response quality of personal assistants. However, computational resources…
SAFT: Structure-Aware Fine-Tuning of LLMs for AMR-to-Text Generation
Rafiq Kamel, Filippo Guerranti, Simon Geisler +1
Large Language Models (LLMs) are increasingly applied to tasks involving structured inputs such as graphs. Abstract Meaning Representations (AMRs), which encode rich semantics as d…
Sampling-aware Adversarial Attacks Against Large Language Models
Tim Beyer, Yan Scholten, Leo Schwinn +1
To guarantee safe and robust deployment of large language models (LLMs) at scale, it is critical to accurately assess their adversarial robustness. Existing adversarial attacks typ…
UnHiPPO: Uncertainty-aware Initialization for State Space Models
Marten Lienen, Abdullah Saydemir, Stephan Günnemann
State space models are emerging as a dominant model class for sequence problems with many relying on the HiPPO framework to initialize their dynamics. However, HiPPO fundamentally…
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…
Accurate Ab-initio Neural-network Solutions to Large-Scale Electronic Structure Problems
Michael Scherbela, Nicholas Gao, Philipp Grohs +1
We present finite-range embeddings (FiRE), a novel wave function ansatz for accurate large-scale ab-initio electronic structure calculations. Compared to contemporary neural-networ…
OmegAMP: Targeted AMP Discovery via Biologically Informed Generation
Diogo Soares, Leon Hetzel, Paulina Szymczak +6
Deep learning-based antimicrobial peptide (AMP) discovery faces critical challenges such as limited controllability, lack of representations that efficiently model antimicrobial pr…
Prior2Former -- Evidential Modeling of Mask Transformers for Assumption-Free Open-World Panoptic Segmentation
Sebastian Schmidt, Julius Körner, Dominik Fuchsgruber +3
In panoptic segmentation, individual instances must be separated within semantic classes. As state-of-the-art methods rely on a pre-defined set of classes, they struggle with novel…
LLM-Safety Evaluations Lack Robustness
Tim Beyer, Sophie Xhonneux, Simon Geisler +3
In this paper, we argue that current safety alignment research efforts for large language models are hindered by many intertwined sources of noise, such as small datasets, methodol…
REINFORCE Adversarial Attacks on Large Language Models: An Adaptive, Distributional, and Semantic Objective
Simon Geisler, Tom Wollschläger, M. H. I. Abdalla +3
To circumvent the alignment of large language models (LLMs), current optimization-based adversarial attacks usually craft adversarial prompts by maximizing the likelihood of a so-c…
Adversarial Alignment for LLMs Requires Simpler, Reproducible, and More Measurable Objectives
Leo Schwinn, Yan Scholten, Tom Wollschläger +4
Misaligned research objectives have considerably hindered progress in adversarial robustness research over the past decade. For instance, an extensive focus on optimizing target me…
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…
Rethinking Link Prediction for Directed Graphs
Mingguo He, Yuhe Guo, Yanping Zheng +3
Link prediction for directed graphs is a crucial task with diverse real-world applications. Recent advances in embedding methods and Graph Neural Networks (GNNs) have shown promisi…