11 citations · 47 across the 48 of their papers we have counts for
55 papers
Chain of Thought Monitoring Can Fail Even When CoT Is Necessary
Lennart Bürger, Piotr Komorowski, Moritz Weckbecker +4
Chain of Thought (CoT) monitoring is used by frontier labs to detect misbehaviour of AI systems. Yet, its reliability remains poorly understood. We attribute this to the lack of a…
Stress-Testing LLM Lie Detectors: Role-Play Failures and Spurious Correlations
Maximilian von Klinski, Sebastian Lapuschkin, Wojciech Samek +1
Lie detection probes aim to predict from a language model's internal states whether its output is truthful or dishonest. However, role-play complicates what "truth" means for an LL…
Can Data Attribution Filter Out Subliminal Learning? Not Reliably
Moritz Weckbecker, Sweta Jena, Jonas Müller +5
Subliminal learning allows language models to transmit behavioral traits through training data with no obvious semantic relationship to those traits, undermining content-based data…
ResLRP: The Role of Residual Cancellation in Attribution Instability in Vision Transformers
Jim Berend, Reduan Achtibat, Daniel Schäffer +4
Vision Transformers (ViTs) are central to most modern vision models, yet obtaining input attributions that are fine-grained, faithful, and stable remains challenging. Layer-wise Re…
Safety Signals to Verify NetOps Agents with Action-Level Granularity
Tobias Labarta, Frederik Pahde, Novak Boškov +6
Agentic Network Operations (NetOps) are an emerging paradigm promising to enable workload-aware, self-adjustable, and reliable autonomous networks. While agents have proven their v…
ICON decomposition: Multivariate concept auditing reveals shortcuts that neural networks rely on
Roshan Prakash Rane, Marco Simnacher, Manuel Pfeuffer +7
Deep neural networks often exploit spurious associations, a failure known as shortcut learning. Before deployment, models should therefore be audited for reliance on concepts such…