Author

W. Samek

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Oct 2026

Heads of Security: Learned Attention Gates Improve Prompt Injection Robustness

Heads of Security (HoS), a prompt injection defense that enforces instruction-data separation via a small set of learned per-head attention gates, is introduced and shows that prompt injection robustness can be achieved and improved through targeted attention interventions.

Igor Shilov, Xiao-Xue Yang, Alexander Panfilov et al. · 0 citations

#small language model Preprint Oct 2026

Argument Graph Uncertainty: Quantifying Uncertainty from the Logical Structure of Reasoning Chains

This work introduces Argument Graph Uncertainty, a post-hoc framework for multiple choice question tasks that estimates model confidence directly from the logical structure of a single chain-of-thought reasoning trace, and demonstrates through extensive combination analyses that argument graph uncertainty captures an o...

S. Baur, Sumire Honda, W. Samek et al. · 0 citations