3 papers
cs.CR2025
Chasing Shadows: Pitfalls in LLM Security Research
Jonathan Evertz, Niklas Risse, Nicolai Neuer +12
Large language models (LLMs) are increasingly prevalent in security research. Their unique characteristics, however, introduce challenges that undermine established paradigms of re…
cs.LG2025
Learning Dynamics in Memristor-Based Equilibrium Propagation
Michael Döll, Andreas Müller, Bernd Ulmann
Memristor-based in-memory computing has emerged as a promising paradigm to overcome the constraints of the von Neumann bottleneck and the memory wall by enabling fully parallelisab…
cs.CL2024
Evaluating Gender Bias in Large Language Models
Michael Döll, Markus Döhring, Andreas Müller
Gender bias in artificial intelligence has become an important issue, particularly in the context of language models used in communication-oriented applications. This study examine…