Author

Mohamed Akrout

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.

Preprint Aug 2026

Enforcing LLM Safety through DMD-based Classification of Prompt-Response Embedding Dynamics

Large Language Models (LLMs) are increasingly deployed in high-stakes applications, yet their tendency to generate toxic, harmful, or policy-violating content poses significant risks. Detecting these unsafe outputs efficiently in a black-box manner remains an open challenge. In this paper, we extend a recently proposed...

Mohamed Akrout, O. Kotevska, Dan Wilson · 0 citations

#machine learning May 2026

Low-Cost Black-Box Detection of LLM Hallucinations via Dynamical System Prediction

This approach enables low-cost hallucination detection in a single-sample pass, avoiding the need for secondary sampling or external grounding, and achieves state-of-the-art performance with reduced resource overhead.

Dan Wilson, Mohamed Akrout · arXiv.org · 3 citations