no code implementations • 15 Apr 2024 • Raven Beutner, Bernd Finkbeiner, Hadar Frenkel, Niklas Metzger
For the parallel model, we show that the monitoring of the second-order hyperproperties of Hyper$^2$LTL$_f$ can be reduced to monitoring first-order hyperproperties.
no code implementations • 4 Jun 2022 • Christopher Hahn, Frederik Schmitt, Julia J. Tillman, Niklas Metzger, Julian Siber, Bernd Finkbeiner
We study the generalization abilities of language models when translating natural language into formal specifications with complex semantics.
1 code implementation • 30 May 2022 • Niklas Metzger, Christopher Hahn, Julian Siber, Frederik Schmitt, Bernd Finkbeiner
In this paper, we study the computation of how much an input token in a Transformer model influences its prediction.