1 citations · 1 across the 2 of their papers we have counts for
4 papers
STAR: SocioTechnical Approach to Red Teaming Language Models
Laura Weidinger, John Mellor, Bernat Guillen Pegueroles +9
This research introduces STAR, a sociotechnical framework that improves on current best practices for red teaming safety of large language models. STAR makes two key contributions:…
Optimal control with learning on the fly: a toy problem
Charles L. Fefferman, Bernat Guillen Pegueroles, Clarence W. Rowley +1
We exhibit optimal control strategies for a simple toy problem in which the underlying dynamics depend on a parameter that is initially unknown and must be learned. We consider a c…
Sensitivity and safety of fully probabilistic control
Bernat Guillen Pegueroles, Giovanni Russo
In this paper we present a sensitivity analysis for the so-called fully probabilistic control scheme. This scheme attempts to control a system modeled via a probability density fun…
Structure Learning from Time Series with False Discovery Control
Bernat Guillen Pegueroles, Bhanukiran Vinzamuri, Karthikeyan Shanmugam +3
We consider the Granger causal structure learning problem from time series data. Granger causal algorithms predict a 'Granger causal effect' between two variables by testing if pre…