3 papers
cs.CL2024
FLRT: Fluent Student-Teacher Redteaming
T. Ben Thompson, Michael Sklar
Many publicly available language models have been safety tuned to reduce the likelihood of toxic or liability-inducing text. To redteam or jailbreak these models for compliance wit…
cs.CL2024
Fluent dreaming for language models
T. Ben Thompson, Zygimantas Straznickas, Michael Sklar
Feature visualization, also known as "dreaming", offers insights into vision models by optimizing the inputs to maximize a neuron's activation or other internal component. However,…
stat.ME2022
Guarantees for Comprehensive Simulation Assessment of Statistical Methods
James Yang, T. Ben Thompson, Michael Sklar
Simulation can evaluate a statistical method for properties such as Type I Error, FDR, or bias on a grid of hypothesized parameter values. But what about the gaps between the grid-…