118 citations · 601 across the 20 of their papers we have counts for
20 papers
Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming
Mrinank Sharma, Meg Tong, Jesse Mu +40
Large language models (LLMs) are vulnerable to universal jailbreaks-prompting strategies that systematically bypass model safeguards and enable users to carry out harmful processes…
On Targeted Manipulation and Deception when Optimizing LLMs for User Feedback
Marcus Williams, Micah Carroll, Adhyyan Narang +3
As LLMs become more widely deployed, there is increasing interest in directly optimizing for feedback from end users (e.g. thumbs up) in addition to feedback from paid annotators.…
Digital Twin Earth -- Coasts: Developing a fast and physics-informed surrogate model for coastal floods via neural operators
Peishi Jiang, Nis Meinert, Helga Jordão +8
Developing fast and accurate surrogates for physics-based coastal and ocean models is an urgent need due to the coastal flood risk under accelerating sea level rise, and the comput…
Progress in developing a hybrid deep learning algorithm for identifying and locating primary vertices
Simon Akar, Gowtham Atluri, Thomas Boettcher +7
The locations of proton-proton collision points in LHC experiments are called primary vertices (PVs). Preliminary results of a hybrid deep learning algorithm for identifying and lo…
Enhancing searches for resonances with machine learning and moment decomposition
Ouail Kitouni, Benjamin Nachman, Constantin Weisser +1
A key challenge in searches for resonant new physics is that classifiers trained to enhance potential signals must not induce localized structures. Such structures could result in…
An updated hybrid deep learning algorithm for identifying and locating primary vertices
Simon Akar, Thomas J. Boettcher, Sarah Carl +5
We present an improved hybrid algorithm for vertexing, that combines deep learning with conventional methods. Even though the algorithm is a generic approach to vertex finding, we…