10 citations · 10 across the 1 of their papers we have counts for
3 papers
Noise Injection Reveals Hidden Capabilities of Sandbagging Language Models
Cameron Tice, Philipp Alexander Kreer, Nathan Helm-Burger +7
Capability evaluations play a crucial role in assessing and regulating frontier AI systems. The effectiveness of these evaluations faces a significant challenge: strategic underper…
The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning
Nathaniel Li, Alexander Pan, Anjali Gopal +54
The White House Executive Order on Artificial Intelligence highlights the risks of large language models (LLMs) empowering malicious actors in developing biological, cyber, and che…
Will releasing the weights of future large language models grant widespread access to pandemic agents?
Anjali Gopal, Nathan Helm-Burger, Lennart Justen +6
Large language models can benefit research and human understanding by providing tutorials that draw on expertise from many different fields. A properly safeguarded model will refus…