565 citations · 613 across the 6 of their papers we have counts for
5 papers · 1 filter
Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs
Mantas Mazeika, Xuwang Yin, Rishub Tamirisa +8
As AIs rapidly advance and become more agentic, the risk they pose is governed not only by their capabilities but increasingly by their propensities, including goals and values. Tr…
Humanity's Last Exam
Long Phan, Alice Gatti, Ziwen Han +1168
Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achi…
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…
Temperature as Uncertainty in Contrastive Learning
Oliver Zhang, Mike Wu, Jasmine Bayrooti +1
Contrastive learning has demonstrated great capability to learn representations without annotations, even outperforming supervised baselines. However, it still lacks important prop…
Optimal Transport Based Generative Autoencoders
Oliver Zhang, Ruei-Sung Lin, Yuchuan Gou
The field of deep generative modeling is dominated by generative adversarial networks (GANs). However, the training of GANs often lacks stability, fails to converge, and suffers fr…