565 citations · 613 across the 6 of their papers we have counts for
7 papers
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…
MAUD: An Expert-Annotated Legal NLP Dataset for Merger Agreement Understanding
Steven H. Wang, Antoine Scardigli, Leonard Tang +7
Reading comprehension of legal text can be a particularly challenging task due to the length and complexity of legal clauses and a shortage of expert-annotated datasets. To address…
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
Aarohi Srivastava, Abhinav Rastogi, Abhishek Rao +448
Language models demonstrate both quantitative improvement and new qualitative capabilities with increasing scale. Despite their potentially transformative impact, these new capabil…
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…