← Search

Ariel Herbert-Voss

2 accepted papers

2024

The WMDP Benchmark: Measuring and Reducing Malicious Use with Unlearning

ICML 2024poster

The White House Executive Order on Artificial Intelligence highlights the risks of large language models (LLMs) empowering malicious actors in developing biological, cyber, and chemical weapons. To measure these risks, government institutions and major AI labs are developing evaluations for hazardou…

Cited by 145SourcePDFScholar
2020

Language Models are Few-Shot Learners

NeurIPS 2020oral

We demonstrate that scaling up language models greatly improves task-agnostic, few-shot performance, sometimes even becoming competitive with prior state-of-the-art fine-tuning approaches. Specifically, we train GPT-3, an autoregressive language model with 175 billion parameters, 10x more than any p…