24 citations · 43 across the 5 of their papers we have counts for
Showing 2023Show all
2 papers · 1 filter
cs.CR2023★ 3 cited
Exploiting Novel GPT-4 APIs
Kellin Pelrine, Mohammad Taufeeque, Michał Zając +2
Language model attacks typically assume one of two extreme threat models: full white-box access to model weights, or black-box access limited to a text generation API. However, rea…
cs.CL2023★ 24 cited
Inverse Scaling: When Bigger Isn't Better
Ian R. McKenzie, Alexander Lyzhov, Michael Pieler +24
Work on scaling laws has found that large language models (LMs) show predictable improvements to overall loss with increased scale (model size, training data, and compute). Here, w…