8 citations · 24 across the 16 of their papers we have counts for
4 papers · 1 filter
Model Hypnosis: Strong control of AI via additive subliminal effects
Enric Boix-Adsera, Benedict Tessler
We demonstrate that AI models are broadly susceptible to a phenomenon we call model hypnosis, in which individually weak and seemingly irrelevant cues in the prompt can be systemat…
Toward universal steering and monitoring of AI models
Daniel Beaglehole, Adityanarayanan Radhakrishnan, Enric Boix-Adserà +1
Modern AI models contain much of human knowledge, yet understanding of their internal representation of this knowledge remains elusive. Characterizing the structure and properties…
Prompts have evil twins
Rimon Melamed, Lucas H. McCabe, Tanay Wakhare +3
We discover that many natural-language prompts can be replaced by corresponding prompts that are unintelligible to humans but that provably elicit similar behavior in language mode…
When can transformers reason with abstract symbols?
Enric Boix-Adsera, Omid Saremi, Emmanuel Abbe +3
We investigate the capabilities of transformer models on relational reasoning tasks. In these tasks, models are trained on a set of strings encoding abstract relations, and are the…