3 citations · 3 across the 5 of their papers we have counts for
3 papers · 1 filter
Meta-Models: An Architecture for Decoding LLM Behaviors Through Interpreted Embeddings and Natural Language
Anthony Costarelli, Mat Allen, Severin Field
As Large Language Models (LLMs) become increasingly integrated into our daily lives, the potential harms from deceptive behavior underlie the need for faithfully interpreting their…
What Features in Prompts Jailbreak LLMs? Investigating the Mechanisms Behind Attacks
Nathalie Kirch, Constantin Weisser, Severin Field +2
Jailbreaks have been a central focus of research regarding the safety and reliability of large language models (LLMs), yet the mechanisms underlying these attacks remain poorly und…
Poser: Unmasking Alignment Faking LLMs by Manipulating Their Internals
Joshua Clymer, Caden Juang, Severin Field
Like a criminal under investigation, Large Language Models (LLMs) might pretend to be aligned while evaluated and misbehave when they have a good opportunity. Can current interpret…