6 papers
Forcing Diffuse Distributions out of Language Models
Yiming Zhang, Avi Schwarzschild, Nicholas Carlini +2
Despite being trained specifically to follow user instructions, today's instructiontuned language models perform poorly when instructed to produce random outputs. For example, when…
Effective Prompt Extraction from Language Models
Yiming Zhang, Nicholas Carlini, Daphne Ippolito
The text generated by large language models is commonly controlled by prompting, where a prompt prepended to a user's query guides the model's output. The prompts used by companies…
RAID: A Shared Benchmark for Robust Evaluation of Machine-Generated Text Detectors
Liam Dugan, Alyssa Hwang, Filip Trhlik +5
Many commercial and open-source models claim to detect machine-generated text with extremely high accuracy (99% or more). However, very few of these detectors are evaluated on shar…
LMD3: Language Model Data Density Dependence
John Kirchenbauer, Garrett Honke, Gowthami Somepalli +5
We develop a methodology for analyzing language model task performance at the individual example level based on training data density estimation. Experiments with paraphrasing as a…
Are aligned neural networks adversarially aligned?
Nicholas Carlini, Milad Nasr, Christopher A. Choquette-Choo +8
Large language models are now tuned to align with the goals of their creators, namely to be "helpful and harmless." These models should respond helpfully to user questions, but ref…
Gemma: Open Models Based on Gemini Research and Technology
Gemma Team, Thomas Mesnard, Cassidy Hardin +105
This work introduces Gemma, a family of lightweight, state-of-the art open models built from the research and technology used to create Gemini models. Gemma models demonstrate stro…