98 citations · 131 across the 5 of their papers we have counts for
5 papers
Prmpt: Sanitizing Sensitive Prompts for LLMs
Amrita Roy Chowdhury, David Glukhov, Divyam Anshumaan +4
The rise of large language models (LLMs) has introduced new privacy challenges, particularly during inference where sensitive information in prompts may be exposed to proprietary L…
Societal Alignment Frameworks Can Improve LLM Alignment
Karolina Stańczak, Nicholas Meade, Mehar Bhatia +14
Recent progress in large language models (LLMs) has focused on producing responses that meet human expectations and align with shared values - a process coined alignment. However,…
Temporal-Difference Learning Using Distributed Error Signals
Jonas Guan, Shon Eduard Verch, Claas Voelcker +3
A computational problem in biological reward-based learning is how credit assignment is performed in the nucleus accumbens (NAc). Much research suggests that NAc dopamine encodes t…
Thieves on Sesame Street! Model Extraction of BERT-based APIs
Kalpesh Krishna, Gaurav Singh Tomar, Ankur P. Parikh +2
We study the problem of model extraction in natural language processing, in which an adversary with only query access to a victim model attempts to reconstruct a local copy of that…
Analyzing and Improving Representations with the Soft Nearest Neighbor Loss
Nicholas Frosst, Nicolas Papernot, Geoffrey Hinton
We explore and expand the to measure the of class manifolds in representation space: i.e., how close pairs of points f…