65 citations · 125 across the 20 of their papers we have counts for
4 papers · 1 filter
Enhancing AI Safety Through the Fusion of Low Rank Adapters
Satya Swaroop Gudipudi, Sreeram Vipparla, Harpreet Singh +2
Instruction fine-tuning of large language models (LLMs) is a powerful method for improving task-specific performance, but it can inadvertently lead to a phenomenon where models gen…
A Cognac Shot To Forget Bad Memories: Corrective Unlearning for Graph Neural Networks
Varshita Kolipaka, Akshit Sinha, Debangan Mishra +4
Graph Neural Networks (GNNs) are increasingly being used for a variety of ML applications on graph data. Because graph data does not follow the independently and identically distri…
The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning
Nathaniel Li, Alexander Pan, Anjali Gopal +54
The White House Executive Order on Artificial Intelligence highlights the risks of large language models (LLMs) empowering malicious actors in developing biological, cyber, and che…
Corrective Machine Unlearning
Shashwat Goel, Ameya Prabhu, Philip Torr +2
Machine Learning models increasingly face data integrity challenges due to the use of large-scale training datasets drawn from the Internet. We study what model developers can do i…