Search Results for author:
Found 3 papers, 0 papers with code
Can LLMs get help from other LLMs without revealing private information?
In this work, we show the feasibility of applying cascade systems in such setups by equipping the local model with privacy-preserving techniques that reduce the risk of leaking private information when querying the remote model.
Social Learning: Towards Collaborative Learning with Large Language Models
We present and evaluate two approaches for knowledge transfer between LLMs.
Federated Learning for Ranking Browser History Suggestions
To improve the ranking of suggestions in the Firefox URL bar, we make use of Federated Learning to train a model on user interactions in a privacy-preserving way.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
