Can LLMs get help from other LLMs without revealing private information?

arXiv:2404.01041v1 Announce Type: new
Abstract: Cascades are a common type of machine learning systems in which a large, remote model can be queried if a local model is not able to accurately label a user's data by itself. Serving stacks for large language models (LLMs) increasingly use cascades due to their ability to preserve task performance while dramatically reducing inference costs. However, applying cascade systems in situations where the local model has access to sensitive data constitutes a significant privacy …

abstract arxiv cs.ai cs.cr cs.lg cs.ma data information language language models large language large language models learning systems llms machine machine learning stacks systems type