← all papers · overview

Emerging Safety Attack And Defense In Federated Instruction Tuning Of Large Language Models

Abstract

Federated learning (FL) enables multiple parties to collaboratively fine-tune an large language model (LLM) without the need of direct data sharing. Ideally, by training on decentralized data that is aligned with human preferences and safety principles, federated instruction tuning can result in an LLM that could behave in a helpful and safe manner. In this paper, we for the first time reveal the

Related papers

Ranked by semantic similarity — how closely each paper's abstract matches this one (100% = near-identical topic).