← all papers · overview

Safety Arithmetic: A Framework For Test-time Safety Alignment Of Language Models By Steering Parameters And Activations

Abstract

Ensuring the safe alignment of large language models (LLMs) with human values is critical as they become integral to applications like translation and question answering. Current alignment methods struggle with dynamic user intentions and complex objectives, making models vulnerable to generating harmful content. We propose Safety Arithmetic, a training-free framework enhancing LLM safety across d

Related papers

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